From 3fcd10620f9bb4196559cb169d24e7798d229dcf Mon Sep 17 00:00:00 2001 From: Melanie I Stefan Date: Mon, 29 Feb 2016 11:38:17 +0000 Subject: [PATCH 01/21] new python notebook for the task of pulling github repo information from abstracts and looking them up using the github api --- src/find_github_repo.ipynb | 0 1 file changed, 0 insertions(+), 0 deletions(-) create mode 100644 src/find_github_repo.ipynb diff --git a/src/find_github_repo.ipynb b/src/find_github_repo.ipynb new file mode 100644 index 0000000..e69de29 From 21c1cbf91889d004e9341a6dde655ac84e5d286f Mon Sep 17 00:00:00 2001 From: Melanie I Stefan Date: Fri, 11 Mar 2016 19:04:00 +0000 Subject: [PATCH 02/21] try to create new ipynb and save --- src/find_github_repo.ipynb | 47 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) diff --git a/src/find_github_repo.ipynb b/src/find_github_repo.ipynb index e69de29..e1b19d4 100644 --- a/src/find_github_repo.ipynb +++ b/src/find_github_repo.ipynb @@ -0,0 +1,47 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "2" + ] + }, + "execution_count": 1, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "1+1" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 2", + "language": "python", + "name": "python2" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 2 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython2", + "version": "2.7.10" + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} From bda1d7ba7cd4affd8ba95a4c1f018e7555b6f5f7 Mon Sep 17 00:00:00 2001 From: Melanie I Stefan Date: Fri, 11 Mar 2016 19:08:44 +0000 Subject: [PATCH 03/21] wrote up a list of aims --- src/find_github_repo.ipynb | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/src/find_github_repo.ipynb b/src/find_github_repo.ipynb index e1b19d4..a8f4a6e 100644 --- a/src/find_github_repo.ipynb +++ b/src/find_github_repo.ipynb @@ -1,5 +1,19 @@ { "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# find_github_repo\n", + "\n", + "## Goals\n", + "\n", + "- To extract the names of github repositories from Pubmed abstracts that mention github.\n", + "- To use the github api to get author and contribution data about those repositories\n", + "- To create a dataset linking the two\n", + "\n" + ] + }, { "cell_type": "code", "execution_count": 1, From 27282c61cae24ccb9b26d82d0e6d2bb05adb6216 Mon Sep 17 00:00:00 2001 From: Melanie I Stefan Date: Fri, 11 Mar 2016 19:15:28 +0000 Subject: [PATCH 04/21] change to data directory; list content --- src/find_github_repo.ipynb | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/src/find_github_repo.ipynb b/src/find_github_repo.ipynb index a8f4a6e..74f0015 100644 --- a/src/find_github_repo.ipynb +++ b/src/find_github_repo.ipynb @@ -16,7 +16,7 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 6, "metadata": { "collapsed": false }, @@ -24,16 +24,18 @@ { "data": { "text/plain": [ - "2" + "['github_pubs.xml', 'README.md']" ] }, - "execution_count": 1, + "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "1+1" + "import os\n", + "os.chdir(\"../data/\")\n", + "os.listdir(\"./\")" ] } ], From 09212e1a6e33bb7f73062c3b66e45928cc345075 Mon Sep 17 00:00:00 2001 From: Melanie I Stefan Date: Tue, 15 Mar 2016 13:31:16 +0000 Subject: [PATCH 05/21] libraries for xml parsing --- src/find_github_repo.ipynb | 30 ++++++++++++++++++++++++++++-- 1 file changed, 28 insertions(+), 2 deletions(-) diff --git a/src/find_github_repo.ipynb b/src/find_github_repo.ipynb index 74f0015..5b93982 100644 --- a/src/find_github_repo.ipynb +++ b/src/find_github_repo.ipynb @@ -14,9 +14,16 @@ "\n" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "First, set working directory" + ] + }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 1, "metadata": { "collapsed": false }, @@ -27,7 +34,7 @@ "['github_pubs.xml', 'README.md']" ] }, - "execution_count": 6, + "execution_count": 1, "metadata": {}, "output_type": "execute_result" } @@ -37,6 +44,25 @@ "os.chdir(\"../data/\")\n", "os.listdir(\"./\")" ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Next, import libraries needed for xml parsing" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "import xml.etree.ElementTree as ET\n", + "import datetime" + ] } ], "metadata": { From cd71f02bf7b8ec3f5882a9d8a95eca07ed87f1f0 Mon Sep 17 00:00:00 2001 From: Melanie I Stefan Date: Tue, 15 Mar 2016 13:50:24 +0000 Subject: [PATCH 06/21] successfully imported xml and created data frameo --- src/find_github_repo.ipynb | 303 ++++++++++++++++++++++++++++++++++++- 1 file changed, 302 insertions(+), 1 deletion(-) diff --git a/src/find_github_repo.ipynb b/src/find_github_repo.ipynb index 5b93982..1db1af5 100644 --- a/src/find_github_repo.ipynb +++ b/src/find_github_repo.ipynb @@ -11,7 +11,8 @@ "- To extract the names of github repositories from Pubmed abstracts that mention github.\n", "- To use the github api to get author and contribution data about those repositories\n", "- To create a dataset linking the two\n", - "\n" + "\n", + "The bit that reads in xml files and extracts article information to a data frame is from Kevin's xml_parsing script" ] }, { @@ -63,6 +64,306 @@ "import xml.etree.ElementTree as ET\n", "import datetime" ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Create Article class definition" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "class Article(object):\n", + " \"\"\"Container for publication info\"\"\"\n", + " def __init__(self, pmid, pubdate, journal, title, abstract, authors):\n", + " self.pmid = pmid\n", + " self.pubdate = pubdate\n", + " self.journal = journal\n", + " self.title = title\n", + " self.abstract = abstract\n", + " self.authors = authors\n", + " def __repr__(self):\n", + " return \"
\".format(self.pmid)\n", + "\n", + " def get_authors(self):\n", + " for author in self.authors:\n", + " yield author[\"Last\"], author[\"First\"]" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Article generator function" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "def parse_pubmed_xml(xml_file):\n", + " xml_handle = ET.parse(xml_file)\n", + " root = xml_handle.getroot()\n", + "\n", + " for Citation in root.iter(\"MedlineCitation\"):\n", + " pmid = Citation[0].text\n", + " pubdate = datetime.date(\n", + " int(Citation[1][0].text), # year\n", + " int(Citation[1][1].text), # month\n", + " int(Citation[1][2].text) # day\n", + " )\n", + " \n", + " Journal = next(Citation.iter(\"Journal\"))\n", + "\n", + " journal_title = Journal.find(\"ISOAbbreviation\").text\n", + " article_title = next(Citation.iter(\"ArticleTitle\")).text\n", + " \n", + " abstract = next(Citation.iter(\"AbstractText\")).text\n", + " try:\n", + " authors = [{\n", + " \"Last\": Author.find(\"LastName\").text,\n", + " \"First\": Author.find(\"ForeName\").text\n", + " } for Author in Citation.iter(\"Author\")]\n", + " except:\n", + " continue\n", + " \n", + " yield Article(pmid, pubdate, journal_title, article_title, abstract, authors)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Make data frame (this differs a bit from Kevin's code by including abstract also)" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " Abstract \\\n", + "26357045 Stability and sensitivity analyses of biologic... \n", + "25601296 Most electronic data capture (EDC) and electro... \n", + "25558360 Remotely sensed data - available at medium to ... \n", + "25553811 Whole-genome bisulfite sequencing (WGBS) is an... \n", + "25549775 A number of computational approaches have been... \n", + "25543048 Sampling the conformational space of biologica... \n", + "25540185 With rapidly increasing volumes of biological ... \n", + "25527832 Current strategies for SNP and INDEL discovery... \n", + "25526884 An absent word of a word y of length n is a wo... \n", + "25524895 VarSim is a framework for assessing alignment ... \n", + "25521965 Thyroid cancer is the most common endocrine tu... \n", + "25520192 RNA performs a diverse array of important func... \n", + "25514851 We describe an open-source kPAL package that f... \n", + "25505094 Circular permutation is an important type of p... \n", + "25505087 In bioinformatic applications, computationally... \n", + "25505086 All current mitochondrial haplogroup classific... \n", + "25504847 A standard approach to classifying sets of gen... \n", + "25481009 ICMA, a software framework to create 3D finite... \n", + "25481007 Kablammo is a web-based application that produ... \n", + "25480375 Expression quantitative trait loci (eQTL) stud... \n", + "25474353 Phylogenetic analyses which include fossils or... \n", + "25461763 Since the read lengths of high throughput sequ... \n", + "25452688 Mobile elements constitute greater than 45% of... \n", + "25435543 Isobaric labeling techniques coupled with high... \n", + "25431162 Post-translational modifications (PTMs) consti... \n", + "25428347 Genetic screens of an unprecedented scale have... \n", + "25422674 Rapid molecular typing of bacterial pathogens ... \n", + "25414364 Protein sequence and structure representation ... \n", + "25414349 The emergence of new sequencing technologies h... \n", + "25410596 Whole-genome sequences are now available for m... \n", + "... ... \n", + "22238257 CHROMATRA (CHROmatin Mapping Across TRAnscript... \n", + "22235263 Although complex diseases and traits are thoug... \n", + "22215819 Probabilistic logic programming offers a power... \n", + "25328913 Scientists are continually faced with the need... \n", + "22151646 Many metazoan genomes conserve chromosome-scal... \n", + "22080292 Digital Imaging and Communications in Medicine... \n", + "22017798 Genome-wide mapping of protein-DNA interaction... \n", + "21994228 Recent technological progress has greatly faci... \n", + "21911333 SPREAD is a user-friendly, cross-platform appl... \n", + "21899774 In bioinformatics projects, scientific workflo... \n", + "21824426 Temporal analysis of gene expression data has ... \n", + "21724594 MethylCoder is a software program that generat... \n", + "21685055 We report CRdata.org, a cloud-based, free, ope... \n", + "21685051 Methyl-Analyzer is a python package that analy... \n", + "21635747 The possibilities offered by next generation s... \n", + "21595876 Recovery of ribosomal small subunit genes by a... \n", + "21529350 The availability of bioinformatics web-based s... \n", + "21501495 It is difficult to accurately interpret chromo... \n", + "21493652 Analysis of genomic sequencing data requires e... \n", + "21478170 Bacterial Rho-independent terminators (RITs) a... \n", + "21357752 With the availability of genome-wide transcrip... \n", + "21296748 Gobe is a web-based tool for viewing comparati... \n", + "21169373 The Sample avAILability system-SAIL-is a web b... \n", + "21124986 Identifying transcription factor (TF) binding ... \n", + "20935049 The Sol Genomics Network (SGN; http://solgenom... \n", + "20798169 JCVI Metagenomics Reports (METAREP) is a Web 2... \n", + "20562450 Bridges is a heuristic search tool that uses s... \n", + "20529912 High-throughput data is providing a comprehens... \n", + "20421198 DendroPy is a cross-platform library for the P... \n", + "20106815 Short sequence motifs are an important class o... \n", + "\n", + " Authors Date \\\n", + "26357045 [(Shiraishi, Fumihide), (Yoshida, Erika), (Voi... 2015-09-11 \n", + "25601296 [(Dixit, Abhishek), (Dobson, Richard J B)] 2015-01-20 \n", + "25558360 [(Tuck, Sean L), (Phillips, Helen Rp), (Hintze... 2015-01-05 \n", + "25553811 [(Chen, Junfang), (Lutsik, Pavlo), (Akulenko, ... 2015-01-02 \n", + "25549775 [(Manini, Simone), (Antiga, Luca), (Botti, Lor... 2015-06-09 \n", + "25543048 [(Bouvier, Guillaume), (Desdouits, Nathan), (F... 2015-04-28 \n", + "25540185 [(Meinicke, Peter)] 2015-04-28 \n", + "25527832 [(Lindberg, Michael R), (Hall, Ira M), (Quinla... 2015-04-12 \n", + "25526884 [(Barton, Carl), (Heliou, Alice), (Mouchard, L... 2015-04-27 \n", + "25524895 [(Mu, John C), (Mohiyuddin, Marghoob), (Li, Ji... 2015-04-28 \n", + "25521965 [(Wu, Chengkun), (Schwartz, Jean-Marc), (Braba... 2014-12-19 \n", + "25520192 [(Gardner, Paul P), (Eldai, Hisham)] 2015-01-24 \n", + "25514851 [(Anvar, Seyed Yahya), (Khachatryan, Lusine), ... 2015-02-06 \n", + "25505094 [(Bliven, Spencer E), (Bourne, Philip E), (Prl... 2015-04-12 \n", + "25505087 [(Völkel, Gunnar), (Lausser, Ludwig), (Schmid,... 2015-04-12 \n", + "25505086 [(Navarro-Gomez, Daniel), (Leipzig, Jeremy), (... 2015-04-12 \n", + "25504847 [(Haubold, Bernhard), (Klötzl, Fabian), (Pfaff... 2015-04-12 \n", + "25481009 [(Hussan, Jagir R), (Hunter, Peter J), (Gladdi... 2015-04-12 \n", + "25481007 [(Wintersinger, Jeff A), (Wasmuth, James D)] 2015-04-12 \n", + "25480375 [(Harvey, Chris T), (Moyerbrailean, Gregory A)... 2015-04-12 \n", + "25474353 [(Gavryushkina, Alexandra), (Welch, David), (S... 2014-12-05 \n", + "25461763 [(Zhu, Xiao), (Leung, Henry C M), (Chin, Franc... 2014-12-03 \n", + "25452688 [(Lee, Wan-Ping), (Wu, Jiantao), (Marth, Gabor... 2014-12-02 \n", + "25435543 [(Sheng, Quanhu), (Li, Rongxia), (Dai, Jie), (... 2015-01-31 \n", + "25431162 [(Warnecke, Andreas), (Sandalova, Tatyana), (A... 2015-04-27 \n", + "25428347 [(Diaz, Aaron A), (Qin, Han), (Ramalho-Santos,... 2015-02-18 \n", + "25422674 [(Inouye, Michael), (Dashnow, Harriet), (Raven... 2014-11-25 \n", + "25414364 [(Hirsh, Layla), (Piovesan, Damiano), (Giollo,... 2015-04-03 \n", + "25414349 [(Croucher, Nicholas J), (Page, Andrew J), (Co... 2015-02-18 \n", + "25410596 [(Treangen, Todd J), (Ondov, Brian D), (Koren,... 2015-01-07 \n", + "... ... ... \n", + "22238257 [(Hentrich, Thomas), (Schulze, Julia M), (Embe... 2012-03-01 \n", + "22235263 [(Peltola, Tomi), (Marttinen, Pekka), (Jula, A... 2012-01-11 \n", + "22215819 [(Mørk, Søren), (Holmes, Ian)] 2012-03-01 \n", + "25328913 [(Fenwick, Matthew), (Sesanker, Colbert), (Sch... 2014-10-20 \n", + "22151646 [(Lv, Jie), (Havlak, Paul), (Putnam, Nicholas H)] 2011-12-13 \n", + "22080292 [(Langer, Steve G)] 2012-03-07 \n", + "22017798 [(Pinello, Luca), (Lo Bosco, Giosuè), (Hanlon,... 2012-01-06 \n", + "21994228 [(Riba-Grognuz, Oksana), (Keller, Laurent), (F... 2011-12-13 \n", + "21911333 [(Bielejec, Filip), (Rambaut, Andrew), (Suchar... 2011-10-06 \n", + "21899774 [(Mishima, Hiroyuki), (Sasaki, Kensaku), (Tana... 2011-09-29 \n", + "21824426 [(Jethava, Vinay), (Bhattacharyya, Chiranjib),... 2011-09-12 \n", + "21724594 [(Pedersen, Brent), (Hsieh, Tzung-Fu), (Ibarra... 2011-08-19 \n", + "21685055 [(Bolouri, Hamid), (Dulepet, Rajiv), (Angerman... 2011-08-05 \n", + "21685051 [(Xin, Yurong), (Ge, Yongchao), (Haghighi, Fat... 2011-08-05 \n", + "21635747 [(Blanca, Jose M), (Pascual, Laura), (Ziarsolo... 2011-06-28 \n", + "21595876 [(Miller, Christopher S), (Baker, Brett J), (T... 2011-10-20 \n", + "21529350 [(Oshita, Kazuki), (Arakawa, Kazuharu), (Tomit... 2011-05-26 \n", + "21501495 [(Tang, Haibao), (Lyons, Eric), (Pedersen, Bre... 2011-05-09 \n", + "21493652 [(Barnett, Derek W), (Garrison, Erik K), (Quin... 2011-06-03 \n", + "21478170 [(Gardner, Paul P), (Barquist, Lars), (Bateman... 2011-08-09 \n", + "21357752 [(Washietl, Stefan), (Findeiss, Sven), (Müller... 2011-03-22 \n", + "21296748 [(Pedersen, Brent S), (Tang, Haibao), (Freelin... 2011-03-30 \n", + "21169373 [(Gostev, Mikhail), (Fernandez-Banet, Julio), ... 2011-02-10 \n", + "21124986 [(Miller, Andrew K), (Print, Cristin G), (Niel... 2010-12-02 \n", + "20935049 [(Bombarely, Aureliano), (Menda, Naama), (Tecl... 2010-12-23 \n", + "20798169 [(Goll, Johannes), (Rusch, Douglas B), (Tanenb... 2010-10-08 \n", + "20562450 [(Kondrashov, Alexey S), (Assis, Raquel)] 2010-08-06 \n", + "20529912 [(Vaske, Charles J), (Benz, Stephen C), (Sanbo... 2010-06-09 \n", + "20421198 [(Sukumaran, Jeet), (Holder, Mark T)] 2010-06-09 \n", + "20106815 [(Piipari, Matias), (Down, Thomas A), (Saini, ... 2010-03-08 \n", + "\n", + " Journal \n", + "26357045 IEEE/ACM Trans Comput Biol Bioinform \n", + "25601296 JMIR Med Inform \n", + "25558360 Ecol Evol \n", + "25553811 J Bioinform Comput Biol \n", + "25549775 Ann Biomed Eng \n", + "25543048 Bioinformatics \n", + "25540185 Bioinformatics \n", + "25527832 Bioinformatics \n", + "25526884 BMC Bioinformatics \n", + "25524895 Bioinformatics \n", + "25521965 BMC Med Genomics \n", + "25520192 Nucleic Acids Res. \n", + "25514851 Genome Biol. \n", + "25505094 Bioinformatics \n", + "25505087 Bioinformatics \n", + "25505086 Bioinformatics \n", + "25504847 Bioinformatics \n", + "25481009 Bioinformatics \n", + "25481007 Bioinformatics \n", + "25480375 Bioinformatics \n", + "25474353 PLoS Comput. Biol. \n", + "25461763 PLoS ONE \n", + "25452688 Cancer Inform \n", + "25435543 Mol. Cell Proteomics \n", + "25431162 BMC Bioinformatics \n", + "25428347 Nucleic Acids Res. \n", + "25422674 Genome Med \n", + "25414364 Bioinformatics \n", + "25414349 Nucleic Acids Res. \n", + "25410596 Genome Biol. \n", + "... ... \n", + "22238257 Bioinformatics \n", + "22235263 PLoS ONE \n", + "22215819 Bioinformatics \n", + "25328913 Proc Int Conf Inf Technol New Gener \n", + "22151646 BMC Bioinformatics \n", + "22080292 J Digit Imaging \n", + "22017798 BMC Bioinformatics \n", + "21994228 Bioinformatics \n", + "21911333 Bioinformatics \n", + "21899774 BMC Res Notes \n", + "21824426 BMC Bioinformatics \n", + "21724594 Bioinformatics \n", + "21685055 Bioinformatics \n", + "21685051 Bioinformatics \n", + "21635747 BMC Genomics \n", + "21595876 Genome Biol. \n", + "21529350 Source Code Biol Med \n", + "21501495 BMC Bioinformatics \n", + "21493652 Bioinformatics \n", + "21478170 Nucleic Acids Res. \n", + "21357752 RNA \n", + "21296748 Bioinformatics \n", + "21169373 Bioinformatics \n", + "21124986 PLoS ONE \n", + "20935049 Nucleic Acids Res. \n", + "20798169 Bioinformatics \n", + "20562450 Bioinformatics \n", + "20529912 Bioinformatics \n", + "20421198 Bioinformatics \n", + "20106815 Bioinformatics \n", + "\n", + "[402 rows x 4 columns]\n" + ] + } + ], + "source": [ + "import pandas as pd\n", + "df = pd.DataFrame()\n", + "col_names = [\"Date\", \"Journal\", \"Authors\",\"Abstract\"]\n", + "\n", + "for article in parse_pubmed_xml('github_pubs.xml'):\n", + " row = pd.Series([article.pubdate, article.journal, [(author[0], author[1]) for author in article.get_authors()],\n", + " article.abstract],name=article.pmid, index=col_names)\n", + " df = df.append(row)\n", + "\n", + "print(df)" + ] } ], "metadata": { From bb141f19917c898f9979ff543b650f0bfe7e902e Mon Sep 17 00:00:00 2001 From: Melanie I Stefan Date: Tue, 15 Mar 2016 14:24:52 +0000 Subject: [PATCH 07/21] find github url string from abstract --- src/find_github_repo.ipynb | 411 +++++++++++++++++++------------------ 1 file changed, 210 insertions(+), 201 deletions(-) diff --git a/src/find_github_repo.ipynb b/src/find_github_repo.ipynb index 1db1af5..5e74e0c 100644 --- a/src/find_github_repo.ipynb +++ b/src/find_github_repo.ipynb @@ -24,7 +24,7 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 11, "metadata": { "collapsed": false }, @@ -35,7 +35,7 @@ "['github_pubs.xml', 'README.md']" ] }, - "execution_count": 1, + "execution_count": 11, "metadata": {}, "output_type": "execute_result" } @@ -55,7 +55,7 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": 12, "metadata": { "collapsed": true }, @@ -74,7 +74,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 13, "metadata": { "collapsed": true }, @@ -106,7 +106,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 14, "metadata": { "collapsed": true }, @@ -150,206 +150,91 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 15, "metadata": { "collapsed": false }, "outputs": [ { - "name": "stdout", - "output_type": "stream", - "text": [ - " Abstract \\\n", - "26357045 Stability and sensitivity analyses of biologic... \n", - "25601296 Most electronic data capture (EDC) and electro... \n", - "25558360 Remotely sensed data - available at medium to ... \n", - "25553811 Whole-genome bisulfite sequencing (WGBS) is an... \n", - "25549775 A number of computational approaches have been... \n", - "25543048 Sampling the conformational space of biologica... \n", - "25540185 With rapidly increasing volumes of biological ... \n", - "25527832 Current strategies for SNP and INDEL discovery... \n", - "25526884 An absent word of a word y of length n is a wo... \n", - "25524895 VarSim is a framework for assessing alignment ... \n", - "25521965 Thyroid cancer is the most common endocrine tu... \n", - "25520192 RNA performs a diverse array of important func... \n", - "25514851 We describe an open-source kPAL package that f... \n", - "25505094 Circular permutation is an important type of p... \n", - "25505087 In bioinformatic applications, computationally... \n", - "25505086 All current mitochondrial haplogroup classific... \n", - "25504847 A standard approach to classifying sets of gen... \n", - "25481009 ICMA, a software framework to create 3D finite... \n", - "25481007 Kablammo is a web-based application that produ... \n", - "25480375 Expression quantitative trait loci (eQTL) stud... \n", - "25474353 Phylogenetic analyses which include fossils or... \n", - "25461763 Since the read lengths of high throughput sequ... \n", - "25452688 Mobile elements constitute greater than 45% of... \n", - "25435543 Isobaric labeling techniques coupled with high... \n", - "25431162 Post-translational modifications (PTMs) consti... \n", - "25428347 Genetic screens of an unprecedented scale have... \n", - "25422674 Rapid molecular typing of bacterial pathogens ... \n", - "25414364 Protein sequence and structure representation ... \n", - "25414349 The emergence of new sequencing technologies h... \n", - "25410596 Whole-genome sequences are now available for m... \n", - "... ... \n", - "22238257 CHROMATRA (CHROmatin Mapping Across TRAnscript... \n", - "22235263 Although complex diseases and traits are thoug... \n", - "22215819 Probabilistic logic programming offers a power... \n", - "25328913 Scientists are continually faced with the need... \n", - "22151646 Many metazoan genomes conserve chromosome-scal... \n", - "22080292 Digital Imaging and Communications in Medicine... \n", - "22017798 Genome-wide mapping of protein-DNA interaction... \n", - "21994228 Recent technological progress has greatly faci... \n", - "21911333 SPREAD is a user-friendly, cross-platform appl... \n", - "21899774 In bioinformatics projects, scientific workflo... \n", - "21824426 Temporal analysis of gene expression data has ... \n", - "21724594 MethylCoder is a software program that generat... \n", - "21685055 We report CRdata.org, a cloud-based, free, ope... \n", - "21685051 Methyl-Analyzer is a python package that analy... \n", - "21635747 The possibilities offered by next generation s... \n", - "21595876 Recovery of ribosomal small subunit genes by a... \n", - "21529350 The availability of bioinformatics web-based s... \n", - "21501495 It is difficult to accurately interpret chromo... \n", - "21493652 Analysis of genomic sequencing data requires e... \n", - "21478170 Bacterial Rho-independent terminators (RITs) a... \n", - "21357752 With the availability of genome-wide transcrip... \n", - "21296748 Gobe is a web-based tool for viewing comparati... \n", - "21169373 The Sample avAILability system-SAIL-is a web b... \n", - "21124986 Identifying transcription factor (TF) binding ... \n", - "20935049 The Sol Genomics Network (SGN; http://solgenom... \n", - "20798169 JCVI Metagenomics Reports (METAREP) is a Web 2... \n", - "20562450 Bridges is a heuristic search tool that uses s... \n", - "20529912 High-throughput data is providing a comprehens... \n", - "20421198 DendroPy is a cross-platform library for the P... \n", - "20106815 Short sequence motifs are an important class o... \n", - "\n", - " Authors Date \\\n", - "26357045 [(Shiraishi, Fumihide), (Yoshida, Erika), (Voi... 2015-09-11 \n", - "25601296 [(Dixit, Abhishek), (Dobson, Richard J B)] 2015-01-20 \n", - "25558360 [(Tuck, Sean L), (Phillips, Helen Rp), (Hintze... 2015-01-05 \n", - "25553811 [(Chen, Junfang), (Lutsik, Pavlo), (Akulenko, ... 2015-01-02 \n", - "25549775 [(Manini, Simone), (Antiga, Luca), (Botti, Lor... 2015-06-09 \n", - "25543048 [(Bouvier, Guillaume), (Desdouits, Nathan), (F... 2015-04-28 \n", - "25540185 [(Meinicke, Peter)] 2015-04-28 \n", - "25527832 [(Lindberg, Michael R), (Hall, Ira M), (Quinla... 2015-04-12 \n", - "25526884 [(Barton, Carl), (Heliou, Alice), (Mouchard, L... 2015-04-27 \n", - "25524895 [(Mu, John C), (Mohiyuddin, Marghoob), (Li, Ji... 2015-04-28 \n", - "25521965 [(Wu, Chengkun), (Schwartz, Jean-Marc), (Braba... 2014-12-19 \n", - "25520192 [(Gardner, Paul P), (Eldai, Hisham)] 2015-01-24 \n", - "25514851 [(Anvar, Seyed Yahya), (Khachatryan, Lusine), ... 2015-02-06 \n", - "25505094 [(Bliven, Spencer E), (Bourne, Philip E), (Prl... 2015-04-12 \n", - "25505087 [(Völkel, Gunnar), (Lausser, Ludwig), (Schmid,... 2015-04-12 \n", - "25505086 [(Navarro-Gomez, Daniel), (Leipzig, Jeremy), (... 2015-04-12 \n", - "25504847 [(Haubold, Bernhard), (Klötzl, Fabian), (Pfaff... 2015-04-12 \n", - "25481009 [(Hussan, Jagir R), (Hunter, Peter J), (Gladdi... 2015-04-12 \n", - "25481007 [(Wintersinger, Jeff A), (Wasmuth, James D)] 2015-04-12 \n", - "25480375 [(Harvey, Chris T), (Moyerbrailean, Gregory A)... 2015-04-12 \n", - "25474353 [(Gavryushkina, Alexandra), (Welch, David), (S... 2014-12-05 \n", - "25461763 [(Zhu, Xiao), (Leung, Henry C M), (Chin, Franc... 2014-12-03 \n", - "25452688 [(Lee, Wan-Ping), (Wu, Jiantao), (Marth, Gabor... 2014-12-02 \n", - "25435543 [(Sheng, Quanhu), (Li, Rongxia), (Dai, Jie), (... 2015-01-31 \n", - "25431162 [(Warnecke, Andreas), (Sandalova, Tatyana), (A... 2015-04-27 \n", - "25428347 [(Diaz, Aaron A), (Qin, Han), (Ramalho-Santos,... 2015-02-18 \n", - "25422674 [(Inouye, Michael), (Dashnow, Harriet), (Raven... 2014-11-25 \n", - "25414364 [(Hirsh, Layla), (Piovesan, Damiano), (Giollo,... 2015-04-03 \n", - "25414349 [(Croucher, Nicholas J), (Page, Andrew J), (Co... 2015-02-18 \n", - "25410596 [(Treangen, Todd J), (Ondov, Brian D), (Koren,... 2015-01-07 \n", - "... ... ... \n", - "22238257 [(Hentrich, Thomas), (Schulze, Julia M), (Embe... 2012-03-01 \n", - "22235263 [(Peltola, Tomi), (Marttinen, Pekka), (Jula, A... 2012-01-11 \n", - "22215819 [(Mørk, Søren), (Holmes, Ian)] 2012-03-01 \n", - "25328913 [(Fenwick, Matthew), (Sesanker, Colbert), (Sch... 2014-10-20 \n", - "22151646 [(Lv, Jie), (Havlak, Paul), (Putnam, Nicholas H)] 2011-12-13 \n", - "22080292 [(Langer, Steve G)] 2012-03-07 \n", - "22017798 [(Pinello, Luca), (Lo Bosco, Giosuè), (Hanlon,... 2012-01-06 \n", - "21994228 [(Riba-Grognuz, Oksana), (Keller, Laurent), (F... 2011-12-13 \n", - "21911333 [(Bielejec, Filip), (Rambaut, Andrew), (Suchar... 2011-10-06 \n", - "21899774 [(Mishima, Hiroyuki), (Sasaki, Kensaku), (Tana... 2011-09-29 \n", - "21824426 [(Jethava, Vinay), (Bhattacharyya, Chiranjib),... 2011-09-12 \n", - "21724594 [(Pedersen, Brent), (Hsieh, Tzung-Fu), (Ibarra... 2011-08-19 \n", - "21685055 [(Bolouri, Hamid), (Dulepet, Rajiv), (Angerman... 2011-08-05 \n", - "21685051 [(Xin, Yurong), (Ge, Yongchao), (Haghighi, Fat... 2011-08-05 \n", - "21635747 [(Blanca, Jose M), (Pascual, Laura), (Ziarsolo... 2011-06-28 \n", - "21595876 [(Miller, Christopher S), (Baker, Brett J), (T... 2011-10-20 \n", - "21529350 [(Oshita, Kazuki), (Arakawa, Kazuharu), (Tomit... 2011-05-26 \n", - "21501495 [(Tang, Haibao), (Lyons, Eric), (Pedersen, Bre... 2011-05-09 \n", - "21493652 [(Barnett, Derek W), (Garrison, Erik K), (Quin... 2011-06-03 \n", - "21478170 [(Gardner, Paul P), (Barquist, Lars), (Bateman... 2011-08-09 \n", - "21357752 [(Washietl, Stefan), (Findeiss, Sven), (Müller... 2011-03-22 \n", - "21296748 [(Pedersen, Brent S), (Tang, Haibao), (Freelin... 2011-03-30 \n", - "21169373 [(Gostev, Mikhail), (Fernandez-Banet, Julio), ... 2011-02-10 \n", - "21124986 [(Miller, Andrew K), (Print, Cristin G), (Niel... 2010-12-02 \n", - "20935049 [(Bombarely, Aureliano), (Menda, Naama), (Tecl... 2010-12-23 \n", - "20798169 [(Goll, Johannes), (Rusch, Douglas B), (Tanenb... 2010-10-08 \n", - "20562450 [(Kondrashov, Alexey S), (Assis, Raquel)] 2010-08-06 \n", - "20529912 [(Vaske, Charles J), (Benz, Stephen C), (Sanbo... 2010-06-09 \n", - "20421198 [(Sukumaran, Jeet), (Holder, Mark T)] 2010-06-09 \n", - "20106815 [(Piipari, Matias), (Down, Thomas A), (Saini, ... 2010-03-08 \n", - "\n", - " Journal \n", - "26357045 IEEE/ACM Trans Comput Biol Bioinform \n", - "25601296 JMIR Med Inform \n", - "25558360 Ecol Evol \n", - "25553811 J Bioinform Comput Biol \n", - "25549775 Ann Biomed Eng \n", - "25543048 Bioinformatics \n", - "25540185 Bioinformatics \n", - "25527832 Bioinformatics \n", - "25526884 BMC Bioinformatics \n", - "25524895 Bioinformatics \n", - "25521965 BMC Med Genomics \n", - "25520192 Nucleic Acids Res. \n", - "25514851 Genome Biol. \n", - "25505094 Bioinformatics \n", - "25505087 Bioinformatics \n", - "25505086 Bioinformatics \n", - "25504847 Bioinformatics \n", - "25481009 Bioinformatics \n", - "25481007 Bioinformatics \n", - "25480375 Bioinformatics \n", - "25474353 PLoS Comput. Biol. \n", - "25461763 PLoS ONE \n", - "25452688 Cancer Inform \n", - "25435543 Mol. Cell Proteomics \n", - "25431162 BMC Bioinformatics \n", - "25428347 Nucleic Acids Res. \n", - "25422674 Genome Med \n", - "25414364 Bioinformatics \n", - "25414349 Nucleic Acids Res. \n", - "25410596 Genome Biol. \n", - "... ... \n", - "22238257 Bioinformatics \n", - "22235263 PLoS ONE \n", - "22215819 Bioinformatics \n", - "25328913 Proc Int Conf Inf Technol New Gener \n", - "22151646 BMC Bioinformatics \n", - "22080292 J Digit Imaging \n", - "22017798 BMC Bioinformatics \n", - "21994228 Bioinformatics \n", - "21911333 Bioinformatics \n", - "21899774 BMC Res Notes \n", - "21824426 BMC Bioinformatics \n", - "21724594 Bioinformatics \n", - "21685055 Bioinformatics \n", - "21685051 Bioinformatics \n", - "21635747 BMC Genomics \n", - "21595876 Genome Biol. \n", - "21529350 Source Code Biol Med \n", - "21501495 BMC Bioinformatics \n", - "21493652 Bioinformatics \n", - "21478170 Nucleic Acids Res. \n", - "21357752 RNA \n", - "21296748 Bioinformatics \n", - "21169373 Bioinformatics \n", - "21124986 PLoS ONE \n", - "20935049 Nucleic Acids Res. \n", - "20798169 Bioinformatics \n", - "20562450 Bioinformatics \n", - "20529912 Bioinformatics \n", - "20421198 Bioinformatics \n", - "20106815 Bioinformatics \n", - "\n", - "[402 rows x 4 columns]\n" - ] + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
AbstractAuthorsDateJournal
26357045 Stability and sensitivity analyses of biologic... [(Shiraishi, Fumihide), (Yoshida, Erika), (Voi... 2015-09-11 IEEE/ACM Trans Comput Biol Bioinform
25601296 Most electronic data capture (EDC) and electro... [(Dixit, Abhishek), (Dobson, Richard J B)] 2015-01-20 JMIR Med Inform
25558360 Remotely sensed data - available at medium to ... [(Tuck, Sean L), (Phillips, Helen Rp), (Hintze... 2015-01-05 Ecol Evol
25553811 Whole-genome bisulfite sequencing (WGBS) is an... [(Chen, Junfang), (Lutsik, Pavlo), (Akulenko, ... 2015-01-02 J Bioinform Comput Biol
25549775 A number of computational approaches have been... [(Manini, Simone), (Antiga, Luca), (Botti, Lor... 2015-06-09 Ann Biomed Eng
\n", + "
" + ], + "text/plain": [ + " Abstract \\\n", + "26357045 Stability and sensitivity analyses of biologic... \n", + "25601296 Most electronic data capture (EDC) and electro... \n", + "25558360 Remotely sensed data - available at medium to ... \n", + "25553811 Whole-genome bisulfite sequencing (WGBS) is an... \n", + "25549775 A number of computational approaches have been... \n", + "\n", + " Authors Date \\\n", + "26357045 [(Shiraishi, Fumihide), (Yoshida, Erika), (Voi... 2015-09-11 \n", + "25601296 [(Dixit, Abhishek), (Dobson, Richard J B)] 2015-01-20 \n", + "25558360 [(Tuck, Sean L), (Phillips, Helen Rp), (Hintze... 2015-01-05 \n", + "25553811 [(Chen, Junfang), (Lutsik, Pavlo), (Akulenko, ... 2015-01-02 \n", + "25549775 [(Manini, Simone), (Antiga, Luca), (Botti, Lor... 2015-06-09 \n", + "\n", + " Journal \n", + "26357045 IEEE/ACM Trans Comput Biol Bioinform \n", + "25601296 JMIR Med Inform \n", + "25558360 Ecol Evol \n", + "25553811 J Bioinform Comput Biol \n", + "25549775 Ann Biomed Eng " + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" } ], "source": [ @@ -362,8 +247,132 @@ " article.abstract],name=article.pmid, index=col_names)\n", " df = df.append(row)\n", "\n", - "print(df)" + "df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "Check the content of the first abstract" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "'Stability and sensitivity analyses of biological systems require the ad hocwriting of computer code, which is highly dependent on the particular model and burdensome for large systems. We propose a very accurate strategy to overcome this challenge. Its core concept is the conversion of the model into the format of biochemical systems theory (BST), which greatly facilitates the computation of sensitivities. First, the steady state of interest is determined by integrating the model equations toward the steady state and then using a Newton-Raphson method to fine-tune the result. The second step of conversion into the BST format requires several instances of numerical differentiation. The accuracy of this task is ensured by the use of a complex-variable Taylor scheme for all differentiation steps. The proposed strategy is implemented in a new software program, COSMOS, which automates the stability and sensitivity analysis of essentially arbitrary ODE models in a quick, yet highly accurate manner. The methods underlying the process are theoretically analyzed and illustrated with four representative examples: a simple metabolic reaction model; a model of aspartate-derived amino acid biosynthesis; a TCA-cycle model; and a modified TCA-cycle model. COSMOS has been deposited to https://github.com/BioprocessdesignLab/COSMOS.'" + ] + }, + "execution_count": 26, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.iat[0,0]" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Find address of github repository from abstract by searching for the \"https://github.com\" and then for the next space (this seems to work even if the abstract ends with the github address, so there is no space at the end).\n", + "\n", + "TO DO: make this into a for loop!" + ] + }, + { + "cell_type": "code", + "execution_count": 53, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "402" + ] + }, + "execution_count": 53, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "len(df.index)" ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 51, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "22\n", + "https://github.com/foo\n" + ] + } + ], + "source": [ + "abstract = df.iat[0,0]\n", + "start_index = abstract.find(\"https://github.com\")\n", + "url_to_end = abstract[start_index:]\n", + "space_index = url_to_end.find(\" \")\n", + "github_url = url_to_end[:space_index]\n" + ] + }, + { + "cell_type": "code", + "execution_count": 33, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [] } ], "metadata": { From a33c210007e61d91b7b2ca31f031e7bbb44b4fbb Mon Sep 17 00:00:00 2001 From: Melanie I Stefan Date: Wed, 16 Mar 2016 18:19:08 +0000 Subject: [PATCH 08/21] start iterating through rows of abstract, but get stuck --- src/find_github_repo.ipynb | 234 +++++++++++++++++++++++++++++-------- 1 file changed, 186 insertions(+), 48 deletions(-) diff --git a/src/find_github_repo.ipynb b/src/find_github_repo.ipynb index 5e74e0c..2769802 100644 --- a/src/find_github_repo.ipynb +++ b/src/find_github_repo.ipynb @@ -24,7 +24,7 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 25, "metadata": { "collapsed": false }, @@ -35,7 +35,7 @@ "['github_pubs.xml', 'README.md']" ] }, - "execution_count": 11, + "execution_count": 25, "metadata": {}, "output_type": "execute_result" } @@ -55,7 +55,7 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 26, "metadata": { "collapsed": true }, @@ -74,7 +74,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 27, "metadata": { "collapsed": true }, @@ -106,7 +106,7 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 28, "metadata": { "collapsed": true }, @@ -145,14 +145,15 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "Make data frame (this differs a bit from Kevin's code by including abstract also)" + "Make data frame (this differs a bit from Kevin's code by including abstract and url field) " ] }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 67, "metadata": { - "collapsed": false + "collapsed": false, + "scrolled": true }, "outputs": [ { @@ -167,6 +168,7 @@ " Authors\n", " Date\n", " Journal\n", + " Url\n", " \n", " \n", " \n", @@ -176,6 +178,7 @@ " [(Shiraishi, Fumihide), (Yoshida, Erika), (Voi...\n", " 2015-09-11\n", " IEEE/ACM Trans Comput Biol Bioinform\n", + " \n", " \n", " \n", " 25601296\n", @@ -183,6 +186,7 @@ " [(Dixit, Abhishek), (Dobson, Richard J B)]\n", " 2015-01-20\n", " JMIR Med Inform\n", + " \n", " \n", " \n", " 25558360\n", @@ -190,6 +194,7 @@ " [(Tuck, Sean L), (Phillips, Helen Rp), (Hintze...\n", " 2015-01-05\n", " Ecol Evol\n", + " \n", " \n", " \n", " 25553811\n", @@ -197,6 +202,7 @@ " [(Chen, Junfang), (Lutsik, Pavlo), (Akulenko, ...\n", " 2015-01-02\n", " J Bioinform Comput Biol\n", + " \n", " \n", " \n", " 25549775\n", @@ -204,6 +210,7 @@ " [(Manini, Simone), (Antiga, Luca), (Botti, Lor...\n", " 2015-06-09\n", " Ann Biomed Eng\n", + " \n", " \n", " \n", "\n", @@ -224,15 +231,15 @@ "25553811 [(Chen, Junfang), (Lutsik, Pavlo), (Akulenko, ... 2015-01-02 \n", "25549775 [(Manini, Simone), (Antiga, Luca), (Botti, Lor... 2015-06-09 \n", "\n", - " Journal \n", - "26357045 IEEE/ACM Trans Comput Biol Bioinform \n", - "25601296 JMIR Med Inform \n", - "25558360 Ecol Evol \n", - "25553811 J Bioinform Comput Biol \n", - "25549775 Ann Biomed Eng " + " Journal Url \n", + "26357045 IEEE/ACM Trans Comput Biol Bioinform \n", + "25601296 JMIR Med Inform \n", + "25558360 Ecol Evol \n", + "25553811 J Bioinform Comput Biol \n", + "25549775 Ann Biomed Eng " ] }, - "execution_count": 15, + "execution_count": 67, "metadata": {}, "output_type": "execute_result" } @@ -240,30 +247,28 @@ "source": [ "import pandas as pd\n", "df = pd.DataFrame()\n", - "col_names = [\"Date\", \"Journal\", \"Authors\",\"Abstract\"]\n", + "col_names = [\"Date\", \"Journal\", \"Authors\",\"Abstract\",\"Url\"]\n", "\n", "for article in parse_pubmed_xml('github_pubs.xml'):\n", " row = pd.Series([article.pubdate, article.journal, [(author[0], author[1]) for author in article.get_authors()],\n", - " article.abstract],name=article.pmid, index=col_names)\n", + " article.abstract, ''],name=article.pmid, index=col_names)\n", " df = df.append(row)\n", "\n", "df.head()" ] }, { - "cell_type": "code", - "execution_count": null, + "cell_type": "markdown", "metadata": { "collapsed": true }, - "outputs": [], "source": [ "Check the content of the first abstract" ] }, { "cell_type": "code", - "execution_count": 26, + "execution_count": 30, "metadata": { "collapsed": false }, @@ -274,7 +279,7 @@ "'Stability and sensitivity analyses of biological systems require the ad hocwriting of computer code, which is highly dependent on the particular model and burdensome for large systems. We propose a very accurate strategy to overcome this challenge. Its core concept is the conversion of the model into the format of biochemical systems theory (BST), which greatly facilitates the computation of sensitivities. First, the steady state of interest is determined by integrating the model equations toward the steady state and then using a Newton-Raphson method to fine-tune the result. The second step of conversion into the BST format requires several instances of numerical differentiation. The accuracy of this task is ensured by the use of a complex-variable Taylor scheme for all differentiation steps. The proposed strategy is implemented in a new software program, COSMOS, which automates the stability and sensitivity analysis of essentially arbitrary ODE models in a quick, yet highly accurate manner. The methods underlying the process are theoretically analyzed and illustrated with four representative examples: a simple metabolic reaction model; a model of aspartate-derived amino acid biosynthesis; a TCA-cycle model; and a modified TCA-cycle model. COSMOS has been deposited to https://github.com/BioprocessdesignLab/COSMOS.'" ] }, - "execution_count": 26, + "execution_count": 30, "metadata": {}, "output_type": "execute_result" } @@ -289,12 +294,41 @@ "source": [ "Find address of github repository from abstract by searching for the \"https://github.com\" and then for the next space (this seems to work even if the abstract ends with the github address, so there is no space at the end).\n", "\n", - "TO DO: make this into a for loop!" + "TO DO: Work out problem in for loop! Work out close paren problem" + ] + }, + { + "cell_type": "code", + "execution_count": 78, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "ename": "AttributeError", + "evalue": "'NoneType' object has no attribute 'find'", + "output_type": "error", + "traceback": [ + "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[1;31mAttributeError\u001b[0m Traceback (most recent call last)", + "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m()\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mi\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mindex\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m-\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 2\u001b[0m \u001b[0mabstract\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mdf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0miat\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 3\u001b[1;33m \u001b[0mstart_index\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mabstract\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfind\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"https://github.com\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 4\u001b[0m \u001b[0murl_to_end\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mabstract\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mstart_index\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5\u001b[0m \u001b[0mspace_index\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0murl_to_end\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfind\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\" \"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;31mAttributeError\u001b[0m: 'NoneType' object has no attribute 'find'" + ] + } + ], + "source": [ + "for i in range(0,(len(df.index)-1)): \n", + " abstract = df.iat[i,0]\n", + " start_index = abstract.find(\"https://github.com\")\n", + " url_to_end = abstract[start_index:]\n", + " space_index = url_to_end.find(\" \")\n", + " github_url = url_to_end[:space_index]\n", + " df.iat[i,4] = github_url" ] }, { "cell_type": "code", - "execution_count": 53, + "execution_count": 79, "metadata": { "collapsed": false }, @@ -302,68 +336,172 @@ { "data": { "text/plain": [ - "402" + "79" ] }, - "execution_count": 53, + "execution_count": 79, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "len(df.index)" + "i" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 73, "metadata": { - "collapsed": true + "collapsed": false }, "outputs": [], "source": [] }, { "cell_type": "code", - "execution_count": 51, + "execution_count": 70, "metadata": { "collapsed": false }, "outputs": [ { - "name": "stdout", - "output_type": "stream", - "text": [ - "22\n", - "https://github.com/foo\n" - ] + "data": { + "text/plain": [ + "'https://github.com/BioprocessdesignLab/COSMOS'" + ] + }, + "execution_count": 70, + "metadata": {}, + "output_type": "execute_result" } ], - "source": [ - "abstract = df.iat[0,0]\n", - "start_index = abstract.find(\"https://github.com\")\n", - "url_to_end = abstract[start_index:]\n", - "space_index = url_to_end.find(\" \")\n", - "github_url = url_to_end[:space_index]\n" - ] + "source": [] }, { "cell_type": "code", - "execution_count": 33, + "execution_count": 74, "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "'https://github.com/BioprocessdesignLab/COSMOS'" + ] + }, + "execution_count": 74, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 80, "metadata": { "collapsed": false }, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
AbstractAuthorsDateJournalUrl
26357045 Stability and sensitivity analyses of biologic... [(Shiraishi, Fumihide), (Yoshida, Erika), (Voi... 2015-09-11 IEEE/ACM Trans Comput Biol Bioinform https://github.com/BioprocessdesignLab/COSMOS
25601296 Most electronic data capture (EDC) and electro... [(Dixit, Abhishek), (Dobson, Richard J B)] 2015-01-20 JMIR Med Inform
25558360 Remotely sensed data - available at medium to ... [(Tuck, Sean L), (Phillips, Helen Rp), (Hintze... 2015-01-05 Ecol Evol https://github.com/seantuck12/MODISTools)
25553811 Whole-genome bisulfite sequencing (WGBS) is an... [(Chen, Junfang), (Lutsik, Pavlo), (Akulenko, ... 2015-01-02 J Bioinform Comput Biol https://github.com/Junfang/AKSmooth
25549775 A number of computational approaches have been... [(Manini, Simone), (Antiga, Luca), (Botti, Lor... 2015-06-09 Ann Biomed Eng
\n", + "
" + ], + "text/plain": [ + " Abstract \\\n", + "26357045 Stability and sensitivity analyses of biologic... \n", + "25601296 Most electronic data capture (EDC) and electro... \n", + "25558360 Remotely sensed data - available at medium to ... \n", + "25553811 Whole-genome bisulfite sequencing (WGBS) is an... \n", + "25549775 A number of computational approaches have been... \n", + "\n", + " Authors Date \\\n", + "26357045 [(Shiraishi, Fumihide), (Yoshida, Erika), (Voi... 2015-09-11 \n", + "25601296 [(Dixit, Abhishek), (Dobson, Richard J B)] 2015-01-20 \n", + "25558360 [(Tuck, Sean L), (Phillips, Helen Rp), (Hintze... 2015-01-05 \n", + "25553811 [(Chen, Junfang), (Lutsik, Pavlo), (Akulenko, ... 2015-01-02 \n", + "25549775 [(Manini, Simone), (Antiga, Luca), (Botti, Lor... 2015-06-09 \n", + "\n", + " Journal \\\n", + "26357045 IEEE/ACM Trans Comput Biol Bioinform \n", + "25601296 JMIR Med Inform \n", + "25558360 Ecol Evol \n", + "25553811 J Bioinform Comput Biol \n", + "25549775 Ann Biomed Eng \n", + "\n", + " Url \n", + "26357045 https://github.com/BioprocessdesignLab/COSMOS \n", + "25601296 \n", + "25558360 https://github.com/seantuck12/MODISTools) \n", + "25553811 https://github.com/Junfang/AKSmooth \n", + "25549775 " + ] + }, + "execution_count": 80, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.head()" + ] }, { "cell_type": "code", From b466633fabe1c68fd621553bc3311d02eaf60f8f Mon Sep 17 00:00:00 2001 From: Melanie I Stefan Date: Thu, 17 Mar 2016 10:18:18 +0000 Subject: [PATCH 09/21] finding github url for all abstracts and saving them to data frame --- src/find_github_repo.ipynb | 180 +++++++++++++++++++++---------------- 1 file changed, 101 insertions(+), 79 deletions(-) diff --git a/src/find_github_repo.ipynb b/src/find_github_repo.ipynb index 2769802..13983ab 100644 --- a/src/find_github_repo.ipynb +++ b/src/find_github_repo.ipynb @@ -24,7 +24,7 @@ }, { "cell_type": "code", - "execution_count": 25, + "execution_count": 2, "metadata": { "collapsed": false }, @@ -35,7 +35,7 @@ "['github_pubs.xml', 'README.md']" ] }, - "execution_count": 25, + "execution_count": 2, "metadata": {}, "output_type": "execute_result" } @@ -55,7 +55,7 @@ }, { "cell_type": "code", - "execution_count": 26, + "execution_count": 3, "metadata": { "collapsed": true }, @@ -74,7 +74,7 @@ }, { "cell_type": "code", - "execution_count": 27, + "execution_count": 4, "metadata": { "collapsed": true }, @@ -106,7 +106,7 @@ }, { "cell_type": "code", - "execution_count": 28, + "execution_count": 5, "metadata": { "collapsed": true }, @@ -150,7 +150,7 @@ }, { "cell_type": "code", - "execution_count": 67, + "execution_count": 6, "metadata": { "collapsed": false, "scrolled": true @@ -239,7 +239,7 @@ "25549775 Ann Biomed Eng " ] }, - "execution_count": 67, + "execution_count": 6, "metadata": {}, "output_type": "execute_result" } @@ -268,7 +268,7 @@ }, { "cell_type": "code", - "execution_count": 30, + "execution_count": 7, "metadata": { "collapsed": false }, @@ -279,7 +279,7 @@ "'Stability and sensitivity analyses of biological systems require the ad hocwriting of computer code, which is highly dependent on the particular model and burdensome for large systems. We propose a very accurate strategy to overcome this challenge. Its core concept is the conversion of the model into the format of biochemical systems theory (BST), which greatly facilitates the computation of sensitivities. First, the steady state of interest is determined by integrating the model equations toward the steady state and then using a Newton-Raphson method to fine-tune the result. The second step of conversion into the BST format requires several instances of numerical differentiation. The accuracy of this task is ensured by the use of a complex-variable Taylor scheme for all differentiation steps. The proposed strategy is implemented in a new software program, COSMOS, which automates the stability and sensitivity analysis of essentially arbitrary ODE models in a quick, yet highly accurate manner. The methods underlying the process are theoretically analyzed and illustrated with four representative examples: a simple metabolic reaction model; a model of aspartate-derived amino acid biosynthesis; a TCA-cycle model; and a modified TCA-cycle model. COSMOS has been deposited to https://github.com/BioprocessdesignLab/COSMOS.'" ] }, - "execution_count": 30, + "execution_count": 7, "metadata": {}, "output_type": "execute_result" } @@ -299,107 +299,111 @@ }, { "cell_type": "code", - "execution_count": 78, + "execution_count": 9, "metadata": { "collapsed": false }, "outputs": [ { - "ename": "AttributeError", - "evalue": "'NoneType' object has no attribute 'find'", - "output_type": "error", - "traceback": [ - "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[1;31mAttributeError\u001b[0m Traceback (most recent call last)", - "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m()\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mi\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mindex\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m-\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 2\u001b[0m \u001b[0mabstract\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mdf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0miat\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 3\u001b[1;33m \u001b[0mstart_index\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mabstract\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfind\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"https://github.com\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 4\u001b[0m \u001b[0murl_to_end\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mabstract\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mstart_index\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5\u001b[0m \u001b[0mspace_index\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0murl_to_end\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfind\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\" \"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;31mAttributeError\u001b[0m: 'NoneType' object has no attribute 'find'" + "name": "stdout", + "output_type": "stream", + "text": [ + "Stability and sensitivity analyses of biological systems require the ad hocwriting of computer code, which is highly dependent on the particular model and burdensome for large systems. We propose a very accurate strategy to overcome this challenge. Its core concept is the conversion of the model into the format of biochemical systems theory (BST), which greatly facilitates the computation of sensitivities. First, the steady state of interest is determined by integrating the model equations toward the steady state and then using a Newton-Raphson method to fine-tune the result. The second step of conversion into the BST format requires several instances of numerical differentiation. The accuracy of this task is ensured by the use of a complex-variable Taylor scheme for all differentiation steps. The proposed strategy is implemented in a new software program, COSMOS, which automates the stability and sensitivity analysis of essentially arbitrary ODE models in a quick, yet highly accurate manner. The methods underlying the process are theoretically analyzed and illustrated with four representative examples: a simple metabolic reaction model; a model of aspartate-derived amino acid biosynthesis; a TCA-cycle model; and a modified TCA-cycle model. COSMOS has been deposited to https://github.com/BioprocessdesignLab/COSMOS.\n" ] } ], "source": [ - "for i in range(0,(len(df.index)-1)): \n", - " abstract = df.iat[i,0]\n", - " start_index = abstract.find(\"https://github.com\")\n", - " url_to_end = abstract[start_index:]\n", - " space_index = url_to_end.find(\" \")\n", - " github_url = url_to_end[:space_index]\n", - " df.iat[i,4] = github_url" + "i=0\n", + "abstract = df.iat[i,0]\n", + "print abstract\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Use regexp to extract github url from abstract (adapted from http://stackoverflow.com/questions/839994/extracting-a-url-in-python) - This is overkill, but does the job. We need re to use regular expressoions." ] }, { "cell_type": "code", - "execution_count": 79, + "execution_count": 27, "metadata": { - "collapsed": false + "collapsed": true }, - "outputs": [ - { - "data": { - "text/plain": [ - "79" - ] - }, - "execution_count": 79, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ - "i" + "import re\n", + "github_url_regex = r\"\"\"(?i)\\b((?:https?://github[.](?:com|net|org|edu|gov|mil|aero|asia|biz|cat|coop|info|int|jobs|mobi|museum|name|post|pro|tel|travel|xxx|ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cs|cu|cv|cx|cy|cz|dd|de|dj|dk|dm|do|dz|ec|ee|eg|eh|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|Ja|sk|sl|sm|sn|so|sr|ss|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|yu|za|zm|zw)/)(?:[^\\s()<>{}\\[\\]]+|\\([^\\s()]*?\\([^\\s()]+\\)[^\\s()]*?\\)|\\([^\\s]+?\\))+(?:\\([^\\s()]*?\\([^\\s()]+\\)[^\\s()]*?\\)|\\([^\\s]+?\\)|[^\\s`!()\\[\\]{};:'\".,<>?«»“”‘’])|(?:(? [(Shiraishi, Fumihide), (Yoshida, Erika), (Voi...\n", " 2015-09-11\n", " IEEE/ACM Trans Comput Biol Bioinform\n", - " https://github.com/BioprocessdesignLab/COSMOS\n", + " [https://github.com/BioprocessdesignLab/COSMOS]\n", " \n", " \n", " 25601296\n", @@ -434,7 +438,7 @@ " [(Dixit, Abhishek), (Dobson, Richard J B)]\n", " 2015-01-20\n", " JMIR Med Inform\n", - " \n", + " []\n", " \n", " \n", " 25558360\n", @@ -442,7 +446,7 @@ " [(Tuck, Sean L), (Phillips, Helen Rp), (Hintze...\n", " 2015-01-05\n", " Ecol Evol\n", - " https://github.com/seantuck12/MODISTools)\n", + " [https://github.com/seantuck12/MODISTools]\n", " \n", " \n", " 25553811\n", @@ -450,7 +454,7 @@ " [(Chen, Junfang), (Lutsik, Pavlo), (Akulenko, ...\n", " 2015-01-02\n", " J Bioinform Comput Biol\n", - " https://github.com/Junfang/AKSmooth\n", + " [https://github.com/Junfang/AKSmooth]\n", " \n", " \n", " 25549775\n", @@ -458,7 +462,7 @@ " [(Manini, Simone), (Antiga, Luca), (Botti, Lor...\n", " 2015-06-09\n", " Ann Biomed Eng\n", - " \n", + " [archtk.github.com]\n", " \n", " \n", "\n", @@ -486,15 +490,15 @@ "25553811 J Bioinform Comput Biol \n", "25549775 Ann Biomed Eng \n", "\n", - " Url \n", - "26357045 https://github.com/BioprocessdesignLab/COSMOS \n", - "25601296 \n", - "25558360 https://github.com/seantuck12/MODISTools) \n", - "25553811 https://github.com/Junfang/AKSmooth \n", - "25549775 " + " Url \n", + "26357045 [https://github.com/BioprocessdesignLab/COSMOS] \n", + "25601296 [] \n", + "25558360 [https://github.com/seantuck12/MODISTools] \n", + "25553811 [https://github.com/Junfang/AKSmooth] \n", + "25549775 [archtk.github.com] " ] }, - "execution_count": 80, + "execution_count": 49, "metadata": {}, "output_type": "execute_result" } @@ -503,6 +507,24 @@ "df.head()" ] }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [] + }, { "cell_type": "code", "execution_count": null, From d7055253111d868282b1ea47c430cbc7b23af1ae Mon Sep 17 00:00:00 2001 From: Melanie I Stefan Date: Thu, 17 Mar 2016 13:16:22 +0000 Subject: [PATCH 10/21] started playing around with pygithub --- src/find_github_repo.ipynb | 119 +++++++++++++++++++++++++++++-------- 1 file changed, 94 insertions(+), 25 deletions(-) diff --git a/src/find_github_repo.ipynb b/src/find_github_repo.ipynb index 13983ab..96e31d7 100644 --- a/src/find_github_repo.ipynb +++ b/src/find_github_repo.ipynb @@ -24,7 +24,7 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": 14, "metadata": { "collapsed": false }, @@ -35,7 +35,7 @@ "['github_pubs.xml', 'README.md']" ] }, - "execution_count": 2, + "execution_count": 14, "metadata": {}, "output_type": "execute_result" } @@ -55,7 +55,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 15, "metadata": { "collapsed": true }, @@ -74,7 +74,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 16, "metadata": { "collapsed": true }, @@ -106,7 +106,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 17, "metadata": { "collapsed": true }, @@ -150,7 +150,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 18, "metadata": { "collapsed": false, "scrolled": true @@ -239,7 +239,7 @@ "25549775 Ann Biomed Eng " ] }, - "execution_count": 6, + "execution_count": 18, "metadata": {}, "output_type": "execute_result" } @@ -268,7 +268,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 19, "metadata": { "collapsed": false }, @@ -279,7 +279,7 @@ "'Stability and sensitivity analyses of biological systems require the ad hocwriting of computer code, which is highly dependent on the particular model and burdensome for large systems. We propose a very accurate strategy to overcome this challenge. Its core concept is the conversion of the model into the format of biochemical systems theory (BST), which greatly facilitates the computation of sensitivities. First, the steady state of interest is determined by integrating the model equations toward the steady state and then using a Newton-Raphson method to fine-tune the result. The second step of conversion into the BST format requires several instances of numerical differentiation. The accuracy of this task is ensured by the use of a complex-variable Taylor scheme for all differentiation steps. The proposed strategy is implemented in a new software program, COSMOS, which automates the stability and sensitivity analysis of essentially arbitrary ODE models in a quick, yet highly accurate manner. The methods underlying the process are theoretically analyzed and illustrated with four representative examples: a simple metabolic reaction model; a model of aspartate-derived amino acid biosynthesis; a TCA-cycle model; and a modified TCA-cycle model. COSMOS has been deposited to https://github.com/BioprocessdesignLab/COSMOS.'" ] }, - "execution_count": 7, + "execution_count": 19, "metadata": {}, "output_type": "execute_result" } @@ -299,7 +299,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 20, "metadata": { "collapsed": false }, @@ -327,7 +327,7 @@ }, { "cell_type": "code", - "execution_count": 27, + "execution_count": 21, "metadata": { "collapsed": true }, @@ -346,7 +346,7 @@ }, { "cell_type": "code", - "execution_count": 44, + "execution_count": 22, "metadata": { "collapsed": false }, @@ -357,7 +357,7 @@ }, { "cell_type": "code", - "execution_count": 45, + "execution_count": 23, "metadata": { "collapsed": false }, @@ -384,9 +384,10 @@ }, { "cell_type": "code", - "execution_count": 48, + "execution_count": 24, "metadata": { - "collapsed": false + "collapsed": false, + "scrolled": true }, "outputs": [ { @@ -403,7 +404,7 @@ }, { "cell_type": "code", - "execution_count": 49, + "execution_count": 30, "metadata": { "collapsed": false }, @@ -498,7 +499,7 @@ "25549775 [archtk.github.com] " ] }, - "execution_count": 49, + "execution_count": 30, "metadata": {}, "output_type": "execute_result" } @@ -509,30 +510,98 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "metadata": { "collapsed": false }, "outputs": [], - "source": [] + "source": [ + "from github import Github\n", + "\n", + "g = Github(\"MelanieIStefan\", \"hn8PJuM\")\n" + ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "metadata": { "collapsed": false }, - "outputs": [], - "source": [] + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "gender-comp-bio\n", + "datasciencecoursera\n", + "datasharing\n", + "ExData_Plotting1\n", + "getting_cleaning_data\n", + "lanalytics\n", + "matlikert\n", + "moose\n", + "ProgrammingAssignment2\n", + "QMBC\n", + "RepData_PeerAssessment1\n", + "understanding_data_analysis_in_papers\n" + ] + } + ], + "source": [ + "for repo in g.get_user().get_repos():\n", + " print repo.name\n", + " " + ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 7, "metadata": { "collapsed": false }, - "outputs": [], - "source": [] + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Whisper is a file-based time-series database format for Graphite.\n" + ] + } + ], + "source": [ + "whisper = g.get_repo(\"graphite-project/whisper\")\n", + "print whisper.description" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "ename": "UnknownObjectException", + "evalue": "404 {u'documentation_url': u'https://developer.github.com/v3', u'message': u'Not Found'}", + "output_type": "error", + "traceback": [ + "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[1;31mUnknownObjectException\u001b[0m Traceback (most recent call last)", + "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m()\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[0marchtk\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mg\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_repo\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"archtk\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 2\u001b[1;33m \u001b[1;32mprint\u001b[0m \u001b[0marchtk\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdescription\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m", + "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/Repository.pyc\u001b[0m in \u001b[0;36mdescription\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 185\u001b[0m \u001b[1;33m:\u001b[0m\u001b[0mtype\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mstring\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 186\u001b[0m \"\"\"\n\u001b[1;32m--> 187\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_completeIfNotSet\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_description\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 188\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_description\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvalue\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 189\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/GithubObject.pyc\u001b[0m in \u001b[0;36m_completeIfNotSet\u001b[1;34m(self, value)\u001b[0m\n\u001b[0;32m 226\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_completeIfNotSet\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 227\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mvalue\u001b[0m \u001b[1;32mis\u001b[0m \u001b[0mNotSet\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 228\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_completeIfNeeded\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 229\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 230\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_completeIfNeeded\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/GithubObject.pyc\u001b[0m in \u001b[0;36m_completeIfNeeded\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 230\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_completeIfNeeded\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 231\u001b[0m \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__completed\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 232\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__complete\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 233\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 234\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m__complete\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/GithubObject.pyc\u001b[0m in \u001b[0;36m__complete\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 235\u001b[0m headers, data = self._requester.requestJsonAndCheck(\n\u001b[0;32m 236\u001b[0m \u001b[1;34m\"GET\"\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 237\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_url\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvalue\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 238\u001b[0m )\n\u001b[0;32m 239\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_storeAndUseAttributes\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mheaders\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/Requester.pyc\u001b[0m in \u001b[0;36mrequestJsonAndCheck\u001b[1;34m(self, verb, url, parameters, headers, input, cnx)\u001b[0m\n\u001b[0;32m 169\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 170\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mrequestJsonAndCheck\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mverb\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mheaders\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minput\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcnx\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 171\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__check\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrequestJson\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mverb\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mheaders\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minput\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcnx\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 172\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 173\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mrequestMultipartAndCheck\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mverb\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mheaders\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minput\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/Requester.pyc\u001b[0m in \u001b[0;36m__check\u001b[1;34m(self, status, responseHeaders, output)\u001b[0m\n\u001b[0;32m 177\u001b[0m \u001b[0moutput\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__structuredFromJson\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0moutput\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 178\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mstatus\u001b[0m \u001b[1;33m>=\u001b[0m \u001b[1;36m400\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 179\u001b[1;33m \u001b[1;32mraise\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__createException\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mstatus\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mresponseHeaders\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0moutput\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 180\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mresponseHeaders\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0moutput\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 181\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;31mUnknownObjectException\u001b[0m: 404 {u'documentation_url': u'https://developer.github.com/v3', u'message': u'Not Found'}" + ] + } + ], + "source": [ + "cosmos = g.get_repo(\"\")\n", + "print cosmos.description" + ] } ], "metadata": { From 48ced8ce38ecb388faa91a3f8acc8114d1dd03b4 Mon Sep 17 00:00:00 2001 From: Melanie I Stefan Date: Thu, 17 Mar 2016 17:50:07 +0000 Subject: [PATCH 11/21] refrain from telling the world my password --- src/find_github_repo.ipynb | 28 +++++++++------------------- 1 file changed, 9 insertions(+), 19 deletions(-) diff --git a/src/find_github_repo.ipynb b/src/find_github_repo.ipynb index 96e31d7..d12a21c 100644 --- a/src/find_github_repo.ipynb +++ b/src/find_github_repo.ipynb @@ -510,7 +510,7 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 4, "metadata": { "collapsed": false }, @@ -518,7 +518,7 @@ "source": [ "from github import Github\n", "\n", - "g = Github(\"MelanieIStefan\", \"hn8PJuM\")\n" + "g = Github()\n" ] }, { @@ -555,7 +555,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 5, "metadata": { "collapsed": false }, @@ -575,31 +575,21 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 6, "metadata": { "collapsed": false }, "outputs": [ { - "ename": "UnknownObjectException", - "evalue": "404 {u'documentation_url': u'https://developer.github.com/v3', u'message': u'Not Found'}", - "output_type": "error", - "traceback": [ - "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[1;31mUnknownObjectException\u001b[0m Traceback (most recent call last)", - "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m()\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[0marchtk\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mg\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_repo\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"archtk\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 2\u001b[1;33m \u001b[1;32mprint\u001b[0m \u001b[0marchtk\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdescription\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m", - "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/Repository.pyc\u001b[0m in \u001b[0;36mdescription\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 185\u001b[0m \u001b[1;33m:\u001b[0m\u001b[0mtype\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mstring\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 186\u001b[0m \"\"\"\n\u001b[1;32m--> 187\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_completeIfNotSet\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_description\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 188\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_description\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvalue\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 189\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/GithubObject.pyc\u001b[0m in \u001b[0;36m_completeIfNotSet\u001b[1;34m(self, value)\u001b[0m\n\u001b[0;32m 226\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_completeIfNotSet\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 227\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mvalue\u001b[0m \u001b[1;32mis\u001b[0m \u001b[0mNotSet\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 228\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_completeIfNeeded\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 229\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 230\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_completeIfNeeded\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/GithubObject.pyc\u001b[0m in \u001b[0;36m_completeIfNeeded\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 230\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_completeIfNeeded\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 231\u001b[0m \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__completed\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 232\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__complete\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 233\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 234\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m__complete\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/GithubObject.pyc\u001b[0m in \u001b[0;36m__complete\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 235\u001b[0m headers, data = self._requester.requestJsonAndCheck(\n\u001b[0;32m 236\u001b[0m \u001b[1;34m\"GET\"\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 237\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_url\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvalue\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 238\u001b[0m )\n\u001b[0;32m 239\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_storeAndUseAttributes\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mheaders\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/Requester.pyc\u001b[0m in \u001b[0;36mrequestJsonAndCheck\u001b[1;34m(self, verb, url, parameters, headers, input, cnx)\u001b[0m\n\u001b[0;32m 169\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 170\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mrequestJsonAndCheck\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mverb\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mheaders\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minput\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcnx\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 171\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__check\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrequestJson\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mverb\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mheaders\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minput\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcnx\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 172\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 173\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mrequestMultipartAndCheck\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mverb\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mheaders\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minput\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/Requester.pyc\u001b[0m in \u001b[0;36m__check\u001b[1;34m(self, status, responseHeaders, output)\u001b[0m\n\u001b[0;32m 177\u001b[0m \u001b[0moutput\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__structuredFromJson\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0moutput\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 178\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mstatus\u001b[0m \u001b[1;33m>=\u001b[0m \u001b[1;36m400\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 179\u001b[1;33m \u001b[1;32mraise\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__createException\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mstatus\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mresponseHeaders\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0moutput\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 180\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mresponseHeaders\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0moutput\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 181\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;31mUnknownObjectException\u001b[0m: 404 {u'documentation_url': u'https://developer.github.com/v3', u'message': u'Not Found'}" + "name": "stdout", + "output_type": "stream", + "text": [ + "Computation of Sensitivities in Model ODE Systems\n" ] } ], "source": [ - "cosmos = g.get_repo(\"\")\n", + "cosmos = g.get_repo(\"BioprocessdesignLab/COSMOS\")\n", "print cosmos.description" ] } From 282aa38921cff675ed84c5bdf2b5a16d37d42f7c Mon Sep 17 00:00:00 2001 From: Melanie Date: Thu, 24 Mar 2016 11:13:17 +0000 Subject: [PATCH 12/21] look into extracting github project from url (might need to just do a string search) --- src/find_github_repo.ipynb | 299 +++++++++++++++++++------------------ 1 file changed, 151 insertions(+), 148 deletions(-) diff --git a/src/find_github_repo.ipynb b/src/find_github_repo.ipynb index d12a21c..fc9c80a 100644 --- a/src/find_github_repo.ipynb +++ b/src/find_github_repo.ipynb @@ -24,7 +24,7 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 1, "metadata": { "collapsed": false }, @@ -35,7 +35,7 @@ "['github_pubs.xml', 'README.md']" ] }, - "execution_count": 14, + "execution_count": 1, "metadata": {}, "output_type": "execute_result" } @@ -55,7 +55,7 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 2, "metadata": { "collapsed": true }, @@ -74,7 +74,7 @@ }, { "cell_type": "code", - "execution_count": 16, + "execution_count": 3, "metadata": { "collapsed": true }, @@ -106,7 +106,7 @@ }, { "cell_type": "code", - "execution_count": 17, + "execution_count": 4, "metadata": { "collapsed": true }, @@ -150,7 +150,7 @@ }, { "cell_type": "code", - "execution_count": 18, + "execution_count": 28, "metadata": { "collapsed": false, "scrolled": true @@ -159,7 +159,7 @@ { "data": { "text/html": [ - "
\n", + "
\n", "\n", " \n", " \n", @@ -167,6 +167,7 @@ " \n", " \n", " \n", + " \n", " \n", " \n", " \n", @@ -174,43 +175,48 @@ " \n", " \n", " \n", - " \n", - " \n", - " \n", - " \n", - " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", " \n", " \n", " \n", - " \n", - " \n", - " \n", - " \n", - " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", " \n", " \n", " \n", - " \n", - " \n", - " \n", - " \n", - " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", " \n", " \n", " \n", - " \n", - " \n", - " \n", - " \n", - " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", " \n", " \n", " \n", - " \n", - " \n", - " \n", - " \n", - " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", " \n", " \n", "
AbstractAuthorsDateGithubJournalUrl
26357045 Stability and sensitivity analyses of biologic... [(Shiraishi, Fumihide), (Yoshida, Erika), (Voi... 2015-09-11 IEEE/ACM Trans Comput Biol Bioinform Stability and sensitivity analyses of biologic...[(Shiraishi, Fumihide), (Yoshida, Erika), (Voi...2015-09-11IEEE/ACM Trans Comput Biol Bioinform
25601296 Most electronic data capture (EDC) and electro... [(Dixit, Abhishek), (Dobson, Richard J B)] 2015-01-20 JMIR Med Inform Most electronic data capture (EDC) and electro...[(Dixit, Abhishek), (Dobson, Richard J B)]2015-01-20JMIR Med Inform
25558360 Remotely sensed data - available at medium to ... [(Tuck, Sean L), (Phillips, Helen Rp), (Hintze... 2015-01-05 Ecol Evol Remotely sensed data - available at medium to ...[(Tuck, Sean L), (Phillips, Helen Rp), (Hintze...2015-01-05Ecol Evol
25553811 Whole-genome bisulfite sequencing (WGBS) is an... [(Chen, Junfang), (Lutsik, Pavlo), (Akulenko, ... 2015-01-02 J Bioinform Comput Biol Whole-genome bisulfite sequencing (WGBS) is an...[(Chen, Junfang), (Lutsik, Pavlo), (Akulenko, ...2015-01-02J Bioinform Comput Biol
25549775 A number of computational approaches have been... [(Manini, Simone), (Antiga, Luca), (Botti, Lor... 2015-06-09 Ann Biomed Eng A number of computational approaches have been...[(Manini, Simone), (Antiga, Luca), (Botti, Lor...2015-06-09Ann Biomed Eng
\n", @@ -231,15 +237,15 @@ "25553811 [(Chen, Junfang), (Lutsik, Pavlo), (Akulenko, ... 2015-01-02 \n", "25549775 [(Manini, Simone), (Antiga, Luca), (Botti, Lor... 2015-06-09 \n", "\n", - " Journal Url \n", - "26357045 IEEE/ACM Trans Comput Biol Bioinform \n", - "25601296 JMIR Med Inform \n", - "25558360 Ecol Evol \n", - "25553811 J Bioinform Comput Biol \n", - "25549775 Ann Biomed Eng " + " Github Journal Url \n", + "26357045 IEEE/ACM Trans Comput Biol Bioinform \n", + "25601296 JMIR Med Inform \n", + "25558360 Ecol Evol \n", + "25553811 J Bioinform Comput Biol \n", + "25549775 Ann Biomed Eng " ] }, - "execution_count": 18, + "execution_count": 28, "metadata": {}, "output_type": "execute_result" } @@ -247,11 +253,11 @@ "source": [ "import pandas as pd\n", "df = pd.DataFrame()\n", - "col_names = [\"Date\", \"Journal\", \"Authors\",\"Abstract\",\"Url\"]\n", + "col_names = [\"Date\", \"Journal\", \"Authors\",\"Abstract\",\"Url\",\"Github\"]\n", "\n", "for article in parse_pubmed_xml('github_pubs.xml'):\n", " row = pd.Series([article.pubdate, article.journal, [(author[0], author[1]) for author in article.get_authors()],\n", - " article.abstract, ''],name=article.pmid, index=col_names)\n", + " article.abstract, '', ''],name=article.pmid, index=col_names)\n", " df = df.append(row)\n", "\n", "df.head()" @@ -268,7 +274,7 @@ }, { "cell_type": "code", - "execution_count": 19, + "execution_count": 6, "metadata": { "collapsed": false }, @@ -279,7 +285,7 @@ "'Stability and sensitivity analyses of biological systems require the ad hocwriting of computer code, which is highly dependent on the particular model and burdensome for large systems. We propose a very accurate strategy to overcome this challenge. Its core concept is the conversion of the model into the format of biochemical systems theory (BST), which greatly facilitates the computation of sensitivities. First, the steady state of interest is determined by integrating the model equations toward the steady state and then using a Newton-Raphson method to fine-tune the result. The second step of conversion into the BST format requires several instances of numerical differentiation. The accuracy of this task is ensured by the use of a complex-variable Taylor scheme for all differentiation steps. The proposed strategy is implemented in a new software program, COSMOS, which automates the stability and sensitivity analysis of essentially arbitrary ODE models in a quick, yet highly accurate manner. The methods underlying the process are theoretically analyzed and illustrated with four representative examples: a simple metabolic reaction model; a model of aspartate-derived amino acid biosynthesis; a TCA-cycle model; and a modified TCA-cycle model. COSMOS has been deposited to https://github.com/BioprocessdesignLab/COSMOS.'" ] }, - "execution_count": 19, + "execution_count": 6, "metadata": {}, "output_type": "execute_result" } @@ -288,36 +294,6 @@ "df.iat[0,0]" ] }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Find address of github repository from abstract by searching for the \"https://github.com\" and then for the next space (this seems to work even if the abstract ends with the github address, so there is no space at the end).\n", - "\n", - "TO DO: Work out problem in for loop! Work out close paren problem" - ] - }, - { - "cell_type": "code", - "execution_count": 20, - "metadata": { - "collapsed": false - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Stability and sensitivity analyses of biological systems require the ad hocwriting of computer code, which is highly dependent on the particular model and burdensome for large systems. We propose a very accurate strategy to overcome this challenge. Its core concept is the conversion of the model into the format of biochemical systems theory (BST), which greatly facilitates the computation of sensitivities. First, the steady state of interest is determined by integrating the model equations toward the steady state and then using a Newton-Raphson method to fine-tune the result. The second step of conversion into the BST format requires several instances of numerical differentiation. The accuracy of this task is ensured by the use of a complex-variable Taylor scheme for all differentiation steps. The proposed strategy is implemented in a new software program, COSMOS, which automates the stability and sensitivity analysis of essentially arbitrary ODE models in a quick, yet highly accurate manner. The methods underlying the process are theoretically analyzed and illustrated with four representative examples: a simple metabolic reaction model; a model of aspartate-derived amino acid biosynthesis; a TCA-cycle model; and a modified TCA-cycle model. COSMOS has been deposited to https://github.com/BioprocessdesignLab/COSMOS.\n" - ] - } - ], - "source": [ - "i=0\n", - "abstract = df.iat[i,0]\n", - "print abstract\n" - ] - }, { "cell_type": "markdown", "metadata": {}, @@ -327,7 +303,7 @@ }, { "cell_type": "code", - "execution_count": 21, + "execution_count": 40, "metadata": { "collapsed": true }, @@ -346,7 +322,7 @@ }, { "cell_type": "code", - "execution_count": 22, + "execution_count": 9, "metadata": { "collapsed": false }, @@ -357,7 +333,7 @@ }, { "cell_type": "code", - "execution_count": 23, + "execution_count": 59, "metadata": { "collapsed": false }, @@ -366,8 +342,9 @@ "for i in range(0,(len(df.index)-1)): \n", " abstract = df.iat[i,0]\n", " try:\n", - " github_url = re.findall(github_url_regex, abstract)\n", - " df.iat[i,4] = github_url\n", + " github_url = str(re.findall(github_url_regex, abstract))\n", + " df.iat[i,5] = github_url\n", + " \n", " except:\n", " except_no = except_no + 1 \n", " pass" @@ -384,7 +361,7 @@ }, { "cell_type": "code", - "execution_count": 24, + "execution_count": 51, "metadata": { "collapsed": false, "scrolled": true @@ -394,7 +371,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "1\n" + "5\n" ] } ], @@ -404,7 +381,7 @@ }, { "cell_type": "code", - "execution_count": 30, + "execution_count": 52, "metadata": { "collapsed": false }, @@ -412,7 +389,7 @@ { "data": { "text/html": [ - "
\n", + "
\n", "\n", " \n", " \n", @@ -420,6 +397,7 @@ " \n", " \n", " \n", + " \n", " \n", " \n", " \n", @@ -427,43 +405,48 @@ " \n", " \n", " \n", - " \n", - " \n", - " \n", - " \n", - " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", " \n", " \n", " \n", - " \n", - " \n", - " \n", - " \n", - " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", " \n", " \n", " \n", - " \n", - " \n", - " \n", - " \n", - " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", " \n", " \n", " \n", - " \n", - " \n", - " \n", - " \n", - " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", " \n", " \n", " \n", - " \n", - " \n", - " \n", - " \n", - " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", " \n", " \n", "
AbstractAuthorsDateGithubJournalUrl
26357045 Stability and sensitivity analyses of biologic... [(Shiraishi, Fumihide), (Yoshida, Erika), (Voi... 2015-09-11 IEEE/ACM Trans Comput Biol Bioinform [https://github.com/BioprocessdesignLab/COSMOS]Stability and sensitivity analyses of biologic...[(Shiraishi, Fumihide), (Yoshida, Erika), (Voi...2015-09-11IEEE/ACM Trans Comput Biol Bioinform['https://github.com/BioprocessdesignLab/COSMOS']
25601296 Most electronic data capture (EDC) and electro... [(Dixit, Abhishek), (Dobson, Richard J B)] 2015-01-20 JMIR Med Inform []Most electronic data capture (EDC) and electro...[(Dixit, Abhishek), (Dobson, Richard J B)]2015-01-20JMIR Med Inform[]
25558360 Remotely sensed data - available at medium to ... [(Tuck, Sean L), (Phillips, Helen Rp), (Hintze... 2015-01-05 Ecol Evol [https://github.com/seantuck12/MODISTools]Remotely sensed data - available at medium to ...[(Tuck, Sean L), (Phillips, Helen Rp), (Hintze...2015-01-05Ecol Evol['https://github.com/seantuck12/MODISTools']
25553811 Whole-genome bisulfite sequencing (WGBS) is an... [(Chen, Junfang), (Lutsik, Pavlo), (Akulenko, ... 2015-01-02 J Bioinform Comput Biol [https://github.com/Junfang/AKSmooth]Whole-genome bisulfite sequencing (WGBS) is an...[(Chen, Junfang), (Lutsik, Pavlo), (Akulenko, ...2015-01-02J Bioinform Comput Biol[u'https://github.com/Junfang/AKSmooth']
25549775 A number of computational approaches have been... [(Manini, Simone), (Antiga, Luca), (Botti, Lor... 2015-06-09 Ann Biomed Eng [archtk.github.com]A number of computational approaches have been...[(Manini, Simone), (Antiga, Luca), (Botti, Lor...2015-06-09Ann Biomed Eng['archtk.github.com']
\n", @@ -484,22 +467,22 @@ "25553811 [(Chen, Junfang), (Lutsik, Pavlo), (Akulenko, ... 2015-01-02 \n", "25549775 [(Manini, Simone), (Antiga, Luca), (Botti, Lor... 2015-06-09 \n", "\n", - " Journal \\\n", - "26357045 IEEE/ACM Trans Comput Biol Bioinform \n", - "25601296 JMIR Med Inform \n", - "25558360 Ecol Evol \n", - "25553811 J Bioinform Comput Biol \n", - "25549775 Ann Biomed Eng \n", + " Github Journal \\\n", + "26357045 IEEE/ACM Trans Comput Biol Bioinform \n", + "25601296 JMIR Med Inform \n", + "25558360 Ecol Evol \n", + "25553811 J Bioinform Comput Biol \n", + "25549775 Ann Biomed Eng \n", "\n", - " Url \n", - "26357045 [https://github.com/BioprocessdesignLab/COSMOS] \n", - "25601296 [] \n", - "25558360 [https://github.com/seantuck12/MODISTools] \n", - "25553811 [https://github.com/Junfang/AKSmooth] \n", - "25549775 [archtk.github.com] " + " Url \n", + "26357045 ['https://github.com/BioprocessdesignLab/COSMOS'] \n", + "25601296 [] \n", + "25558360 ['https://github.com/seantuck12/MODISTools'] \n", + "25553811 [u'https://github.com/Junfang/AKSmooth'] \n", + "25549775 ['archtk.github.com'] " ] }, - "execution_count": 30, + "execution_count": 52, "metadata": {}, "output_type": "execute_result" } @@ -510,52 +493,72 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 53, "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "['https://github.com/BioprocessdesignLab/COSMOS']\n" + ] + } + ], "source": [ - "from github import Github\n", - "\n", - "g = Github()\n" + "test = str(df.iat[0,5])\n", + "print test" ] }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 54, "metadata": { "collapsed": false }, "outputs": [ { - "name": "stdout", - "output_type": "stream", - "text": [ - "gender-comp-bio\n", - "datasciencecoursera\n", - "datasharing\n", - "ExData_Plotting1\n", - "getting_cleaning_data\n", - "lanalytics\n", - "matlikert\n", - "moose\n", - "ProgrammingAssignment2\n", - "QMBC\n", - "RepData_PeerAssessment1\n", - "understanding_data_analysis_in_papers\n" - ] + "data": { + "text/plain": [ + "2" + ] + }, + "execution_count": 54, + "metadata": {}, + "output_type": "execute_result" } ], "source": [ - "for repo in g.get_user().get_repos():\n", - " print repo.name\n", - " " + "test.find(\"https://github.com/\")\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "collapsed": false + }, + "source": [ + "access github api using pygithub\n" ] }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 55, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "from github import Github\n", + "\n", + "g = Github()" + ] + }, + { + "cell_type": "code", + "execution_count": 56, "metadata": { "collapsed": false }, @@ -575,7 +578,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 57, "metadata": { "collapsed": false }, @@ -610,7 +613,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython2", - "version": "2.7.10" + "version": "2.7.6" } }, "nbformat": 4, From 71154e6dda0b7005ee5ad1853b186c15a422e47b Mon Sep 17 00:00:00 2001 From: Melanie Date: Fri, 1 Apr 2016 18:24:18 +0100 Subject: [PATCH 13/21] play aorund with urlparse --- src/find_github_repo.ipynb | 148 +++++++++++++++++++++++++++++++++---- 1 file changed, 132 insertions(+), 16 deletions(-) diff --git a/src/find_github_repo.ipynb b/src/find_github_repo.ipynb index fc9c80a..c8c7c9a 100644 --- a/src/find_github_repo.ipynb +++ b/src/find_github_repo.ipynb @@ -150,7 +150,7 @@ }, { "cell_type": "code", - "execution_count": 28, + "execution_count": 5, "metadata": { "collapsed": false, "scrolled": true @@ -245,7 +245,7 @@ "25549775 Ann Biomed Eng " ] }, - "execution_count": 28, + "execution_count": 5, "metadata": {}, "output_type": "execute_result" } @@ -303,7 +303,7 @@ }, { "cell_type": "code", - "execution_count": 40, + "execution_count": 7, "metadata": { "collapsed": true }, @@ -322,18 +322,29 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 8, "metadata": { "collapsed": false }, "outputs": [], + "source": [ + "from urlparse import urlparse" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "metadata": { + "collapsed": true + }, + "outputs": [], "source": [ "except_no = 0" ] }, { "cell_type": "code", - "execution_count": 59, + "execution_count": 9, "metadata": { "collapsed": false }, @@ -343,6 +354,8 @@ " abstract = df.iat[i,0]\n", " try:\n", " github_url = str(re.findall(github_url_regex, abstract))\n", + " urlparse(github_url)\n", + " github_project = \n", " df.iat[i,5] = github_url\n", " \n", " except:\n", @@ -350,6 +363,15 @@ " pass" ] }, + { + "cell_type": "code", + "execution_count": 23, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [] + }, { "cell_type": "markdown", "metadata": { @@ -361,7 +383,7 @@ }, { "cell_type": "code", - "execution_count": 51, + "execution_count": 10, "metadata": { "collapsed": false, "scrolled": true @@ -371,7 +393,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "5\n" + "1\n" ] } ], @@ -381,7 +403,7 @@ }, { "cell_type": "code", - "execution_count": 52, + "execution_count": 11, "metadata": { "collapsed": false }, @@ -482,7 +504,7 @@ "25549775 ['archtk.github.com'] " ] }, - "execution_count": 52, + "execution_count": 11, "metadata": {}, "output_type": "execute_result" } @@ -493,7 +515,7 @@ }, { "cell_type": "code", - "execution_count": 53, + "execution_count": 12, "metadata": { "collapsed": false }, @@ -513,7 +535,101 @@ }, { "cell_type": "code", - "execution_count": 54, + "execution_count": 27, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "['archtk.github.com']\n" + ] + } + ], + "source": [ + "test2 = str(df.iat[4,5])\n", + "print test2" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "ParseResult(scheme='', netloc='', path=\"['https://github.com/BioprocessdesignLab/COSMOS']\", params='', query='', fragment='')" + ] + }, + "execution_count": 25, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "urlparse(test)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "ParseResult(scheme='', netloc='', path=\"['archtk.github.com']\", params='', query='', fragment='')" + ] + }, + "execution_count": 28, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "urlparse(test2)" + ] + }, + { + "cell_type": "code", + "execution_count": 34, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "gurl = urlparse(\"https://github.com/BioprosessdesignLab/COSMOS\")" + ] + }, + { + "cell_type": "code", + "execution_count": 35, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "/BioprosessdesignLab/COSMOS\n" + ] + } + ], + "source": [ + "print(gurl.path)" + ] + }, + { + "cell_type": "code", + "execution_count": 13, "metadata": { "collapsed": false }, @@ -524,7 +640,7 @@ "2" ] }, - "execution_count": 54, + "execution_count": 13, "metadata": {}, "output_type": "execute_result" } @@ -545,7 +661,7 @@ }, { "cell_type": "code", - "execution_count": 55, + "execution_count": 14, "metadata": { "collapsed": false }, @@ -558,7 +674,7 @@ }, { "cell_type": "code", - "execution_count": 56, + "execution_count": 15, "metadata": { "collapsed": false }, @@ -578,7 +694,7 @@ }, { "cell_type": "code", - "execution_count": 57, + "execution_count": 16, "metadata": { "collapsed": false }, @@ -592,7 +708,7 @@ } ], "source": [ - "cosmos = g.get_repo(\"BioprocessdesignLab/COSMOS\")\n", + "cosmos = g.get_repo(\"/BioprocessdesignLab/COSMOS\")\n", "print cosmos.description" ] } From 5ae4b182bf7c653eb0faa679726de95615b00a14 Mon Sep 17 00:00:00 2001 From: Melanie Date: Wed, 6 Apr 2016 09:56:55 +0100 Subject: [PATCH 14/21] extracting github project works for all urls of the form https://github.com/project_name --- src/find_github_repo.ipynb | 906 +++++++++++++++++++++++++++++++++++-- 1 file changed, 858 insertions(+), 48 deletions(-) diff --git a/src/find_github_repo.ipynb b/src/find_github_repo.ipynb index c8c7c9a..852f783 100644 --- a/src/find_github_repo.ipynb +++ b/src/find_github_repo.ipynb @@ -24,7 +24,7 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 146, "metadata": { "collapsed": false }, @@ -35,7 +35,7 @@ "['github_pubs.xml', 'README.md']" ] }, - "execution_count": 1, + "execution_count": 146, "metadata": {}, "output_type": "execute_result" } @@ -55,7 +55,7 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": 147, "metadata": { "collapsed": true }, @@ -74,7 +74,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 148, "metadata": { "collapsed": true }, @@ -106,7 +106,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 149, "metadata": { "collapsed": true }, @@ -150,7 +150,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 150, "metadata": { "collapsed": false, "scrolled": true @@ -245,7 +245,7 @@ "25549775 Ann Biomed Eng " ] }, - "execution_count": 5, + "execution_count": 150, "metadata": {}, "output_type": "execute_result" } @@ -274,7 +274,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 151, "metadata": { "collapsed": false }, @@ -285,7 +285,7 @@ "'Stability and sensitivity analyses of biological systems require the ad hocwriting of computer code, which is highly dependent on the particular model and burdensome for large systems. We propose a very accurate strategy to overcome this challenge. Its core concept is the conversion of the model into the format of biochemical systems theory (BST), which greatly facilitates the computation of sensitivities. First, the steady state of interest is determined by integrating the model equations toward the steady state and then using a Newton-Raphson method to fine-tune the result. The second step of conversion into the BST format requires several instances of numerical differentiation. The accuracy of this task is ensured by the use of a complex-variable Taylor scheme for all differentiation steps. The proposed strategy is implemented in a new software program, COSMOS, which automates the stability and sensitivity analysis of essentially arbitrary ODE models in a quick, yet highly accurate manner. The methods underlying the process are theoretically analyzed and illustrated with four representative examples: a simple metabolic reaction model; a model of aspartate-derived amino acid biosynthesis; a TCA-cycle model; and a modified TCA-cycle model. COSMOS has been deposited to https://github.com/BioprocessdesignLab/COSMOS.'" ] }, - "execution_count": 6, + "execution_count": 151, "metadata": {}, "output_type": "execute_result" } @@ -303,7 +303,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 152, "metadata": { "collapsed": true }, @@ -322,7 +322,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 153, "metadata": { "collapsed": false }, @@ -333,7 +333,7 @@ }, { "cell_type": "code", - "execution_count": 23, + "execution_count": 154, "metadata": { "collapsed": true }, @@ -344,7 +344,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 155, "metadata": { "collapsed": false }, @@ -354,10 +354,16 @@ " abstract = df.iat[i,0]\n", " try:\n", " github_url = str(re.findall(github_url_regex, abstract))\n", - " urlparse(github_url)\n", - " github_project = \n", " df.iat[i,5] = github_url\n", " \n", + " github_project = urlparse(github_url[2:-2]).path\n", + " \n", + " if github_project.startswith(\"/\"):\n", + " github_project = github_project[1:]\n", + " \n", + " \n", + " df.iat[i,3] = github_project\n", + " \n", " except:\n", " except_no = except_no + 1 \n", " pass" @@ -365,7 +371,7 @@ }, { "cell_type": "code", - "execution_count": 23, + "execution_count": null, "metadata": { "collapsed": true }, @@ -383,7 +389,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 156, "metadata": { "collapsed": false, "scrolled": true @@ -403,7 +409,7 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 157, "metadata": { "collapsed": false }, @@ -430,7 +436,7 @@ " Stability and sensitivity analyses of biologic...\n", " [(Shiraishi, Fumihide), (Yoshida, Erika), (Voi...\n", " 2015-09-11\n", - " \n", + " BioprocessdesignLab/COSMOS\n", " IEEE/ACM Trans Comput Biol Bioinform\n", " ['https://github.com/BioprocessdesignLab/COSMOS']\n", " \n", @@ -448,7 +454,7 @@ " Remotely sensed data - available at medium to ...\n", " [(Tuck, Sean L), (Phillips, Helen Rp), (Hintze...\n", " 2015-01-05\n", - " \n", + " seantuck12/MODISTools\n", " Ecol Evol\n", " ['https://github.com/seantuck12/MODISTools']\n", " \n", @@ -457,7 +463,7 @@ " Whole-genome bisulfite sequencing (WGBS) is an...\n", " [(Chen, Junfang), (Lutsik, Pavlo), (Akulenko, ...\n", " 2015-01-02\n", - " \n", + " 'https://github.com/Junfang/AKSmooth\n", " J Bioinform Comput Biol\n", " [u'https://github.com/Junfang/AKSmooth']\n", " \n", @@ -466,12 +472,517 @@ " A number of computational approaches have been...\n", " [(Manini, Simone), (Antiga, Luca), (Botti, Lor...\n", " 2015-06-09\n", - " \n", + " archtk.github.com\n", " Ann Biomed Eng\n", " ['archtk.github.com']\n", " \n", + " \n", + " 25543048\n", + " Sampling the conformational space of biologica...\n", + " [(Bouvier, Guillaume), (Desdouits, Nathan), (F...\n", + " 2015-04-28\n", + " \n", + " Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25540185\n", + " With rapidly increasing volumes of biological ...\n", + " [(Meinicke, Peter)]\n", + " 2015-04-28\n", + " \n", + " Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25527832\n", + " Current strategies for SNP and INDEL discovery...\n", + " [(Lindberg, Michael R), (Hall, Ira M), (Quinla...\n", + " 2015-04-12\n", + " \n", + " Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25526884\n", + " An absent word of a word y of length n is a wo...\n", + " [(Barton, Carl), (Heliou, Alice), (Mouchard, L...\n", + " 2015-04-27\n", + " \n", + " BMC Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25524895\n", + " VarSim is a framework for assessing alignment ...\n", + " [(Mu, John C), (Mohiyuddin, Marghoob), (Li, Ji...\n", + " 2015-04-28\n", + " \n", + " Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25521965\n", + " Thyroid cancer is the most common endocrine tu...\n", + " [(Wu, Chengkun), (Schwartz, Jean-Marc), (Braba...\n", + " 2014-12-19\n", + " \n", + " BMC Med Genomics\n", + " []\n", + " \n", + " \n", + " 25520192\n", + " RNA performs a diverse array of important func...\n", + " [(Gardner, Paul P), (Eldai, Hisham)]\n", + " 2015-01-24\n", + " ppgardne/RMfam\n", + " Nucleic Acids Res.\n", + " ['https://github.com/ppgardne/RMfam']\n", + " \n", + " \n", + " 25514851\n", + " We describe an open-source kPAL package that f...\n", + " [(Anvar, Seyed Yahya), (Khachatryan, Lusine), ...\n", + " 2015-02-06\n", + " LUMC/kPAL\n", + " Genome Biol.\n", + " ['https://github.com/LUMC/kPAL']\n", + " \n", + " \n", + " 25505094\n", + " Circular permutation is an important type of p...\n", + " [(Bliven, Spencer E), (Bourne, Philip E), (Prl...\n", + " 2015-04-12\n", + " \n", + " Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25505087\n", + " In bioinformatic applications, computationally...\n", + " [(Völkel, Gunnar), (Lausser, Ludwig), (Schmid,...\n", + " 2015-04-12\n", + " \n", + " Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25505086\n", + " All current mitochondrial haplogroup classific...\n", + " [(Navarro-Gomez, Daniel), (Leipzig, Jeremy), (...\n", + " 2015-04-12\n", + " \n", + " Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25504847\n", + " A standard approach to classifying sets of gen...\n", + " [(Haubold, Bernhard), (Klötzl, Fabian), (Pfaff...\n", + " 2015-04-12\n", + " \n", + " Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25481009\n", + " ICMA, a software framework to create 3D finite...\n", + " [(Hussan, Jagir R), (Hunter, Peter J), (Gladdi...\n", + " 2015-04-12\n", + " \n", + " Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25481007\n", + " Kablammo is a web-based application that produ...\n", + " [(Wintersinger, Jeff A), (Wasmuth, James D)]\n", + " 2015-04-12\n", + " \n", + " Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25480375\n", + " Expression quantitative trait loci (eQTL) stud...\n", + " [(Harvey, Chris T), (Moyerbrailean, Gregory A)...\n", + " 2015-04-12\n", + " \n", + " Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25474353\n", + " Phylogenetic analyses which include fossils or...\n", + " [(Gavryushkina, Alexandra), (Welch, David), (S...\n", + " 2014-12-05\n", + " CompEvol/sampled-ancestors\n", + " PLoS Comput. Biol.\n", + " ['https://github.com/CompEvol/sampled-ancestors']\n", + " \n", + " \n", + " 25461763\n", + " Since the read lengths of high throughput sequ...\n", + " [(Zhu, Xiao), (Leung, Henry C M), (Chin, Franc...\n", + " 2014-12-03\n", + " hitbio/PERGA\n", + " PLoS ONE\n", + " ['https://github.com/hitbio/PERGA']\n", + " \n", + " \n", + " 25452688\n", + " Mobile elements constitute greater than 45% of...\n", + " [(Lee, Wan-Ping), (Wu, Jiantao), (Marth, Gabor...\n", + " 2014-12-02\n", + " jiantao/Tangram\n", + " Cancer Inform\n", + " ['https://github.com/jiantao/Tangram']\n", + " \n", + " \n", + " 25435543\n", + " Isobaric labeling techniques coupled with high...\n", + " [(Sheng, Quanhu), (Li, Rongxia), (Dai, Jie), (...\n", + " 2015-01-31\n", + " shengqh/RCPA.Tools/releases\n", + " Mol. Cell Proteomics\n", + " ['https://github.com/shengqh/RCPA.Tools/releas...\n", + " \n", + " \n", + " 25431162\n", + " Post-translational modifications (PTMs) consti...\n", + " [(Warnecke, Andreas), (Sandalova, Tatyana), (A...\n", + " 2015-04-27\n", + " \n", + " BMC Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25428347\n", + " Genetic screens of an unprecedented scale have...\n", + " [(Diaz, Aaron A), (Qin, Han), (Ramalho-Santos,...\n", + " 2015-02-18\n", + " sourceforge.net/', 'https://github.com/diazlab...\n", + " Nucleic Acids Res.\n", + " ['sourceforge.net/', 'https://github.com/diazl...\n", + " \n", + " \n", + " 25422674\n", + " Rapid molecular typing of bacterial pathogens ...\n", + " [(Inouye, Michael), (Dashnow, Harriet), (Raven...\n", + " 2014-11-25\n", + " katholt.github.io/\n", + " Genome Med\n", + " ['katholt.github.io/']\n", + " \n", + " \n", + " 25414364\n", + " Protein sequence and structure representation ...\n", + " [(Hirsh, Layla), (Piovesan, Damiano), (Giollo,...\n", + " 2015-04-03\n", + " \n", + " Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25414349\n", + " The emergence of new sequencing technologies h...\n", + " [(Croucher, Nicholas J), (Page, Andrew J), (Co...\n", + " 2015-02-18\n", + " github.com/\n", + " Nucleic Acids Res.\n", + " ['github.com/']\n", + " \n", + " \n", + " 25410596\n", + " Whole-genome sequences are now available for m...\n", + " [(Treangen, Todd J), (Ondov, Brian D), (Koren,...\n", + " 2015-01-07\n", + " marbl/harvest\n", + " Genome Biol.\n", + " ['http://github.com/marbl/harvest']\n", + " \n", + " \n", + " ...\n", + " ...\n", + " ...\n", + " ...\n", + " ...\n", + " ...\n", + " ...\n", + " \n", + " \n", + " 25262154\n", + " We have created a Shiny-based Web application,...\n", + " [(McMurdie, Paul J), (Holmes, Susan)]\n", + " 2015-01-10\n", + " \n", + " Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25254639\n", + " Since its identification in 1983, HIV-1 has be...\n", + " [(Hepler, N Lance), (Scheffler, Konrad), (Weav...\n", + " 2014-09-26\n", + " veg/idepi\n", + " PLoS Comput. Biol.\n", + " ['https://github.com/veg/idepi']\n", + " \n", + " \n", + " 25253358\n", + " It has recently become possible to rapidly and...\n", + " [(Beckmann, Noam D), (Karri, Sashank), (Fang, ...\n", + " 2014-09-25\n", + " \n", + " BMC Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25252881\n", + " Although there are many different algorithms a...\n", + " [(Gholami, Milad), (Arbabi, Aryan), (Sharifi-Z...\n", + " 2014-09-25\n", + " \n", + " BMC Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25236461\n", + " We present a Web service to access Ensembl dat...\n", + " [(Yates, Andrew), (Beal, Kathryn), (Keenan, St...\n", + " 2014-12-20\n", + " \n", + " Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25232314\n", + " Neuromorphic hardware offers an electronic sub...\n", + " [(Stefanini, Fabio), (Neftci, Emre O), (Sheik,...\n", + " 2014-09-18\n", + " inincs/pyNCS\n", + " Front Neuroinform\n", + " ['https://github.com/inincs/pyNCS']\n", + " \n", + " \n", + " 25231498\n", + " Mechanistic 'whole-cell' models are needed to ...\n", + " [(Karr, Jonathan R), (Phillips, Nolan C), (Cov...\n", + " 2014-09-18\n", + " \n", + " Database (Oxford)\n", + " []\n", + " \n", + " \n", + " 25212755\n", + " cddApp is a Cytoscape extension that supports ...\n", + " [(Morris, John H), (Wu, Allan), (Yamashita, Ro...\n", + " 2014-12-20\n", + " \n", + " Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25206364\n", + " The detection of \"signatures of selection\" is ...\n", + " [(Cadzow, Murray), (Boocock, James), (Nguyen, ...\n", + " 2014-09-10\n", + " www.github.com/\n", + " Front Genet\n", + " ['www.github.com/']\n", + " \n", + " \n", + " 25202595\n", + " None\n", + " [(Salinas, Nelson R), (Little, Damon P)]\n", + " 2014-09-09\n", + " \n", + " Appl Plant Sci\n", + " \n", + " \n", + " \n", + " 25192740\n", + " Somatic internal tandem duplications (ITDs) ar...\n", + " [(Chiba, Kenichi), (Shiraishi, Yuichi), (Nagat...\n", + " 2014-12-20\n", + " ken0-1n/Genomon-ITDetector\n", + " Bioinformatics\n", + " ['https://github.com/ken0-1n/Genomon-ITDetector']\n", + " \n", + " \n", + " 25192739\n", + " We describe mod_bio, a set of modules for the ...\n", + " [(Lindenbaum, Pierre), (Redon, Richard)]\n", + " 2014-12-20\n", + " \n", + " Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25189781\n", + " Next-generation sequencing experiments, such a...\n", + " [(Robinson, David G), (Storey, John D)]\n", + " 2014-11-26\n", + " \n", + " Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25189778\n", + " The analysis of large biological datasets ofte...\n", + " [(Cingolani, Pablo), (Sladek, Rob), (Blanchett...\n", + " 2014-12-20\n", + " \n", + " Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25183856\n", + " This article describes our participation of th...\n", + " [(Zhu, Dongqing), (Li, Dingcheng), (Carterette...\n", + " 2014-09-03\n", + " \n", + " Database (Oxford)\n", + " []\n", + " \n", + " \n", + " 25183485\n", + " Often during the analysis of biological data, ...\n", + " [(Pomyen, Yotsawat), (Segura, Marcelo), (Ebbel...\n", + " 2014-12-20\n", + " \n", + " Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25181531\n", + " Managing data from large-scale projects (such ...\n", + " [(Samur, Mehmet Kemal)]\n", + " 2014-09-03\n", + " \n", + " PLoS ONE\n", + " []\n", + " \n", + " \n", + " 25178461\n", + " Parallel visualization of multiple individual ...\n", + " [(Lajugie, Julien), (Fourel, Nicolas), (Bouhas...\n", + " 2014-12-20\n", + " \n", + " Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25177538\n", + " We present a performance-optimized algorithm, ...\n", + " [(Rideout, Jai Ram), (He, Yan), (Navas-Molina,...\n", + " 2014-09-01\n", + " \n", + " PeerJ\n", + " []\n", + " \n", + " \n", + " 25170024\n", + " Genome-wide association studies (GWAS) have id...\n", + " [(Burren, Oliver S), (Guo, Hui), (Wallace, Chr...\n", + " 2014-11-26\n", + " \n", + " Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25165093\n", + " I present MR_predictor, a simulation engine de...\n", + " [(Voight, Benjamin F)]\n", + " 2014-11-26\n", + " \n", + " Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25161247\n", + " Human immunodeficiency virus (HIV) and cancer ...\n", + " [(Gönen, Mehmet), (Margolin, Adam A)]\n", + " 2014-08-27\n", + " \n", + " Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25161245\n", + " Species trees provide insight into basic biolo...\n", + " [(Mirarab, S), (Reaz, R), (Bayzid, Md S), (Zim...\n", + " 2014-08-27\n", + " \n", + " Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25161244\n", + " The construction of statistics for summarizing...\n", + " [(Benner, Philipp), (Bačák, Miroslav), (Bourgu...\n", + " 2014-08-27\n", + " \n", + " Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25161237\n", + " Recently it has been shown that the quality of...\n", + " [(Michel, Mirco), (Hayat, Sikander), (Skwark, ...\n", + " 2014-08-27\n", + " \n", + " Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25161223\n", + " Accurate haplotyping-determining from which pa...\n", + " [(Kuleshov, Volodymyr)]\n", + " 2014-08-27\n", + " \n", + " Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25160522\n", + " Many tumors are composed of genetically diverg...\n", + " [(Qiao, Yi), (Quinlan, Aaron R), (Jazaeri, Ami...\n", + " 2014-12-04\n", + " yiq/SubcloneSeeker\n", + " Genome Biol.\n", + " ['https://github.com/yiq/SubcloneSeeker']\n", + " \n", + " \n", + " 25159222\n", + " First pass methods based on BLAST match are co...\n", + " [(Zhu, Qiyun), (Kosoy, Michael), (Dittmar, Kat...\n", + " 2014-09-02\n", + " \n", + " BMC Genomics\n", + " []\n", + " \n", + " \n", + " 25147360\n", + " pViz.js is a visualization library for display...\n", + " [(Mukhyala, Kiran), (Masselot, Alexandre)]\n", + " 2014-11-26\n", + " \n", + " Bioinformatics\n", + " []\n", + " \n", + " \n", + " 25147359\n", + " Current sequence alignment browsers allow visu...\n", + " [(Gymrek, Melissa)]\n", + " 2014-11-26\n", + " \n", + " Bioinformatics\n", + " []\n", + " \n", " \n", "\n", + "

100 rows × 6 columns

\n", "
" ], "text/plain": [ @@ -481,6 +992,62 @@ "25558360 Remotely sensed data - available at medium to ... \n", "25553811 Whole-genome bisulfite sequencing (WGBS) is an... \n", "25549775 A number of computational approaches have been... \n", + "25543048 Sampling the conformational space of biologica... \n", + "25540185 With rapidly increasing volumes of biological ... \n", + "25527832 Current strategies for SNP and INDEL discovery... \n", + "25526884 An absent word of a word y of length n is a wo... \n", + "25524895 VarSim is a framework for assessing alignment ... \n", + "25521965 Thyroid cancer is the most common endocrine tu... \n", + "25520192 RNA performs a diverse array of important func... \n", + "25514851 We describe an open-source kPAL package that f... \n", + "25505094 Circular permutation is an important type of p... \n", + "25505087 In bioinformatic applications, computationally... \n", + "25505086 All current mitochondrial haplogroup classific... \n", + "25504847 A standard approach to classifying sets of gen... \n", + "25481009 ICMA, a software framework to create 3D finite... \n", + "25481007 Kablammo is a web-based application that produ... \n", + "25480375 Expression quantitative trait loci (eQTL) stud... \n", + "25474353 Phylogenetic analyses which include fossils or... \n", + "25461763 Since the read lengths of high throughput sequ... \n", + "25452688 Mobile elements constitute greater than 45% of... \n", + "25435543 Isobaric labeling techniques coupled with high... \n", + "25431162 Post-translational modifications (PTMs) consti... \n", + "25428347 Genetic screens of an unprecedented scale have... \n", + "25422674 Rapid molecular typing of bacterial pathogens ... \n", + "25414364 Protein sequence and structure representation ... \n", + "25414349 The emergence of new sequencing technologies h... \n", + "25410596 Whole-genome sequences are now available for m... \n", + "... ... \n", + "25262154 We have created a Shiny-based Web application,... \n", + "25254639 Since its identification in 1983, HIV-1 has be... \n", + "25253358 It has recently become possible to rapidly and... \n", + "25252881 Although there are many different algorithms a... \n", + "25236461 We present a Web service to access Ensembl dat... \n", + "25232314 Neuromorphic hardware offers an electronic sub... \n", + "25231498 Mechanistic 'whole-cell' models are needed to ... \n", + "25212755 cddApp is a Cytoscape extension that supports ... \n", + "25206364 The detection of \"signatures of selection\" is ... \n", + "25202595 None \n", + "25192740 Somatic internal tandem duplications (ITDs) ar... \n", + "25192739 We describe mod_bio, a set of modules for the ... \n", + "25189781 Next-generation sequencing experiments, such a... \n", + "25189778 The analysis of large biological datasets ofte... \n", + "25183856 This article describes our participation of th... \n", + "25183485 Often during the analysis of biological data, ... \n", + "25181531 Managing data from large-scale projects (such ... \n", + "25178461 Parallel visualization of multiple individual ... \n", + "25177538 We present a performance-optimized algorithm, ... \n", + "25170024 Genome-wide association studies (GWAS) have id... \n", + "25165093 I present MR_predictor, a simulation engine de... \n", + "25161247 Human immunodeficiency virus (HIV) and cancer ... \n", + "25161245 Species trees provide insight into basic biolo... \n", + "25161244 The construction of statistics for summarizing... \n", + "25161237 Recently it has been shown that the quality of... \n", + "25161223 Accurate haplotyping-determining from which pa... \n", + "25160522 Many tumors are composed of genetically diverg... \n", + "25159222 First pass methods based on BLAST match are co... \n", + "25147360 pViz.js is a visualization library for display... \n", + "25147359 Current sequence alignment browsers allow visu... \n", "\n", " Authors Date \\\n", "26357045 [(Shiraishi, Fumihide), (Yoshida, Erika), (Voi... 2015-09-11 \n", @@ -488,34 +1055,267 @@ "25558360 [(Tuck, Sean L), (Phillips, Helen Rp), (Hintze... 2015-01-05 \n", "25553811 [(Chen, Junfang), (Lutsik, Pavlo), (Akulenko, ... 2015-01-02 \n", "25549775 [(Manini, Simone), (Antiga, Luca), (Botti, Lor... 2015-06-09 \n", + "25543048 [(Bouvier, Guillaume), (Desdouits, Nathan), (F... 2015-04-28 \n", + "25540185 [(Meinicke, Peter)] 2015-04-28 \n", + "25527832 [(Lindberg, Michael R), (Hall, Ira M), (Quinla... 2015-04-12 \n", + "25526884 [(Barton, Carl), (Heliou, Alice), (Mouchard, L... 2015-04-27 \n", + "25524895 [(Mu, John C), (Mohiyuddin, Marghoob), (Li, Ji... 2015-04-28 \n", + "25521965 [(Wu, Chengkun), (Schwartz, Jean-Marc), (Braba... 2014-12-19 \n", + "25520192 [(Gardner, Paul P), (Eldai, Hisham)] 2015-01-24 \n", + "25514851 [(Anvar, Seyed Yahya), (Khachatryan, Lusine), ... 2015-02-06 \n", + "25505094 [(Bliven, Spencer E), (Bourne, Philip E), (Prl... 2015-04-12 \n", + "25505087 [(Völkel, Gunnar), (Lausser, Ludwig), (Schmid,... 2015-04-12 \n", + "25505086 [(Navarro-Gomez, Daniel), (Leipzig, Jeremy), (... 2015-04-12 \n", + "25504847 [(Haubold, Bernhard), (Klötzl, Fabian), (Pfaff... 2015-04-12 \n", + "25481009 [(Hussan, Jagir R), (Hunter, Peter J), (Gladdi... 2015-04-12 \n", + "25481007 [(Wintersinger, Jeff A), (Wasmuth, James D)] 2015-04-12 \n", + "25480375 [(Harvey, Chris T), (Moyerbrailean, Gregory A)... 2015-04-12 \n", + "25474353 [(Gavryushkina, Alexandra), (Welch, David), (S... 2014-12-05 \n", + "25461763 [(Zhu, Xiao), (Leung, Henry C M), (Chin, Franc... 2014-12-03 \n", + "25452688 [(Lee, Wan-Ping), (Wu, Jiantao), (Marth, Gabor... 2014-12-02 \n", + "25435543 [(Sheng, Quanhu), (Li, Rongxia), (Dai, Jie), (... 2015-01-31 \n", + "25431162 [(Warnecke, Andreas), (Sandalova, Tatyana), (A... 2015-04-27 \n", + "25428347 [(Diaz, Aaron A), (Qin, Han), (Ramalho-Santos,... 2015-02-18 \n", + "25422674 [(Inouye, Michael), (Dashnow, Harriet), (Raven... 2014-11-25 \n", + "25414364 [(Hirsh, Layla), (Piovesan, Damiano), (Giollo,... 2015-04-03 \n", + "25414349 [(Croucher, Nicholas J), (Page, Andrew J), (Co... 2015-02-18 \n", + "25410596 [(Treangen, Todd J), (Ondov, Brian D), (Koren,... 2015-01-07 \n", + "... ... ... \n", + "25262154 [(McMurdie, Paul J), (Holmes, Susan)] 2015-01-10 \n", + "25254639 [(Hepler, N Lance), (Scheffler, Konrad), (Weav... 2014-09-26 \n", + "25253358 [(Beckmann, Noam D), (Karri, Sashank), (Fang, ... 2014-09-25 \n", + "25252881 [(Gholami, Milad), (Arbabi, Aryan), (Sharifi-Z... 2014-09-25 \n", + "25236461 [(Yates, Andrew), (Beal, Kathryn), (Keenan, St... 2014-12-20 \n", + "25232314 [(Stefanini, Fabio), (Neftci, Emre O), (Sheik,... 2014-09-18 \n", + "25231498 [(Karr, Jonathan R), (Phillips, Nolan C), (Cov... 2014-09-18 \n", + "25212755 [(Morris, John H), (Wu, Allan), (Yamashita, Ro... 2014-12-20 \n", + "25206364 [(Cadzow, Murray), (Boocock, James), (Nguyen, ... 2014-09-10 \n", + "25202595 [(Salinas, Nelson R), (Little, Damon P)] 2014-09-09 \n", + "25192740 [(Chiba, Kenichi), (Shiraishi, Yuichi), (Nagat... 2014-12-20 \n", + "25192739 [(Lindenbaum, Pierre), (Redon, Richard)] 2014-12-20 \n", + "25189781 [(Robinson, David G), (Storey, John D)] 2014-11-26 \n", + "25189778 [(Cingolani, Pablo), (Sladek, Rob), (Blanchett... 2014-12-20 \n", + "25183856 [(Zhu, Dongqing), (Li, Dingcheng), (Carterette... 2014-09-03 \n", + "25183485 [(Pomyen, Yotsawat), (Segura, Marcelo), (Ebbel... 2014-12-20 \n", + "25181531 [(Samur, Mehmet Kemal)] 2014-09-03 \n", + "25178461 [(Lajugie, Julien), (Fourel, Nicolas), (Bouhas... 2014-12-20 \n", + "25177538 [(Rideout, Jai Ram), (He, Yan), (Navas-Molina,... 2014-09-01 \n", + "25170024 [(Burren, Oliver S), (Guo, Hui), (Wallace, Chr... 2014-11-26 \n", + "25165093 [(Voight, Benjamin F)] 2014-11-26 \n", + "25161247 [(Gönen, Mehmet), (Margolin, Adam A)] 2014-08-27 \n", + "25161245 [(Mirarab, S), (Reaz, R), (Bayzid, Md S), (Zim... 2014-08-27 \n", + "25161244 [(Benner, Philipp), (Bačák, Miroslav), (Bourgu... 2014-08-27 \n", + "25161237 [(Michel, Mirco), (Hayat, Sikander), (Skwark, ... 2014-08-27 \n", + "25161223 [(Kuleshov, Volodymyr)] 2014-08-27 \n", + "25160522 [(Qiao, Yi), (Quinlan, Aaron R), (Jazaeri, Ami... 2014-12-04 \n", + "25159222 [(Zhu, Qiyun), (Kosoy, Michael), (Dittmar, Kat... 2014-09-02 \n", + "25147360 [(Mukhyala, Kiran), (Masselot, Alexandre)] 2014-11-26 \n", + "25147359 [(Gymrek, Melissa)] 2014-11-26 \n", "\n", - " Github Journal \\\n", - "26357045 IEEE/ACM Trans Comput Biol Bioinform \n", - "25601296 JMIR Med Inform \n", - "25558360 Ecol Evol \n", - "25553811 J Bioinform Comput Biol \n", - "25549775 Ann Biomed Eng \n", + " Github \\\n", + "26357045 BioprocessdesignLab/COSMOS \n", + "25601296 \n", + "25558360 seantuck12/MODISTools \n", + "25553811 'https://github.com/Junfang/AKSmooth \n", + "25549775 archtk.github.com \n", + "25543048 \n", + "25540185 \n", + "25527832 \n", + "25526884 \n", + "25524895 \n", + "25521965 \n", + "25520192 ppgardne/RMfam \n", + "25514851 LUMC/kPAL \n", + "25505094 \n", + "25505087 \n", + "25505086 \n", + "25504847 \n", + "25481009 \n", + "25481007 \n", + "25480375 \n", + "25474353 CompEvol/sampled-ancestors \n", + "25461763 hitbio/PERGA \n", + "25452688 jiantao/Tangram \n", + "25435543 shengqh/RCPA.Tools/releases \n", + "25431162 \n", + "25428347 sourceforge.net/', 'https://github.com/diazlab... \n", + "25422674 katholt.github.io/ \n", + "25414364 \n", + "25414349 github.com/ \n", + "25410596 marbl/harvest \n", + "... ... \n", + "25262154 \n", + "25254639 veg/idepi \n", + "25253358 \n", + "25252881 \n", + "25236461 \n", + "25232314 inincs/pyNCS \n", + "25231498 \n", + "25212755 \n", + "25206364 www.github.com/ \n", + "25202595 \n", + "25192740 ken0-1n/Genomon-ITDetector \n", + "25192739 \n", + "25189781 \n", + "25189778 \n", + "25183856 \n", + "25183485 \n", + "25181531 \n", + "25178461 \n", + "25177538 \n", + "25170024 \n", + "25165093 \n", + "25161247 \n", + "25161245 \n", + "25161244 \n", + "25161237 \n", + "25161223 \n", + "25160522 yiq/SubcloneSeeker \n", + "25159222 \n", + "25147360 \n", + "25147359 \n", + "\n", + " Journal \\\n", + "26357045 IEEE/ACM Trans Comput Biol Bioinform \n", + "25601296 JMIR Med Inform \n", + "25558360 Ecol Evol \n", + "25553811 J Bioinform Comput Biol \n", + "25549775 Ann Biomed Eng \n", + "25543048 Bioinformatics \n", + "25540185 Bioinformatics \n", + "25527832 Bioinformatics \n", + "25526884 BMC Bioinformatics \n", + "25524895 Bioinformatics \n", + "25521965 BMC Med Genomics \n", + "25520192 Nucleic Acids Res. \n", + "25514851 Genome Biol. \n", + "25505094 Bioinformatics \n", + "25505087 Bioinformatics \n", + "25505086 Bioinformatics \n", + "25504847 Bioinformatics \n", + "25481009 Bioinformatics \n", + "25481007 Bioinformatics \n", + "25480375 Bioinformatics \n", + "25474353 PLoS Comput. Biol. \n", + "25461763 PLoS ONE \n", + "25452688 Cancer Inform \n", + "25435543 Mol. Cell Proteomics \n", + "25431162 BMC Bioinformatics \n", + "25428347 Nucleic Acids Res. \n", + "25422674 Genome Med \n", + "25414364 Bioinformatics \n", + "25414349 Nucleic Acids Res. \n", + "25410596 Genome Biol. \n", + "... ... \n", + "25262154 Bioinformatics \n", + "25254639 PLoS Comput. Biol. \n", + "25253358 BMC Bioinformatics \n", + "25252881 BMC Bioinformatics \n", + "25236461 Bioinformatics \n", + "25232314 Front Neuroinform \n", + "25231498 Database (Oxford) \n", + "25212755 Bioinformatics \n", + "25206364 Front Genet \n", + "25202595 Appl Plant Sci \n", + "25192740 Bioinformatics \n", + "25192739 Bioinformatics \n", + "25189781 Bioinformatics \n", + "25189778 Bioinformatics \n", + "25183856 Database (Oxford) \n", + "25183485 Bioinformatics \n", + "25181531 PLoS ONE \n", + "25178461 Bioinformatics \n", + "25177538 PeerJ \n", + "25170024 Bioinformatics \n", + "25165093 Bioinformatics \n", + "25161247 Bioinformatics \n", + "25161245 Bioinformatics \n", + "25161244 Bioinformatics \n", + "25161237 Bioinformatics \n", + "25161223 Bioinformatics \n", + "25160522 Genome Biol. \n", + "25159222 BMC Genomics \n", + "25147360 Bioinformatics \n", + "25147359 Bioinformatics \n", "\n", " Url \n", "26357045 ['https://github.com/BioprocessdesignLab/COSMOS'] \n", "25601296 [] \n", "25558360 ['https://github.com/seantuck12/MODISTools'] \n", "25553811 [u'https://github.com/Junfang/AKSmooth'] \n", - "25549775 ['archtk.github.com'] " + "25549775 ['archtk.github.com'] \n", + "25543048 [] \n", + "25540185 [] \n", + "25527832 [] \n", + "25526884 [] \n", + "25524895 [] \n", + "25521965 [] \n", + "25520192 ['https://github.com/ppgardne/RMfam'] \n", + "25514851 ['https://github.com/LUMC/kPAL'] \n", + "25505094 [] \n", + "25505087 [] \n", + "25505086 [] \n", + "25504847 [] \n", + "25481009 [] \n", + "25481007 [] \n", + "25480375 [] \n", + "25474353 ['https://github.com/CompEvol/sampled-ancestors'] \n", + "25461763 ['https://github.com/hitbio/PERGA'] \n", + "25452688 ['https://github.com/jiantao/Tangram'] \n", + "25435543 ['https://github.com/shengqh/RCPA.Tools/releas... \n", + "25431162 [] \n", + "25428347 ['sourceforge.net/', 'https://github.com/diazl... \n", + "25422674 ['katholt.github.io/'] \n", + "25414364 [] \n", + "25414349 ['github.com/'] \n", + "25410596 ['http://github.com/marbl/harvest'] \n", + "... ... \n", + "25262154 [] \n", + "25254639 ['https://github.com/veg/idepi'] \n", + "25253358 [] \n", + "25252881 [] \n", + "25236461 [] \n", + "25232314 ['https://github.com/inincs/pyNCS'] \n", + "25231498 [] \n", + "25212755 [] \n", + "25206364 ['www.github.com/'] \n", + "25202595 \n", + "25192740 ['https://github.com/ken0-1n/Genomon-ITDetector'] \n", + "25192739 [] \n", + "25189781 [] \n", + "25189778 [] \n", + "25183856 [] \n", + "25183485 [] \n", + "25181531 [] \n", + "25178461 [] \n", + "25177538 [] \n", + "25170024 [] \n", + "25165093 [] \n", + "25161247 [] \n", + "25161245 [] \n", + "25161244 [] \n", + "25161237 [] \n", + "25161223 [] \n", + "25160522 ['https://github.com/yiq/SubcloneSeeker'] \n", + "25159222 [] \n", + "25147360 [] \n", + "25147359 [] \n", + "\n", + "[100 rows x 6 columns]" ] }, - "execution_count": 11, + "execution_count": 157, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "df.head()" + "df.head(100)" ] }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 158, "metadata": { "collapsed": false }, @@ -535,7 +1335,7 @@ }, { "cell_type": "code", - "execution_count": 27, + "execution_count": 159, "metadata": { "collapsed": false }, @@ -555,7 +1355,7 @@ }, { "cell_type": "code", - "execution_count": 25, + "execution_count": 160, "metadata": { "collapsed": false }, @@ -566,7 +1366,7 @@ "ParseResult(scheme='', netloc='', path=\"['https://github.com/BioprocessdesignLab/COSMOS']\", params='', query='', fragment='')" ] }, - "execution_count": 25, + "execution_count": 160, "metadata": {}, "output_type": "execute_result" } @@ -577,7 +1377,7 @@ }, { "cell_type": "code", - "execution_count": 28, + "execution_count": 161, "metadata": { "collapsed": false }, @@ -588,7 +1388,7 @@ "ParseResult(scheme='', netloc='', path=\"['archtk.github.com']\", params='', query='', fragment='')" ] }, - "execution_count": 28, + "execution_count": 161, "metadata": {}, "output_type": "execute_result" } @@ -599,7 +1399,7 @@ }, { "cell_type": "code", - "execution_count": 34, + "execution_count": 162, "metadata": { "collapsed": false }, @@ -610,7 +1410,7 @@ }, { "cell_type": "code", - "execution_count": 35, + "execution_count": 163, "metadata": { "collapsed": false }, @@ -629,7 +1429,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 164, "metadata": { "collapsed": false }, @@ -640,7 +1440,7 @@ "2" ] }, - "execution_count": 13, + "execution_count": 164, "metadata": {}, "output_type": "execute_result" } @@ -661,7 +1461,7 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 165, "metadata": { "collapsed": false }, @@ -674,7 +1474,7 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 166, "metadata": { "collapsed": false }, @@ -694,16 +1494,26 @@ }, { "cell_type": "code", - "execution_count": 16, + "execution_count": 167, "metadata": { "collapsed": false }, "outputs": [ { - "name": "stdout", - "output_type": "stream", - "text": [ - "Computation of Sensitivities in Model ODE Systems\n" + "ename": "UnknownObjectException", + "evalue": "404 {u'documentation_url': u'https://developer.github.com/v3', u'message': u'Not Found'}", + "output_type": "error", + "traceback": [ + "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[1;31mUnknownObjectException\u001b[0m Traceback (most recent call last)", + "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m()\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[0mcosmos\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mg\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_repo\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"/BioprocessdesignLab/COSMOS\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 2\u001b[1;33m \u001b[1;32mprint\u001b[0m \u001b[0mcosmos\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdescription\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m", + "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/Repository.pyc\u001b[0m in \u001b[0;36mdescription\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 185\u001b[0m \u001b[1;33m:\u001b[0m\u001b[0mtype\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mstring\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 186\u001b[0m \"\"\"\n\u001b[1;32m--> 187\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_completeIfNotSet\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_description\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 188\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_description\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvalue\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 189\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/GithubObject.pyc\u001b[0m in \u001b[0;36m_completeIfNotSet\u001b[1;34m(self, value)\u001b[0m\n\u001b[0;32m 226\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_completeIfNotSet\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 227\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mvalue\u001b[0m \u001b[1;32mis\u001b[0m \u001b[0mNotSet\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 228\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_completeIfNeeded\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 229\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 230\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_completeIfNeeded\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/GithubObject.pyc\u001b[0m in \u001b[0;36m_completeIfNeeded\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 230\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_completeIfNeeded\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 231\u001b[0m \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__completed\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 232\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__complete\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 233\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 234\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m__complete\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/GithubObject.pyc\u001b[0m in \u001b[0;36m__complete\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 235\u001b[0m headers, data = self._requester.requestJsonAndCheck(\n\u001b[0;32m 236\u001b[0m \u001b[1;34m\"GET\"\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 237\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_url\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvalue\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 238\u001b[0m )\n\u001b[0;32m 239\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_storeAndUseAttributes\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mheaders\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/Requester.pyc\u001b[0m in \u001b[0;36mrequestJsonAndCheck\u001b[1;34m(self, verb, url, parameters, headers, input, cnx)\u001b[0m\n\u001b[0;32m 169\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 170\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mrequestJsonAndCheck\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mverb\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mheaders\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minput\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcnx\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 171\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__check\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrequestJson\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mverb\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mheaders\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minput\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcnx\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 172\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 173\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mrequestMultipartAndCheck\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mverb\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mheaders\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minput\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/Requester.pyc\u001b[0m in \u001b[0;36m__check\u001b[1;34m(self, status, responseHeaders, output)\u001b[0m\n\u001b[0;32m 177\u001b[0m \u001b[0moutput\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__structuredFromJson\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0moutput\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 178\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mstatus\u001b[0m \u001b[1;33m>=\u001b[0m \u001b[1;36m400\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 179\u001b[1;33m \u001b[1;32mraise\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__createException\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mstatus\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mresponseHeaders\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0moutput\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 180\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mresponseHeaders\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0moutput\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 181\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;31mUnknownObjectException\u001b[0m: 404 {u'documentation_url': u'https://developer.github.com/v3', u'message': u'Not Found'}" ] } ], From dd67f23ad405b15c81ffe223a9b30e4665db9637 Mon Sep 17 00:00:00 2001 From: Melanie Date: Wed, 6 Apr 2016 10:34:28 +0100 Subject: [PATCH 15/21] github project extraction seems to work for most, but not all urls --- src/find_github_repo.ipynb | 664 ++++++++++++++++++------------------- 1 file changed, 332 insertions(+), 332 deletions(-) diff --git a/src/find_github_repo.ipynb b/src/find_github_repo.ipynb index 852f783..58556a2 100644 --- a/src/find_github_repo.ipynb +++ b/src/find_github_repo.ipynb @@ -409,7 +409,7 @@ }, { "cell_type": "code", - "execution_count": 157, + "execution_count": 168, "metadata": { "collapsed": false }, @@ -711,278 +711,278 @@ " ...\n", " \n", " \n", - " 25262154\n", - " We have created a Shiny-based Web application,...\n", - " [(McMurdie, Paul J), (Holmes, Susan)]\n", - " 2015-01-10\n", + " 24728855\n", + " Phylogenetic comparative methods are essential...\n", + " [(Pennell, Matthew W), (Eastman, Jonathan M), ...\n", + " 2014-07-19\n", " \n", " Bioinformatics\n", " []\n", " \n", " \n", - " 25254639\n", - " Since its identification in 1983, HIV-1 has be...\n", - " [(Hepler, N Lance), (Scheffler, Konrad), (Weav...\n", - " 2014-09-26\n", - " veg/idepi\n", - " PLoS Comput. Biol.\n", - " ['https://github.com/veg/idepi']\n", + " 24727652\n", + " Genomic information is encoded on a wide range...\n", + " [(Knijnenburg, Theo A), (Ramsey, Stephen A), (...\n", + " 2014-05-30\n", + " tknijnen/msr/\n", + " Nat. Methods\n", + " ['https://github.com/tknijnen/msr/']\n", " \n", " \n", - " 25253358\n", - " It has recently become possible to rapidly and...\n", - " [(Beckmann, Noam D), (Karri, Sashank), (Fang, ...\n", - " 2014-09-25\n", + " 24715980\n", + " Signaling pathways provide essential informati...\n", + " [(Villaveces, Jose M), (Jimenez, Rafael C), (H...\n", + " 2014-04-09\n", " \n", - " BMC Bioinformatics\n", + " F1000Res\n", " []\n", " \n", " \n", - " 25252881\n", - " Although there are many different algorithms a...\n", - " [(Gholami, Milad), (Arbabi, Aryan), (Sharifi-Z...\n", - " 2014-09-25\n", + " 24707447\n", + " Background Understanding the evolutionary rela...\n", + " [(Grant, Jessica R), (Katz, Laura A)]\n", + " 2014-04-07\n", " \n", - " BMC Bioinformatics\n", + " PLoS Curr\n", " []\n", " \n", " \n", - " 25236461\n", - " We present a Web service to access Ensembl dat...\n", - " [(Yates, Andrew), (Beal, Kathryn), (Keenan, St...\n", - " 2014-12-20\n", - " \n", - " Bioinformatics\n", - " []\n", + " 24703969\n", + " Advances in next-generation sequencing (NGS) t...\n", + " [(Guo, Yan), (Zhao, Shilin), (Sheng, Quanhu), ...\n", + " 2014-06-14\n", + " slzhao/QC3\n", + " Genomics\n", + " ['https://github.com/slzhao/QC3']\n", " \n", " \n", - " 25232314\n", - " Neuromorphic hardware offers an electronic sub...\n", - " [(Stefanini, Fabio), (Neftci, Emre O), (Sheik,...\n", - " 2014-09-18\n", - " inincs/pyNCS\n", - " Front Neuroinform\n", - " ['https://github.com/inincs/pyNCS']\n", + " 24700534\n", + " We here present GradientOptimizer, an intuitiv...\n", + " [(Moruz, Luminita), (Käll, Lukas)]\n", + " 2014-06-12\n", + " statisticalbiotechnology/NonlinearGradientsUI\n", + " Proteomics\n", + " ['https://github.com/statisticalbiotechnology/...\n", " \n", " \n", - " 25231498\n", - " Mechanistic 'whole-cell' models are needed to ...\n", - " [(Karr, Jonathan R), (Phillips, Nolan C), (Cov...\n", - " 2014-09-18\n", - " \n", - " Database (Oxford)\n", - " []\n", + " 24695491\n", + " The primary goal of genome-wide association st...\n", + " [(Botta, Vincent), (Louppe, Gilles), (Geurts, ...\n", + " 2014-04-03\n", + " www.montefiore.ulg.ac.be/', 'github.com/\n", + " PLoS ONE\n", + " ['www.montefiore.ulg.ac.be/', 'github.com/']\n", " \n", " \n", - " 25212755\n", - " cddApp is a Cytoscape extension that supports ...\n", - " [(Morris, John H), (Wu, Allan), (Yamashita, Ro...\n", - " 2014-12-20\n", + " 24695406\n", + " Next-generation sequencing (NGS) has revolutio...\n", + " [(Li, Yi), (Xie, Xiaohui)]\n", + " 2014-07-19\n", " \n", " Bioinformatics\n", " []\n", " \n", " \n", - " 25206364\n", - " The detection of \"signatures of selection\" is ...\n", - " [(Cadzow, Murray), (Boocock, James), (Nguyen, ...\n", - " 2014-09-10\n", - " www.github.com/\n", - " Front Genet\n", - " ['www.github.com/']\n", + " 24688855\n", + " We present a powerful Python library to quickl...\n", + " [(Christensen, Anders S), (Hamelryck, Thomas),...\n", + " 2014-04-01\n", + " jensengroup/fragbuilder/\n", + " PeerJ\n", + " ['https://github.com/jensengroup/fragbuilder/']\n", " \n", " \n", - " 25202595\n", - " None\n", - " [(Salinas, Nelson R), (Little, Damon P)]\n", - " 2014-09-09\n", - " \n", - " Appl Plant Sci\n", - " \n", + " 24681267\n", + " Symmetry is an important feature of protein te...\n", + " [(Myers-Turnbull, Douglas), (Bliven, Spencer E...\n", + " 2014-05-06\n", + " source.rcsb.org/', 'https://github.com/rcsb/sy...\n", + " J. Mol. Biol.\n", + " ['source.rcsb.org/', 'https://github.com/rcsb/...\n", " \n", " \n", - " 25192740\n", - " Somatic internal tandem duplications (ITDs) ar...\n", - " [(Chiba, Kenichi), (Shiraishi, Yuichi), (Nagat...\n", - " 2014-12-20\n", - " ken0-1n/Genomon-ITDetector\n", - " Bioinformatics\n", - " ['https://github.com/ken0-1n/Genomon-ITDetector']\n", + " 24677618\n", + " Transcript-based annotation and pedigree analy...\n", + " [(Jäger, Marten), (Wang, Kai), (Bauer, Sebasti...\n", + " 2014-04-23\n", + " compbio.charite.de', 'https://github.com/chari...\n", + " Hum. Mutat.\n", + " ['compbio.charite.de', 'https://github.com/cha...\n", " \n", " \n", - " 25192739\n", - " We describe mod_bio, a set of modules for the ...\n", - " [(Lindenbaum, Pierre), (Redon, Richard)]\n", - " 2014-12-20\n", - " \n", - " Bioinformatics\n", - " []\n", + " 24675810\n", + " Virus populations can display high genetic div...\n", + " [(Töpfer, Armin), (Marschall, Tobias), (Bull, ...\n", + " 2014-03-28\n", + " 'https://github.com/armintoepfer/haploclique\n", + " PLoS Comput. Biol.\n", + " [u'https://github.com/armintoepfer/haploclique']\n", " \n", " \n", - " 25189781\n", - " Next-generation sequencing experiments, such a...\n", - " [(Robinson, David G), (Storey, John D)]\n", - " 2014-11-26\n", - " \n", - " Bioinformatics\n", - " []\n", + " 24672471\n", + " Analysis of functional magnetic resonance imag...\n", + " [(Eklund, Anders), (Dufort, Paul), (Villani, M...\n", + " 2014-03-27\n", + " wanderine/BROCCOLI/\n", + " Front Neuroinform\n", + " ['https://github.com/wanderine/BROCCOLI/']\n", " \n", " \n", - " 25189778\n", - " The analysis of large biological datasets ofte...\n", - " [(Cingolani, Pablo), (Sladek, Rob), (Blanchett...\n", - " 2014-12-20\n", - " \n", - " Bioinformatics\n", - " []\n", + " 24667828\n", + " Bioreactors are designed to support highly con...\n", + " [(Burdge, David A), (Libourel, Igor G L)]\n", + " 2014-03-26\n", + " LibourelLab/BiofloSoftware\n", + " PLoS ONE\n", + " ['https://github.com/LibourelLab/BiofloSoftware']\n", " \n", " \n", - " 25183856\n", - " This article describes our participation of th...\n", - " [(Zhu, Dongqing), (Li, Dingcheng), (Carterette...\n", - " 2014-09-03\n", + " 24658388\n", + " Power line interference may severely corrupt n...\n", + " [(Keshtkaran, Mohammad Reza), (Yang, Zhi)]\n", + " 2014-04-03\n", " \n", - " Database (Oxford)\n", + " J Neural Eng\n", " []\n", " \n", " \n", - " 25183485\n", - " Often during the analysis of biological data, ...\n", - " [(Pomyen, Yotsawat), (Segura, Marcelo), (Ebbel...\n", - " 2014-12-20\n", - " \n", - " Bioinformatics\n", - " []\n", + " 24657354\n", + " The cerebellum has classically been linked to ...\n", + " [(Park, Min Tae M), (Pipitone, Jon), (Baer, La...\n", + " 2014-06-03\n", + " 'imaging-genetics.camh.ca/', u'https://github....\n", + " Neuroimage\n", + " [u'imaging-genetics.camh.ca/', u'https://githu...\n", " \n", " \n", - " 25181531\n", - " Managing data from large-scale projects (such ...\n", - " [(Samur, Mehmet Kemal)]\n", - " 2014-09-03\n", - " \n", - " PLoS ONE\n", - " []\n", + " 24653694\n", + " Analysis of brain connectivity has become an i...\n", + " [(Billinger, Martin), (Brunner, Clemens), (Mül...\n", + " 2014-03-21\n", + " github.com/\n", + " Front Neuroinform\n", + " ['github.com/']\n", " \n", " \n", - " 25178461\n", - " Parallel visualization of multiple individual ...\n", - " [(Lajugie, Julien), (Fourel, Nicolas), (Bouhas...\n", - " 2014-12-20\n", - " \n", - " Bioinformatics\n", - " []\n", + " 24647222\n", + " Genome-Wide Association Studies are widely use...\n", + " [(Greshake, Bastian), (Bayer, Philipp E), (Rau...\n", + " 2014-03-20\n", + " www.opensnp.org', 'http://github.com/gedankens...\n", + " PLoS ONE\n", + " ['www.opensnp.org', 'http://github.com/gedanke...\n", " \n", " \n", - " 25177538\n", - " We present a performance-optimized algorithm, ...\n", - " [(Rideout, Jai Ram), (He, Yan), (Navas-Molina,...\n", - " 2014-09-01\n", + " 24627804\n", + " The DAGViewer BioJS component is a reusable Ja...\n", + " [(Kalderimis, Alexis), (Stepan, Radek), (Sulli...\n", + " 2014-03-14\n", " \n", - " PeerJ\n", + " F1000Res\n", " []\n", " \n", " \n", - " 25170024\n", - " Genome-wide association studies (GWAS) have id...\n", - " [(Burren, Oliver S), (Guo, Hui), (Wallace, Chr...\n", - " 2014-11-26\n", + " 24618470\n", + " High-throughput single-cell quantitative real-...\n", + " [(Buettner, Florian), (Moignard, Victoria), (G...\n", + " 2014-06-27\n", " \n", " Bioinformatics\n", " []\n", " \n", " \n", - " 25165093\n", - " I present MR_predictor, a simulation engine de...\n", - " [(Voight, Benjamin F)]\n", - " 2014-11-26\n", + " 24602450\n", + " The secondary structure that maximizes the num...\n", + " [(Venkatachalam, Balaji), (Gusfield, Dan), (Fr...\n", + " 2014-03-24\n", " \n", - " Bioinformatics\n", + " Algorithms Mol Biol\n", " []\n", " \n", " \n", - " 25161247\n", - " Human immunodeficiency virus (HIV) and cancer ...\n", - " [(Gönen, Mehmet), (Margolin, Adam A)]\n", - " 2014-08-27\n", - " \n", - " Bioinformatics\n", - " []\n", + " 24588150\n", + " All atom molecular dynamics (MD) models provid...\n", + " [(Ljubetič, Ajasja), (Urbančič, Iztok), (Štran...\n", + " 2014-03-04\n", + " 'https://github.com/lbf-ijs/DiffusiveDynamics\n", + " J Chem Phys\n", + " [u'https://github.com/lbf-ijs/DiffusiveDynamics']\n", " \n", " \n", - " 25161245\n", - " Species trees provide insight into basic biolo...\n", - " [(Mirarab, S), (Reaz, R), (Bayzid, Md S), (Zim...\n", - " 2014-08-27\n", - " \n", - " Bioinformatics\n", - " []\n", + " 24586045\n", + " In eukaryotes, detailed surveys of recombinati...\n", + " [(Yahara, Koji), (Didelot, Xavier), (Ansari, M...\n", + " 2014-05-26\n", + " bioprojects/orderedPainting\n", + " Mol. Biol. Evol.\n", + " ['https://github.com/bioprojects/orderedPainti...\n", " \n", " \n", - " 25161244\n", - " The construction of statistics for summarizing...\n", - " [(Benner, Philipp), (Bačák, Miroslav), (Bourgu...\n", - " 2014-08-27\n", + " 24574113\n", + " Advances in typing methodologies have recently...\n", + " [(Lärkeryd, Adrian), (Myrtennäs, Kerstin), (Ka...\n", + " 2014-06-16\n", " \n", " Bioinformatics\n", " []\n", " \n", " \n", - " 25161237\n", - " Recently it has been shown that the quality of...\n", - " [(Michel, Mirco), (Hayat, Sikander), (Skwark, ...\n", - " 2014-08-27\n", + " 24567544\n", + " The generation of large volumes of omics data ...\n", + " [(Deu-Pons, Jordi), (Schroeder, Michael P), (L...\n", + " 2014-06-16\n", " \n", " Bioinformatics\n", " []\n", " \n", " \n", - " 25161223\n", - " Accurate haplotyping-determining from which pa...\n", - " [(Kuleshov, Volodymyr)]\n", - " 2014-08-27\n", + " 24564867\n", + " RNA-Seq methodology is a revolutionary transcr...\n", + " [(Bu, Jingde), (Chi, Xuebin), (Jin, Zhong)]\n", + " 2014-02-25\n", " \n", - " Bioinformatics\n", + " BMC Syst Biol\n", " []\n", " \n", " \n", - " 25160522\n", - " Many tumors are composed of genetically diverg...\n", - " [(Qiao, Yi), (Quinlan, Aaron R), (Jazaeri, Ami...\n", - " 2014-12-04\n", - " yiq/SubcloneSeeker\n", - " Genome Biol.\n", - " ['https://github.com/yiq/SubcloneSeeker']\n", + " 24564732\n", + " The ISA-Tab format and software suite have bee...\n", + " [(González-Beltrán, Alejandra), (Neumann, Stef...\n", + " 2014-02-25\n", + " \n", + " BMC Bioinformatics\n", + " []\n", " \n", " \n", - " 25159222\n", - " First pass methods based on BLAST match are co...\n", - " [(Zhu, Qiyun), (Kosoy, Michael), (Dittmar, Kat...\n", - " 2014-09-02\n", + " 24564706\n", + " Among challenges that hamper reaping the benef...\n", + " [(Soueidan, Hayssam), (Maurier, Florence), (Gr...\n", + " 2014-02-25\n", " \n", - " BMC Genomics\n", + " BMC Bioinformatics\n", " []\n", " \n", " \n", - " 25147360\n", - " pViz.js is a visualization library for display...\n", - " [(Mukhyala, Kiran), (Masselot, Alexandre)]\n", - " 2014-11-26\n", + " 24564637\n", + " Selecting genes and pathways indicative of dis...\n", + " [(Zhang, Wen), (Wan, Ying-Wooi), (Allen, Genev...\n", + " 2014-02-25\n", " \n", - " Bioinformatics\n", + " BMC Genomics\n", " []\n", " \n", " \n", - " 25147359\n", - " Current sequence alignment browsers allow visu...\n", - " [(Gymrek, Melissa)]\n", - " 2014-11-26\n", + " 24564427\n", + " Many biological processes are carried out by p...\n", + " [(Wong, Daniel), (Li, Xiao-Li), (Wu, Min), (Zh...\n", + " 2014-02-25\n", " \n", - " Bioinformatics\n", + " BMC Genomics\n", " []\n", " \n", " \n", "\n", - "

100 rows × 6 columns

\n", + "

200 rows × 6 columns

\n", "
" ], "text/plain": [ @@ -1018,36 +1018,36 @@ "25414349 The emergence of new sequencing technologies h... \n", "25410596 Whole-genome sequences are now available for m... \n", "... ... \n", - "25262154 We have created a Shiny-based Web application,... \n", - "25254639 Since its identification in 1983, HIV-1 has be... \n", - "25253358 It has recently become possible to rapidly and... \n", - "25252881 Although there are many different algorithms a... \n", - "25236461 We present a Web service to access Ensembl dat... \n", - "25232314 Neuromorphic hardware offers an electronic sub... \n", - "25231498 Mechanistic 'whole-cell' models are needed to ... \n", - "25212755 cddApp is a Cytoscape extension that supports ... \n", - "25206364 The detection of \"signatures of selection\" is ... \n", - "25202595 None \n", - "25192740 Somatic internal tandem duplications (ITDs) ar... \n", - "25192739 We describe mod_bio, a set of modules for the ... \n", - "25189781 Next-generation sequencing experiments, such a... \n", - "25189778 The analysis of large biological datasets ofte... \n", - "25183856 This article describes our participation of th... \n", - "25183485 Often during the analysis of biological data, ... \n", - "25181531 Managing data from large-scale projects (such ... \n", - "25178461 Parallel visualization of multiple individual ... \n", - "25177538 We present a performance-optimized algorithm, ... \n", - "25170024 Genome-wide association studies (GWAS) have id... \n", - "25165093 I present MR_predictor, a simulation engine de... \n", - "25161247 Human immunodeficiency virus (HIV) and cancer ... \n", - "25161245 Species trees provide insight into basic biolo... \n", - "25161244 The construction of statistics for summarizing... \n", - "25161237 Recently it has been shown that the quality of... \n", - "25161223 Accurate haplotyping-determining from which pa... \n", - "25160522 Many tumors are composed of genetically diverg... \n", - "25159222 First pass methods based on BLAST match are co... \n", - "25147360 pViz.js is a visualization library for display... \n", - "25147359 Current sequence alignment browsers allow visu... \n", + "24728855 Phylogenetic comparative methods are essential... \n", + "24727652 Genomic information is encoded on a wide range... \n", + "24715980 Signaling pathways provide essential informati... \n", + "24707447 Background Understanding the evolutionary rela... \n", + "24703969 Advances in next-generation sequencing (NGS) t... \n", + "24700534 We here present GradientOptimizer, an intuitiv... \n", + "24695491 The primary goal of genome-wide association st... \n", + "24695406 Next-generation sequencing (NGS) has revolutio... \n", + "24688855 We present a powerful Python library to quickl... \n", + "24681267 Symmetry is an important feature of protein te... \n", + "24677618 Transcript-based annotation and pedigree analy... \n", + "24675810 Virus populations can display high genetic div... \n", + "24672471 Analysis of functional magnetic resonance imag... \n", + "24667828 Bioreactors are designed to support highly con... \n", + "24658388 Power line interference may severely corrupt n... \n", + "24657354 The cerebellum has classically been linked to ... \n", + "24653694 Analysis of brain connectivity has become an i... \n", + "24647222 Genome-Wide Association Studies are widely use... \n", + "24627804 The DAGViewer BioJS component is a reusable Ja... \n", + "24618470 High-throughput single-cell quantitative real-... \n", + "24602450 The secondary structure that maximizes the num... \n", + "24588150 All atom molecular dynamics (MD) models provid... \n", + "24586045 In eukaryotes, detailed surveys of recombinati... \n", + "24574113 Advances in typing methodologies have recently... \n", + "24567544 The generation of large volumes of omics data ... \n", + "24564867 RNA-Seq methodology is a revolutionary transcr... \n", + "24564732 The ISA-Tab format and software suite have bee... \n", + "24564706 Among challenges that hamper reaping the benef... \n", + "24564637 Selecting genes and pathways indicative of dis... \n", + "24564427 Many biological processes are carried out by p... \n", "\n", " Authors Date \\\n", "26357045 [(Shiraishi, Fumihide), (Yoshida, Erika), (Voi... 2015-09-11 \n", @@ -1081,36 +1081,36 @@ "25414349 [(Croucher, Nicholas J), (Page, Andrew J), (Co... 2015-02-18 \n", "25410596 [(Treangen, Todd J), (Ondov, Brian D), (Koren,... 2015-01-07 \n", "... ... ... \n", - "25262154 [(McMurdie, Paul J), (Holmes, Susan)] 2015-01-10 \n", - "25254639 [(Hepler, N Lance), (Scheffler, Konrad), (Weav... 2014-09-26 \n", - "25253358 [(Beckmann, Noam D), (Karri, Sashank), (Fang, ... 2014-09-25 \n", - "25252881 [(Gholami, Milad), (Arbabi, Aryan), (Sharifi-Z... 2014-09-25 \n", - "25236461 [(Yates, Andrew), (Beal, Kathryn), (Keenan, St... 2014-12-20 \n", - "25232314 [(Stefanini, Fabio), (Neftci, Emre O), (Sheik,... 2014-09-18 \n", - "25231498 [(Karr, Jonathan R), (Phillips, Nolan C), (Cov... 2014-09-18 \n", - "25212755 [(Morris, John H), (Wu, Allan), (Yamashita, Ro... 2014-12-20 \n", - "25206364 [(Cadzow, Murray), (Boocock, James), (Nguyen, ... 2014-09-10 \n", - "25202595 [(Salinas, Nelson R), (Little, Damon P)] 2014-09-09 \n", - "25192740 [(Chiba, Kenichi), (Shiraishi, Yuichi), (Nagat... 2014-12-20 \n", - "25192739 [(Lindenbaum, Pierre), (Redon, Richard)] 2014-12-20 \n", - "25189781 [(Robinson, David G), (Storey, John D)] 2014-11-26 \n", - "25189778 [(Cingolani, Pablo), (Sladek, Rob), (Blanchett... 2014-12-20 \n", - "25183856 [(Zhu, Dongqing), (Li, Dingcheng), (Carterette... 2014-09-03 \n", - "25183485 [(Pomyen, Yotsawat), (Segura, Marcelo), (Ebbel... 2014-12-20 \n", - "25181531 [(Samur, Mehmet Kemal)] 2014-09-03 \n", - "25178461 [(Lajugie, Julien), (Fourel, Nicolas), (Bouhas... 2014-12-20 \n", - "25177538 [(Rideout, Jai Ram), (He, Yan), (Navas-Molina,... 2014-09-01 \n", - "25170024 [(Burren, Oliver S), (Guo, Hui), (Wallace, Chr... 2014-11-26 \n", - "25165093 [(Voight, Benjamin F)] 2014-11-26 \n", - "25161247 [(Gönen, Mehmet), (Margolin, Adam A)] 2014-08-27 \n", - "25161245 [(Mirarab, S), (Reaz, R), (Bayzid, Md S), (Zim... 2014-08-27 \n", - "25161244 [(Benner, Philipp), (Bačák, Miroslav), (Bourgu... 2014-08-27 \n", - "25161237 [(Michel, Mirco), (Hayat, Sikander), (Skwark, ... 2014-08-27 \n", - "25161223 [(Kuleshov, Volodymyr)] 2014-08-27 \n", - "25160522 [(Qiao, Yi), (Quinlan, Aaron R), (Jazaeri, Ami... 2014-12-04 \n", - "25159222 [(Zhu, Qiyun), (Kosoy, Michael), (Dittmar, Kat... 2014-09-02 \n", - "25147360 [(Mukhyala, Kiran), (Masselot, Alexandre)] 2014-11-26 \n", - "25147359 [(Gymrek, Melissa)] 2014-11-26 \n", + "24728855 [(Pennell, Matthew W), (Eastman, Jonathan M), ... 2014-07-19 \n", + "24727652 [(Knijnenburg, Theo A), (Ramsey, Stephen A), (... 2014-05-30 \n", + "24715980 [(Villaveces, Jose M), (Jimenez, Rafael C), (H... 2014-04-09 \n", + "24707447 [(Grant, Jessica R), (Katz, Laura A)] 2014-04-07 \n", + "24703969 [(Guo, Yan), (Zhao, Shilin), (Sheng, Quanhu), ... 2014-06-14 \n", + "24700534 [(Moruz, Luminita), (Käll, Lukas)] 2014-06-12 \n", + "24695491 [(Botta, Vincent), (Louppe, Gilles), (Geurts, ... 2014-04-03 \n", + "24695406 [(Li, Yi), (Xie, Xiaohui)] 2014-07-19 \n", + "24688855 [(Christensen, Anders S), (Hamelryck, Thomas),... 2014-04-01 \n", + "24681267 [(Myers-Turnbull, Douglas), (Bliven, Spencer E... 2014-05-06 \n", + "24677618 [(Jäger, Marten), (Wang, Kai), (Bauer, Sebasti... 2014-04-23 \n", + "24675810 [(Töpfer, Armin), (Marschall, Tobias), (Bull, ... 2014-03-28 \n", + "24672471 [(Eklund, Anders), (Dufort, Paul), (Villani, M... 2014-03-27 \n", + "24667828 [(Burdge, David A), (Libourel, Igor G L)] 2014-03-26 \n", + "24658388 [(Keshtkaran, Mohammad Reza), (Yang, Zhi)] 2014-04-03 \n", + "24657354 [(Park, Min Tae M), (Pipitone, Jon), (Baer, La... 2014-06-03 \n", + "24653694 [(Billinger, Martin), (Brunner, Clemens), (Mül... 2014-03-21 \n", + "24647222 [(Greshake, Bastian), (Bayer, Philipp E), (Rau... 2014-03-20 \n", + "24627804 [(Kalderimis, Alexis), (Stepan, Radek), (Sulli... 2014-03-14 \n", + "24618470 [(Buettner, Florian), (Moignard, Victoria), (G... 2014-06-27 \n", + "24602450 [(Venkatachalam, Balaji), (Gusfield, Dan), (Fr... 2014-03-24 \n", + "24588150 [(Ljubetič, Ajasja), (Urbančič, Iztok), (Štran... 2014-03-04 \n", + "24586045 [(Yahara, Koji), (Didelot, Xavier), (Ansari, M... 2014-05-26 \n", + "24574113 [(Lärkeryd, Adrian), (Myrtennäs, Kerstin), (Ka... 2014-06-16 \n", + "24567544 [(Deu-Pons, Jordi), (Schroeder, Michael P), (L... 2014-06-16 \n", + "24564867 [(Bu, Jingde), (Chi, Xuebin), (Jin, Zhong)] 2014-02-25 \n", + "24564732 [(González-Beltrán, Alejandra), (Neumann, Stef... 2014-02-25 \n", + "24564706 [(Soueidan, Hayssam), (Maurier, Florence), (Gr... 2014-02-25 \n", + "24564637 [(Zhang, Wen), (Wan, Ying-Wooi), (Allen, Genev... 2014-02-25 \n", + "24564427 [(Wong, Daniel), (Li, Xiao-Li), (Wu, Min), (Zh... 2014-02-25 \n", "\n", " Github \\\n", "26357045 BioprocessdesignLab/COSMOS \n", @@ -1144,36 +1144,36 @@ "25414349 github.com/ \n", "25410596 marbl/harvest \n", "... ... \n", - "25262154 \n", - "25254639 veg/idepi \n", - "25253358 \n", - "25252881 \n", - "25236461 \n", - "25232314 inincs/pyNCS \n", - "25231498 \n", - "25212755 \n", - "25206364 www.github.com/ \n", - "25202595 \n", - "25192740 ken0-1n/Genomon-ITDetector \n", - "25192739 \n", - "25189781 \n", - "25189778 \n", - "25183856 \n", - "25183485 \n", - "25181531 \n", - "25178461 \n", - "25177538 \n", - "25170024 \n", - "25165093 \n", - "25161247 \n", - "25161245 \n", - "25161244 \n", - "25161237 \n", - "25161223 \n", - "25160522 yiq/SubcloneSeeker \n", - "25159222 \n", - "25147360 \n", - "25147359 \n", + "24728855 \n", + "24727652 tknijnen/msr/ \n", + "24715980 \n", + "24707447 \n", + "24703969 slzhao/QC3 \n", + "24700534 statisticalbiotechnology/NonlinearGradientsUI \n", + "24695491 www.montefiore.ulg.ac.be/', 'github.com/ \n", + "24695406 \n", + "24688855 jensengroup/fragbuilder/ \n", + "24681267 source.rcsb.org/', 'https://github.com/rcsb/sy... \n", + "24677618 compbio.charite.de', 'https://github.com/chari... \n", + "24675810 'https://github.com/armintoepfer/haploclique \n", + "24672471 wanderine/BROCCOLI/ \n", + "24667828 LibourelLab/BiofloSoftware \n", + "24658388 \n", + "24657354 'imaging-genetics.camh.ca/', u'https://github.... \n", + "24653694 github.com/ \n", + "24647222 www.opensnp.org', 'http://github.com/gedankens... \n", + "24627804 \n", + "24618470 \n", + "24602450 \n", + "24588150 'https://github.com/lbf-ijs/DiffusiveDynamics \n", + "24586045 bioprojects/orderedPainting \n", + "24574113 \n", + "24567544 \n", + "24564867 \n", + "24564732 \n", + "24564706 \n", + "24564637 \n", + "24564427 \n", "\n", " Journal \\\n", "26357045 IEEE/ACM Trans Comput Biol Bioinform \n", @@ -1207,36 +1207,36 @@ "25414349 Nucleic Acids Res. \n", "25410596 Genome Biol. \n", "... ... \n", - "25262154 Bioinformatics \n", - "25254639 PLoS Comput. Biol. \n", - "25253358 BMC Bioinformatics \n", - "25252881 BMC Bioinformatics \n", - "25236461 Bioinformatics \n", - "25232314 Front Neuroinform \n", - "25231498 Database (Oxford) \n", - "25212755 Bioinformatics \n", - "25206364 Front Genet \n", - "25202595 Appl Plant Sci \n", - "25192740 Bioinformatics \n", - "25192739 Bioinformatics \n", - "25189781 Bioinformatics \n", - "25189778 Bioinformatics \n", - "25183856 Database (Oxford) \n", - "25183485 Bioinformatics \n", - "25181531 PLoS ONE \n", - "25178461 Bioinformatics \n", - "25177538 PeerJ \n", - "25170024 Bioinformatics \n", - "25165093 Bioinformatics \n", - "25161247 Bioinformatics \n", - "25161245 Bioinformatics \n", - "25161244 Bioinformatics \n", - "25161237 Bioinformatics \n", - "25161223 Bioinformatics \n", - "25160522 Genome Biol. \n", - "25159222 BMC Genomics \n", - "25147360 Bioinformatics \n", - "25147359 Bioinformatics \n", + "24728855 Bioinformatics \n", + "24727652 Nat. Methods \n", + "24715980 F1000Res \n", + "24707447 PLoS Curr \n", + "24703969 Genomics \n", + "24700534 Proteomics \n", + "24695491 PLoS ONE \n", + "24695406 Bioinformatics \n", + "24688855 PeerJ \n", + "24681267 J. Mol. Biol. \n", + "24677618 Hum. Mutat. \n", + "24675810 PLoS Comput. Biol. \n", + "24672471 Front Neuroinform \n", + "24667828 PLoS ONE \n", + "24658388 J Neural Eng \n", + "24657354 Neuroimage \n", + "24653694 Front Neuroinform \n", + "24647222 PLoS ONE \n", + "24627804 F1000Res \n", + "24618470 Bioinformatics \n", + "24602450 Algorithms Mol Biol \n", + "24588150 J Chem Phys \n", + "24586045 Mol. Biol. Evol. \n", + "24574113 Bioinformatics \n", + "24567544 Bioinformatics \n", + "24564867 BMC Syst Biol \n", + "24564732 BMC Bioinformatics \n", + "24564706 BMC Bioinformatics \n", + "24564637 BMC Genomics \n", + "24564427 BMC Genomics \n", "\n", " Url \n", "26357045 ['https://github.com/BioprocessdesignLab/COSMOS'] \n", @@ -1270,47 +1270,47 @@ "25414349 ['github.com/'] \n", "25410596 ['http://github.com/marbl/harvest'] \n", "... ... \n", - "25262154 [] \n", - "25254639 ['https://github.com/veg/idepi'] \n", - "25253358 [] \n", - "25252881 [] \n", - "25236461 [] \n", - "25232314 ['https://github.com/inincs/pyNCS'] \n", - "25231498 [] \n", - "25212755 [] \n", - "25206364 ['www.github.com/'] \n", - "25202595 \n", - "25192740 ['https://github.com/ken0-1n/Genomon-ITDetector'] \n", - "25192739 [] \n", - "25189781 [] \n", - "25189778 [] \n", - "25183856 [] \n", - "25183485 [] \n", - "25181531 [] \n", - "25178461 [] \n", - "25177538 [] \n", - "25170024 [] \n", - "25165093 [] \n", - "25161247 [] \n", - "25161245 [] \n", - "25161244 [] \n", - "25161237 [] \n", - "25161223 [] \n", - "25160522 ['https://github.com/yiq/SubcloneSeeker'] \n", - "25159222 [] \n", - "25147360 [] \n", - "25147359 [] \n", + "24728855 [] \n", + "24727652 ['https://github.com/tknijnen/msr/'] \n", + "24715980 [] \n", + "24707447 [] \n", + "24703969 ['https://github.com/slzhao/QC3'] \n", + "24700534 ['https://github.com/statisticalbiotechnology/... \n", + "24695491 ['www.montefiore.ulg.ac.be/', 'github.com/'] \n", + "24695406 [] \n", + "24688855 ['https://github.com/jensengroup/fragbuilder/'] \n", + "24681267 ['source.rcsb.org/', 'https://github.com/rcsb/... \n", + "24677618 ['compbio.charite.de', 'https://github.com/cha... \n", + "24675810 [u'https://github.com/armintoepfer/haploclique'] \n", + "24672471 ['https://github.com/wanderine/BROCCOLI/'] \n", + "24667828 ['https://github.com/LibourelLab/BiofloSoftware'] \n", + "24658388 [] \n", + "24657354 [u'imaging-genetics.camh.ca/', u'https://githu... \n", + "24653694 ['github.com/'] \n", + "24647222 ['www.opensnp.org', 'http://github.com/gedanke... \n", + "24627804 [] \n", + "24618470 [] \n", + "24602450 [] \n", + "24588150 [u'https://github.com/lbf-ijs/DiffusiveDynamics'] \n", + "24586045 ['https://github.com/bioprojects/orderedPainti... \n", + "24574113 [] \n", + "24567544 [] \n", + "24564867 [] \n", + "24564732 [] \n", + "24564706 [] \n", + "24564637 [] \n", + "24564427 [] \n", "\n", - "[100 rows x 6 columns]" + "[200 rows x 6 columns]" ] }, - "execution_count": 157, + "execution_count": 168, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "df.head(100)" + "df.head(200)" ] }, { From 3e967b3101510313060e3ac5a6b75c7c82b2ae35 Mon Sep 17 00:00:00 2001 From: Melanie Date: Thu, 7 Apr 2016 11:45:04 +0100 Subject: [PATCH 16/21] select only urls that actually point to github projects --- src/find_github_repo.ipynb | 571 ++++++++++++++++++++----------------- 1 file changed, 302 insertions(+), 269 deletions(-) diff --git a/src/find_github_repo.ipynb b/src/find_github_repo.ipynb index 58556a2..782226b 100644 --- a/src/find_github_repo.ipynb +++ b/src/find_github_repo.ipynb @@ -24,7 +24,7 @@ }, { "cell_type": "code", - "execution_count": 146, + "execution_count": 274, "metadata": { "collapsed": false }, @@ -35,7 +35,7 @@ "['github_pubs.xml', 'README.md']" ] }, - "execution_count": 146, + "execution_count": 274, "metadata": {}, "output_type": "execute_result" } @@ -55,7 +55,7 @@ }, { "cell_type": "code", - "execution_count": 147, + "execution_count": 275, "metadata": { "collapsed": true }, @@ -74,7 +74,7 @@ }, { "cell_type": "code", - "execution_count": 148, + "execution_count": 276, "metadata": { "collapsed": true }, @@ -106,7 +106,7 @@ }, { "cell_type": "code", - "execution_count": 149, + "execution_count": 277, "metadata": { "collapsed": true }, @@ -150,7 +150,7 @@ }, { "cell_type": "code", - "execution_count": 150, + "execution_count": 278, "metadata": { "collapsed": false, "scrolled": true @@ -245,7 +245,7 @@ "25549775 Ann Biomed Eng " ] }, - "execution_count": 150, + "execution_count": 278, "metadata": {}, "output_type": "execute_result" } @@ -274,7 +274,7 @@ }, { "cell_type": "code", - "execution_count": 151, + "execution_count": 279, "metadata": { "collapsed": false }, @@ -285,7 +285,7 @@ "'Stability and sensitivity analyses of biological systems require the ad hocwriting of computer code, which is highly dependent on the particular model and burdensome for large systems. We propose a very accurate strategy to overcome this challenge. Its core concept is the conversion of the model into the format of biochemical systems theory (BST), which greatly facilitates the computation of sensitivities. First, the steady state of interest is determined by integrating the model equations toward the steady state and then using a Newton-Raphson method to fine-tune the result. The second step of conversion into the BST format requires several instances of numerical differentiation. The accuracy of this task is ensured by the use of a complex-variable Taylor scheme for all differentiation steps. The proposed strategy is implemented in a new software program, COSMOS, which automates the stability and sensitivity analysis of essentially arbitrary ODE models in a quick, yet highly accurate manner. The methods underlying the process are theoretically analyzed and illustrated with four representative examples: a simple metabolic reaction model; a model of aspartate-derived amino acid biosynthesis; a TCA-cycle model; and a modified TCA-cycle model. COSMOS has been deposited to https://github.com/BioprocessdesignLab/COSMOS.'" ] }, - "execution_count": 151, + "execution_count": 279, "metadata": {}, "output_type": "execute_result" } @@ -303,14 +303,25 @@ }, { "cell_type": "code", - "execution_count": 152, + "execution_count": 280, "metadata": { "collapsed": true }, "outputs": [], "source": [ "import re\n", - "github_url_regex = r\"\"\"(?i)\\b((?:https?://github[.](?:com|net|org|edu|gov|mil|aero|asia|biz|cat|coop|info|int|jobs|mobi|museum|name|post|pro|tel|travel|xxx|ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cs|cu|cv|cx|cy|cz|dd|de|dj|dk|dm|do|dz|ec|ee|eg|eh|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|Ja|sk|sl|sm|sn|so|sr|ss|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|yu|za|zm|zw)/)(?:[^\\s()<>{}\\[\\]]+|\\([^\\s()]*?\\([^\\s()]+\\)[^\\s()]*?\\)|\\([^\\s]+?\\))+(?:\\([^\\s()]*?\\([^\\s()]+\\)[^\\s()]*?\\)|\\([^\\s]+?\\)|[^\\s`!()\\[\\]{};:'\".,<>?«»“”‘’])|(?:(?{}\\[\\]]+|\\([^\\s()]*?\\([^\\s()]+\\)[^\\s()]*?\\)|\\([^\\s]+?\\))+(?:\\([^\\s()]*?\\([^\\s()]+\\)[^\\s()]*?\\)|\\([^\\s]+?\\)|[^\\s`!()\\[\\]{};:'\".,<>?«»“”‘’])|(?:(?Stability and sensitivity analyses of biologic...\n", " [(Shiraishi, Fumihide), (Yoshida, Erika), (Voi...\n", " 2015-09-11\n", - " BioprocessdesignLab/COSMOS\n", + " /BioprocessdesignLab/COSMOS\n", " IEEE/ACM Trans Comput Biol Bioinform\n", - " ['https://github.com/BioprocessdesignLab/COSMOS']\n", + " https://github.com/BioprocessdesignLab/COSMOS\n", " \n", " \n", " 25601296\n", @@ -447,34 +470,34 @@ " 2015-01-20\n", " \n", " JMIR Med Inform\n", - " []\n", + " \n", " \n", " \n", " 25558360\n", " Remotely sensed data - available at medium to ...\n", " [(Tuck, Sean L), (Phillips, Helen Rp), (Hintze...\n", " 2015-01-05\n", - " seantuck12/MODISTools\n", + " /seantuck12/MODISTools\n", " Ecol Evol\n", - " ['https://github.com/seantuck12/MODISTools']\n", + " https://github.com/seantuck12/MODISTools\n", " \n", " \n", " 25553811\n", " Whole-genome bisulfite sequencing (WGBS) is an...\n", " [(Chen, Junfang), (Lutsik, Pavlo), (Akulenko, ...\n", " 2015-01-02\n", - " 'https://github.com/Junfang/AKSmooth\n", + " /Junfang/AKSmooth\n", " J Bioinform Comput Biol\n", - " [u'https://github.com/Junfang/AKSmooth']\n", + " https://github.com/Junfang/AKSmooth\n", " \n", " \n", " 25549775\n", " A number of computational approaches have been...\n", " [(Manini, Simone), (Antiga, Luca), (Botti, Lor...\n", " 2015-06-09\n", - " archtk.github.com\n", + " /Junfang/AKSmooth\n", " Ann Biomed Eng\n", - " ['archtk.github.com']\n", + " http://archtk.github.com\n", " \n", " \n", " 25543048\n", @@ -483,7 +506,7 @@ " 2015-04-28\n", " \n", " Bioinformatics\n", - " []\n", + " \n", " \n", " \n", " 25540185\n", @@ -492,7 +515,7 @@ " 2015-04-28\n", " \n", " Bioinformatics\n", - " []\n", + " \n", " \n", " \n", " 25527832\n", @@ -501,7 +524,7 @@ " 2015-04-12\n", " \n", " Bioinformatics\n", - " []\n", + " \n", " \n", " \n", " 25526884\n", @@ -510,7 +533,7 @@ " 2015-04-27\n", " \n", " BMC Bioinformatics\n", - " []\n", + " \n", " \n", " \n", " 25524895\n", @@ -519,7 +542,7 @@ " 2015-04-28\n", " \n", " Bioinformatics\n", - " []\n", + " \n", " \n", " \n", " 25521965\n", @@ -528,25 +551,25 @@ " 2014-12-19\n", " \n", " BMC Med Genomics\n", - " []\n", + " \n", " \n", " \n", " 25520192\n", " RNA performs a diverse array of important func...\n", " [(Gardner, Paul P), (Eldai, Hisham)]\n", " 2015-01-24\n", - " ppgardne/RMfam\n", + " /ppgardne/RMfam\n", " Nucleic Acids Res.\n", - " ['https://github.com/ppgardne/RMfam']\n", + " https://github.com/ppgardne/RMfam\n", " \n", " \n", " 25514851\n", " We describe an open-source kPAL package that f...\n", " [(Anvar, Seyed Yahya), (Khachatryan, Lusine), ...\n", " 2015-02-06\n", - " LUMC/kPAL\n", + " /LUMC/kPAL\n", " Genome Biol.\n", - " ['https://github.com/LUMC/kPAL']\n", + " https://github.com/LUMC/kPAL\n", " \n", " \n", " 25505094\n", @@ -555,7 +578,7 @@ " 2015-04-12\n", " \n", " Bioinformatics\n", - " []\n", + " \n", " \n", " \n", " 25505087\n", @@ -564,7 +587,7 @@ " 2015-04-12\n", " \n", " Bioinformatics\n", - " []\n", + " \n", " \n", " \n", " 25505086\n", @@ -573,7 +596,7 @@ " 2015-04-12\n", " \n", " Bioinformatics\n", - " []\n", + " \n", " \n", " \n", " 25504847\n", @@ -582,7 +605,7 @@ " 2015-04-12\n", " \n", " Bioinformatics\n", - " []\n", + " \n", " \n", " \n", " 25481009\n", @@ -591,7 +614,7 @@ " 2015-04-12\n", " \n", " Bioinformatics\n", - " []\n", + " \n", " \n", " \n", " 25481007\n", @@ -600,7 +623,7 @@ " 2015-04-12\n", " \n", " Bioinformatics\n", - " []\n", + " \n", " \n", " \n", " 25480375\n", @@ -609,43 +632,43 @@ " 2015-04-12\n", " \n", " Bioinformatics\n", - " []\n", + " \n", " \n", " \n", " 25474353\n", " Phylogenetic analyses which include fossils or...\n", " [(Gavryushkina, Alexandra), (Welch, David), (S...\n", " 2014-12-05\n", - " CompEvol/sampled-ancestors\n", + " /CompEvol/sampled-ancestors\n", " PLoS Comput. Biol.\n", - " ['https://github.com/CompEvol/sampled-ancestors']\n", + " https://github.com/CompEvol/sampled-ancestors\n", " \n", " \n", " 25461763\n", " Since the read lengths of high throughput sequ...\n", " [(Zhu, Xiao), (Leung, Henry C M), (Chin, Franc...\n", " 2014-12-03\n", - " hitbio/PERGA\n", + " /hitbio/PERGA\n", " PLoS ONE\n", - " ['https://github.com/hitbio/PERGA']\n", + " https://github.com/hitbio/PERGA\n", " \n", " \n", " 25452688\n", " Mobile elements constitute greater than 45% of...\n", " [(Lee, Wan-Ping), (Wu, Jiantao), (Marth, Gabor...\n", " 2014-12-02\n", - " jiantao/Tangram\n", + " /jiantao/Tangram\n", " Cancer Inform\n", - " ['https://github.com/jiantao/Tangram']\n", + " https://github.com/jiantao/Tangram\n", " \n", " \n", " 25435543\n", " Isobaric labeling techniques coupled with high...\n", " [(Sheng, Quanhu), (Li, Rongxia), (Dai, Jie), (...\n", " 2015-01-31\n", - " shengqh/RCPA.Tools/releases\n", + " /shengqh/RCPA.Tools/releases\n", " Mol. Cell Proteomics\n", - " ['https://github.com/shengqh/RCPA.Tools/releas...\n", + " https://github.com/shengqh/RCPA.Tools/releases\n", " \n", " \n", " 25431162\n", @@ -654,25 +677,25 @@ " 2015-04-27\n", " \n", " BMC Bioinformatics\n", - " []\n", + " \n", " \n", " \n", " 25428347\n", " Genetic screens of an unprecedented scale have...\n", " [(Diaz, Aaron A), (Qin, Han), (Ramalho-Santos,...\n", " 2015-02-18\n", - " sourceforge.net/', 'https://github.com/diazlab...\n", + " /diazlab/HiTSelect\n", " Nucleic Acids Res.\n", - " ['sourceforge.net/', 'https://github.com/diazl...\n", + " https://github.com/diazlab/HiTSelect\n", " \n", " \n", " 25422674\n", " Rapid molecular typing of bacterial pathogens ...\n", " [(Inouye, Michael), (Dashnow, Harriet), (Raven...\n", " 2014-11-25\n", - " katholt.github.io/\n", + " /diazlab/HiTSelect\n", " Genome Med\n", - " ['katholt.github.io/']\n", + " http://katholt.github.io/srst2/\n", " \n", " \n", " 25414364\n", @@ -681,25 +704,25 @@ " 2015-04-03\n", " \n", " Bioinformatics\n", - " []\n", + " \n", " \n", " \n", " 25414349\n", " The emergence of new sequencing technologies h...\n", " [(Croucher, Nicholas J), (Page, Andrew J), (Co...\n", " 2015-02-18\n", - " github.com/\n", + " /diazlab/HiTSelect\n", " Nucleic Acids Res.\n", - " ['github.com/']\n", + " github.com/sanger-pathogens/Gubbins\n", " \n", " \n", " 25410596\n", " Whole-genome sequences are now available for m...\n", " [(Treangen, Todd J), (Ondov, Brian D), (Koren,...\n", " 2015-01-07\n", - " marbl/harvest\n", + " /diazlab/HiTSelect\n", " Genome Biol.\n", - " ['http://github.com/marbl/harvest']\n", + " http://github.com/marbl/harvest\n", " \n", " \n", " ...\n", @@ -717,16 +740,16 @@ " 2014-07-19\n", " \n", " Bioinformatics\n", - " []\n", + " \n", " \n", " \n", " 24727652\n", " Genomic information is encoded on a wide range...\n", " [(Knijnenburg, Theo A), (Ramsey, Stephen A), (...\n", " 2014-05-30\n", - " tknijnen/msr/\n", + " /tknijnen/msr/\n", " Nat. Methods\n", - " ['https://github.com/tknijnen/msr/']\n", + " https://github.com/tknijnen/msr/\n", " \n", " \n", " 24715980\n", @@ -735,7 +758,7 @@ " 2014-04-09\n", " \n", " F1000Res\n", - " []\n", + " \n", " \n", " \n", " 24707447\n", @@ -744,34 +767,34 @@ " 2014-04-07\n", " \n", " PLoS Curr\n", - " []\n", + " \n", " \n", " \n", " 24703969\n", " Advances in next-generation sequencing (NGS) t...\n", " [(Guo, Yan), (Zhao, Shilin), (Sheng, Quanhu), ...\n", " 2014-06-14\n", - " slzhao/QC3\n", + " /slzhao/QC3\n", " Genomics\n", - " ['https://github.com/slzhao/QC3']\n", + " https://github.com/slzhao/QC3\n", " \n", " \n", " 24700534\n", " We here present GradientOptimizer, an intuitiv...\n", " [(Moruz, Luminita), (Käll, Lukas)]\n", " 2014-06-12\n", - " statisticalbiotechnology/NonlinearGradientsUI\n", + " /statisticalbiotechnology/NonlinearGradientsUI\n", " Proteomics\n", - " ['https://github.com/statisticalbiotechnology/...\n", + " https://github.com/statisticalbiotechnology/No...\n", " \n", " \n", " 24695491\n", " The primary goal of genome-wide association st...\n", " [(Botta, Vincent), (Louppe, Gilles), (Geurts, ...\n", " 2014-04-03\n", - " www.montefiore.ulg.ac.be/', 'github.com/\n", + " /statisticalbiotechnology/NonlinearGradientsUI\n", " PLoS ONE\n", - " ['www.montefiore.ulg.ac.be/', 'github.com/']\n", + " github.com/0asa/TTree-source\n", " \n", " \n", " 24695406\n", @@ -780,61 +803,61 @@ " 2014-07-19\n", " \n", " Bioinformatics\n", - " []\n", + " \n", " \n", " \n", " 24688855\n", " We present a powerful Python library to quickl...\n", " [(Christensen, Anders S), (Hamelryck, Thomas),...\n", " 2014-04-01\n", - " jensengroup/fragbuilder/\n", + " /jensengroup/fragbuilder/\n", " PeerJ\n", - " ['https://github.com/jensengroup/fragbuilder/']\n", + " https://github.com/jensengroup/fragbuilder/\n", " \n", " \n", " 24681267\n", " Symmetry is an important feature of protein te...\n", " [(Myers-Turnbull, Douglas), (Bliven, Spencer E...\n", " 2014-05-06\n", - " source.rcsb.org/', 'https://github.com/rcsb/sy...\n", + " /rcsb/symmetry\n", " J. Mol. Biol.\n", - " ['source.rcsb.org/', 'https://github.com/rcsb/...\n", + " https://github.com/rcsb/symmetry\n", " \n", " \n", " 24677618\n", " Transcript-based annotation and pedigree analy...\n", " [(Jäger, Marten), (Wang, Kai), (Bauer, Sebasti...\n", " 2014-04-23\n", - " compbio.charite.de', 'https://github.com/chari...\n", + " /charite/jannovar\n", " Hum. Mutat.\n", - " ['compbio.charite.de', 'https://github.com/cha...\n", + " https://github.com/charite/jannovar\n", " \n", " \n", " 24675810\n", " Virus populations can display high genetic div...\n", " [(Töpfer, Armin), (Marschall, Tobias), (Bull, ...\n", " 2014-03-28\n", - " 'https://github.com/armintoepfer/haploclique\n", + " /armintoepfer/haploclique\n", " PLoS Comput. Biol.\n", - " [u'https://github.com/armintoepfer/haploclique']\n", + " https://github.com/armintoepfer/haploclique\n", " \n", " \n", " 24672471\n", " Analysis of functional magnetic resonance imag...\n", " [(Eklund, Anders), (Dufort, Paul), (Villani, M...\n", " 2014-03-27\n", - " wanderine/BROCCOLI/\n", + " /wanderine/BROCCOLI/\n", " Front Neuroinform\n", - " ['https://github.com/wanderine/BROCCOLI/']\n", + " https://github.com/wanderine/BROCCOLI/\n", " \n", " \n", " 24667828\n", " Bioreactors are designed to support highly con...\n", " [(Burdge, David A), (Libourel, Igor G L)]\n", " 2014-03-26\n", - " LibourelLab/BiofloSoftware\n", + " /LibourelLab/BiofloSoftware\n", " PLoS ONE\n", - " ['https://github.com/LibourelLab/BiofloSoftware']\n", + " https://github.com/LibourelLab/BiofloSoftware\n", " \n", " \n", " 24658388\n", @@ -843,34 +866,34 @@ " 2014-04-03\n", " \n", " J Neural Eng\n", - " []\n", + " \n", " \n", " \n", " 24657354\n", " The cerebellum has classically been linked to ...\n", " [(Park, Min Tae M), (Pipitone, Jon), (Baer, La...\n", " 2014-06-03\n", - " 'imaging-genetics.camh.ca/', u'https://github....\n", + " /pipitone/MAGeTbrain\n", " Neuroimage\n", - " [u'imaging-genetics.camh.ca/', u'https://githu...\n", + " https://github.com/pipitone/MAGeTbrain\n", " \n", " \n", " 24653694\n", " Analysis of brain connectivity has become an i...\n", " [(Billinger, Martin), (Brunner, Clemens), (Mül...\n", " 2014-03-21\n", - " github.com/\n", + " /pipitone/MAGeTbrain\n", " Front Neuroinform\n", - " ['github.com/']\n", + " github.com/SCoT-dev/SCoT\n", " \n", " \n", " 24647222\n", " Genome-Wide Association Studies are widely use...\n", " [(Greshake, Bastian), (Bayer, Philipp E), (Rau...\n", " 2014-03-20\n", - " www.opensnp.org', 'http://github.com/gedankens...\n", + " /pipitone/MAGeTbrain\n", " PLoS ONE\n", - " ['www.opensnp.org', 'http://github.com/gedanke...\n", + " http://github.com/gedankenstuecke/snpr\n", " \n", " \n", " 24627804\n", @@ -879,7 +902,7 @@ " 2014-03-14\n", " \n", " F1000Res\n", - " []\n", + " \n", " \n", " \n", " 24618470\n", @@ -888,7 +911,7 @@ " 2014-06-27\n", " \n", " Bioinformatics\n", - " []\n", + " \n", " \n", " \n", " 24602450\n", @@ -897,25 +920,25 @@ " 2014-03-24\n", " \n", " Algorithms Mol Biol\n", - " []\n", + " \n", " \n", " \n", " 24588150\n", " All atom molecular dynamics (MD) models provid...\n", " [(Ljubetič, Ajasja), (Urbančič, Iztok), (Štran...\n", " 2014-03-04\n", - " 'https://github.com/lbf-ijs/DiffusiveDynamics\n", + " /lbf-ijs/DiffusiveDynamics\n", " J Chem Phys\n", - " [u'https://github.com/lbf-ijs/DiffusiveDynamics']\n", + " https://github.com/lbf-ijs/DiffusiveDynamics\n", " \n", " \n", " 24586045\n", " In eukaryotes, detailed surveys of recombinati...\n", " [(Yahara, Koji), (Didelot, Xavier), (Ansari, M...\n", " 2014-05-26\n", - " bioprojects/orderedPainting\n", + " /bioprojects/orderedPainting\n", " Mol. Biol. Evol.\n", - " ['https://github.com/bioprojects/orderedPainti...\n", + " https://github.com/bioprojects/orderedPainting\n", " \n", " \n", " 24574113\n", @@ -924,7 +947,7 @@ " 2014-06-16\n", " \n", " Bioinformatics\n", - " []\n", + " \n", " \n", " \n", " 24567544\n", @@ -933,7 +956,7 @@ " 2014-06-16\n", " \n", " Bioinformatics\n", - " []\n", + " \n", " \n", " \n", " 24564867\n", @@ -942,7 +965,7 @@ " 2014-02-25\n", " \n", " BMC Syst Biol\n", - " []\n", + " \n", " \n", " \n", " 24564732\n", @@ -951,7 +974,7 @@ " 2014-02-25\n", " \n", " BMC Bioinformatics\n", - " []\n", + " \n", " \n", " \n", " 24564706\n", @@ -960,7 +983,7 @@ " 2014-02-25\n", " \n", " BMC Bioinformatics\n", - " []\n", + " \n", " \n", " \n", " 24564637\n", @@ -969,7 +992,7 @@ " 2014-02-25\n", " \n", " BMC Genomics\n", - " []\n", + " \n", " \n", " \n", " 24564427\n", @@ -978,7 +1001,7 @@ " 2014-02-25\n", " \n", " BMC Genomics\n", - " []\n", + " \n", " \n", " \n", "\n", @@ -1112,68 +1135,68 @@ "24564637 [(Zhang, Wen), (Wan, Ying-Wooi), (Allen, Genev... 2014-02-25 \n", "24564427 [(Wong, Daniel), (Li, Xiao-Li), (Wu, Min), (Zh... 2014-02-25 \n", "\n", - " Github \\\n", - "26357045 BioprocessdesignLab/COSMOS \n", - "25601296 \n", - "25558360 seantuck12/MODISTools \n", - "25553811 'https://github.com/Junfang/AKSmooth \n", - "25549775 archtk.github.com \n", - "25543048 \n", - "25540185 \n", - "25527832 \n", - "25526884 \n", - "25524895 \n", - "25521965 \n", - "25520192 ppgardne/RMfam \n", - "25514851 LUMC/kPAL \n", - "25505094 \n", - "25505087 \n", - "25505086 \n", - "25504847 \n", - "25481009 \n", - "25481007 \n", - "25480375 \n", - "25474353 CompEvol/sampled-ancestors \n", - "25461763 hitbio/PERGA \n", - "25452688 jiantao/Tangram \n", - "25435543 shengqh/RCPA.Tools/releases \n", - "25431162 \n", - "25428347 sourceforge.net/', 'https://github.com/diazlab... \n", - "25422674 katholt.github.io/ \n", - "25414364 \n", - "25414349 github.com/ \n", - "25410596 marbl/harvest \n", - "... ... \n", - "24728855 \n", - "24727652 tknijnen/msr/ \n", - "24715980 \n", - "24707447 \n", - "24703969 slzhao/QC3 \n", - "24700534 statisticalbiotechnology/NonlinearGradientsUI \n", - "24695491 www.montefiore.ulg.ac.be/', 'github.com/ \n", - "24695406 \n", - "24688855 jensengroup/fragbuilder/ \n", - "24681267 source.rcsb.org/', 'https://github.com/rcsb/sy... \n", - "24677618 compbio.charite.de', 'https://github.com/chari... \n", - "24675810 'https://github.com/armintoepfer/haploclique \n", - "24672471 wanderine/BROCCOLI/ \n", - "24667828 LibourelLab/BiofloSoftware \n", - "24658388 \n", - "24657354 'imaging-genetics.camh.ca/', u'https://github.... \n", - "24653694 github.com/ \n", - "24647222 www.opensnp.org', 'http://github.com/gedankens... \n", - "24627804 \n", - "24618470 \n", - "24602450 \n", - "24588150 'https://github.com/lbf-ijs/DiffusiveDynamics \n", - "24586045 bioprojects/orderedPainting \n", - "24574113 \n", - "24567544 \n", - "24564867 \n", - "24564732 \n", - "24564706 \n", - "24564637 \n", - "24564427 \n", + " Github \\\n", + "26357045 /BioprocessdesignLab/COSMOS \n", + "25601296 \n", + "25558360 /seantuck12/MODISTools \n", + "25553811 /Junfang/AKSmooth \n", + "25549775 /Junfang/AKSmooth \n", + "25543048 \n", + "25540185 \n", + "25527832 \n", + "25526884 \n", + "25524895 \n", + "25521965 \n", + "25520192 /ppgardne/RMfam \n", + "25514851 /LUMC/kPAL \n", + "25505094 \n", + "25505087 \n", + "25505086 \n", + "25504847 \n", + "25481009 \n", + "25481007 \n", + "25480375 \n", + "25474353 /CompEvol/sampled-ancestors \n", + "25461763 /hitbio/PERGA \n", + "25452688 /jiantao/Tangram \n", + "25435543 /shengqh/RCPA.Tools/releases \n", + "25431162 \n", + "25428347 /diazlab/HiTSelect \n", + "25422674 /diazlab/HiTSelect \n", + "25414364 \n", + "25414349 /diazlab/HiTSelect \n", + "25410596 /diazlab/HiTSelect \n", + "... ... \n", + "24728855 \n", + "24727652 /tknijnen/msr/ \n", + "24715980 \n", + "24707447 \n", + "24703969 /slzhao/QC3 \n", + "24700534 /statisticalbiotechnology/NonlinearGradientsUI \n", + "24695491 /statisticalbiotechnology/NonlinearGradientsUI \n", + "24695406 \n", + "24688855 /jensengroup/fragbuilder/ \n", + "24681267 /rcsb/symmetry \n", + "24677618 /charite/jannovar \n", + "24675810 /armintoepfer/haploclique \n", + "24672471 /wanderine/BROCCOLI/ \n", + "24667828 /LibourelLab/BiofloSoftware \n", + "24658388 \n", + "24657354 /pipitone/MAGeTbrain \n", + "24653694 /pipitone/MAGeTbrain \n", + "24647222 /pipitone/MAGeTbrain \n", + "24627804 \n", + "24618470 \n", + "24602450 \n", + "24588150 /lbf-ijs/DiffusiveDynamics \n", + "24586045 /bioprojects/orderedPainting \n", + "24574113 \n", + "24567544 \n", + "24564867 \n", + "24564732 \n", + "24564706 \n", + "24564637 \n", + "24564427 \n", "\n", " Journal \\\n", "26357045 IEEE/ACM Trans Comput Biol Bioinform \n", @@ -1239,72 +1262,72 @@ "24564427 BMC Genomics \n", "\n", " Url \n", - "26357045 ['https://github.com/BioprocessdesignLab/COSMOS'] \n", - "25601296 [] \n", - "25558360 ['https://github.com/seantuck12/MODISTools'] \n", - "25553811 [u'https://github.com/Junfang/AKSmooth'] \n", - "25549775 ['archtk.github.com'] \n", - "25543048 [] \n", - "25540185 [] \n", - "25527832 [] \n", - "25526884 [] \n", - "25524895 [] \n", - "25521965 [] \n", - "25520192 ['https://github.com/ppgardne/RMfam'] \n", - "25514851 ['https://github.com/LUMC/kPAL'] \n", - "25505094 [] \n", - "25505087 [] \n", - "25505086 [] \n", - "25504847 [] \n", - "25481009 [] \n", - "25481007 [] \n", - "25480375 [] \n", - "25474353 ['https://github.com/CompEvol/sampled-ancestors'] \n", - "25461763 ['https://github.com/hitbio/PERGA'] \n", - "25452688 ['https://github.com/jiantao/Tangram'] \n", - "25435543 ['https://github.com/shengqh/RCPA.Tools/releas... \n", - "25431162 [] \n", - "25428347 ['sourceforge.net/', 'https://github.com/diazl... \n", - "25422674 ['katholt.github.io/'] \n", - "25414364 [] \n", - "25414349 ['github.com/'] \n", - "25410596 ['http://github.com/marbl/harvest'] \n", + "26357045 https://github.com/BioprocessdesignLab/COSMOS \n", + "25601296 \n", + "25558360 https://github.com/seantuck12/MODISTools \n", + "25553811 https://github.com/Junfang/AKSmooth \n", + "25549775 http://archtk.github.com \n", + "25543048 \n", + "25540185 \n", + "25527832 \n", + "25526884 \n", + "25524895 \n", + "25521965 \n", + "25520192 https://github.com/ppgardne/RMfam \n", + "25514851 https://github.com/LUMC/kPAL \n", + "25505094 \n", + "25505087 \n", + "25505086 \n", + "25504847 \n", + "25481009 \n", + "25481007 \n", + "25480375 \n", + "25474353 https://github.com/CompEvol/sampled-ancestors \n", + "25461763 https://github.com/hitbio/PERGA \n", + "25452688 https://github.com/jiantao/Tangram \n", + "25435543 https://github.com/shengqh/RCPA.Tools/releases \n", + "25431162 \n", + "25428347 https://github.com/diazlab/HiTSelect \n", + "25422674 http://katholt.github.io/srst2/ \n", + "25414364 \n", + "25414349 github.com/sanger-pathogens/Gubbins \n", + "25410596 http://github.com/marbl/harvest \n", "... ... \n", - "24728855 [] \n", - "24727652 ['https://github.com/tknijnen/msr/'] \n", - "24715980 [] \n", - "24707447 [] \n", - "24703969 ['https://github.com/slzhao/QC3'] \n", - "24700534 ['https://github.com/statisticalbiotechnology/... \n", - "24695491 ['www.montefiore.ulg.ac.be/', 'github.com/'] \n", - "24695406 [] \n", - "24688855 ['https://github.com/jensengroup/fragbuilder/'] \n", - "24681267 ['source.rcsb.org/', 'https://github.com/rcsb/... \n", - "24677618 ['compbio.charite.de', 'https://github.com/cha... \n", - "24675810 [u'https://github.com/armintoepfer/haploclique'] \n", - "24672471 ['https://github.com/wanderine/BROCCOLI/'] \n", - "24667828 ['https://github.com/LibourelLab/BiofloSoftware'] \n", - "24658388 [] \n", - "24657354 [u'imaging-genetics.camh.ca/', u'https://githu... \n", - "24653694 ['github.com/'] \n", - "24647222 ['www.opensnp.org', 'http://github.com/gedanke... \n", - "24627804 [] \n", - "24618470 [] \n", - "24602450 [] \n", - "24588150 [u'https://github.com/lbf-ijs/DiffusiveDynamics'] \n", - "24586045 ['https://github.com/bioprojects/orderedPainti... \n", - "24574113 [] \n", - "24567544 [] \n", - "24564867 [] \n", - "24564732 [] \n", - "24564706 [] \n", - "24564637 [] \n", - "24564427 [] \n", + "24728855 \n", + "24727652 https://github.com/tknijnen/msr/ \n", + "24715980 \n", + "24707447 \n", + "24703969 https://github.com/slzhao/QC3 \n", + "24700534 https://github.com/statisticalbiotechnology/No... \n", + "24695491 github.com/0asa/TTree-source \n", + "24695406 \n", + "24688855 https://github.com/jensengroup/fragbuilder/ \n", + "24681267 https://github.com/rcsb/symmetry \n", + "24677618 https://github.com/charite/jannovar \n", + "24675810 https://github.com/armintoepfer/haploclique \n", + "24672471 https://github.com/wanderine/BROCCOLI/ \n", + "24667828 https://github.com/LibourelLab/BiofloSoftware \n", + "24658388 \n", + "24657354 https://github.com/pipitone/MAGeTbrain \n", + "24653694 github.com/SCoT-dev/SCoT \n", + "24647222 http://github.com/gedankenstuecke/snpr \n", + "24627804 \n", + "24618470 \n", + "24602450 \n", + "24588150 https://github.com/lbf-ijs/DiffusiveDynamics \n", + "24586045 https://github.com/bioprojects/orderedPainting \n", + "24574113 \n", + "24567544 \n", + "24564867 \n", + "24564732 \n", + "24564706 \n", + "24564637 \n", + "24564427 \n", "\n", "[200 rows x 6 columns]" ] }, - "execution_count": 168, + "execution_count": 301, "metadata": {}, "output_type": "execute_result" } @@ -1315,7 +1338,27 @@ }, { "cell_type": "code", - "execution_count": 158, + "execution_count": 287, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "github_regexp = r\"\"\"(?i)(https?://[.]*github[.]*)\"\"\"" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 288, "metadata": { "collapsed": false }, @@ -1324,7 +1367,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "['https://github.com/BioprocessdesignLab/COSMOS']\n" + "https://github.com/BioprocessdesignLab/COSMOS\n" ] } ], @@ -1335,7 +1378,7 @@ }, { "cell_type": "code", - "execution_count": 159, + "execution_count": 289, "metadata": { "collapsed": false }, @@ -1344,7 +1387,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "['archtk.github.com']\n" + "http://archtk.github.com\n" ] } ], @@ -1355,7 +1398,7 @@ }, { "cell_type": "code", - "execution_count": 160, + "execution_count": 290, "metadata": { "collapsed": false }, @@ -1363,10 +1406,10 @@ { "data": { "text/plain": [ - "ParseResult(scheme='', netloc='', path=\"['https://github.com/BioprocessdesignLab/COSMOS']\", params='', query='', fragment='')" + "ParseResult(scheme='https', netloc='github.com', path='/BioprocessdesignLab/COSMOS', params='', query='', fragment='')" ] }, - "execution_count": 160, + "execution_count": 290, "metadata": {}, "output_type": "execute_result" } @@ -1377,7 +1420,7 @@ }, { "cell_type": "code", - "execution_count": 161, + "execution_count": 291, "metadata": { "collapsed": false }, @@ -1385,10 +1428,10 @@ { "data": { "text/plain": [ - "ParseResult(scheme='', netloc='', path=\"['archtk.github.com']\", params='', query='', fragment='')" + "ParseResult(scheme='http', netloc='archtk.github.com', path='', params='', query='', fragment='')" ] }, - "execution_count": 161, + "execution_count": 291, "metadata": {}, "output_type": "execute_result" } @@ -1399,7 +1442,7 @@ }, { "cell_type": "code", - "execution_count": 162, + "execution_count": 292, "metadata": { "collapsed": false }, @@ -1410,7 +1453,7 @@ }, { "cell_type": "code", - "execution_count": 163, + "execution_count": 293, "metadata": { "collapsed": false }, @@ -1429,7 +1472,7 @@ }, { "cell_type": "code", - "execution_count": 164, + "execution_count": 294, "metadata": { "collapsed": false }, @@ -1437,10 +1480,10 @@ { "data": { "text/plain": [ - "2" + "0" ] }, - "execution_count": 164, + "execution_count": 294, "metadata": {}, "output_type": "execute_result" } @@ -1461,7 +1504,7 @@ }, { "cell_type": "code", - "execution_count": 165, + "execution_count": 295, "metadata": { "collapsed": false }, @@ -1474,7 +1517,7 @@ }, { "cell_type": "code", - "execution_count": 166, + "execution_count": 296, "metadata": { "collapsed": false }, @@ -1494,31 +1537,21 @@ }, { "cell_type": "code", - "execution_count": 167, + "execution_count": 297, "metadata": { "collapsed": false }, "outputs": [ { - "ename": "UnknownObjectException", - "evalue": "404 {u'documentation_url': u'https://developer.github.com/v3', u'message': u'Not Found'}", - "output_type": "error", - "traceback": [ - "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[1;31mUnknownObjectException\u001b[0m Traceback (most recent call last)", - "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m()\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[0mcosmos\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mg\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_repo\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"/BioprocessdesignLab/COSMOS\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 2\u001b[1;33m \u001b[1;32mprint\u001b[0m \u001b[0mcosmos\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdescription\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m", - "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/Repository.pyc\u001b[0m in \u001b[0;36mdescription\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 185\u001b[0m \u001b[1;33m:\u001b[0m\u001b[0mtype\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mstring\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 186\u001b[0m \"\"\"\n\u001b[1;32m--> 187\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_completeIfNotSet\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_description\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 188\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_description\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvalue\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 189\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/GithubObject.pyc\u001b[0m in \u001b[0;36m_completeIfNotSet\u001b[1;34m(self, value)\u001b[0m\n\u001b[0;32m 226\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_completeIfNotSet\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 227\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mvalue\u001b[0m \u001b[1;32mis\u001b[0m \u001b[0mNotSet\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 228\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_completeIfNeeded\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 229\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 230\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_completeIfNeeded\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/GithubObject.pyc\u001b[0m in \u001b[0;36m_completeIfNeeded\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 230\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_completeIfNeeded\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 231\u001b[0m \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__completed\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 232\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__complete\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 233\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 234\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m__complete\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/GithubObject.pyc\u001b[0m in \u001b[0;36m__complete\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 235\u001b[0m headers, data = self._requester.requestJsonAndCheck(\n\u001b[0;32m 236\u001b[0m \u001b[1;34m\"GET\"\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 237\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_url\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvalue\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 238\u001b[0m )\n\u001b[0;32m 239\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_storeAndUseAttributes\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mheaders\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/Requester.pyc\u001b[0m in \u001b[0;36mrequestJsonAndCheck\u001b[1;34m(self, verb, url, parameters, headers, input, cnx)\u001b[0m\n\u001b[0;32m 169\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 170\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mrequestJsonAndCheck\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mverb\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mheaders\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minput\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcnx\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 171\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__check\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrequestJson\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mverb\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mheaders\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minput\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcnx\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 172\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 173\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mrequestMultipartAndCheck\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mverb\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mheaders\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minput\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/Requester.pyc\u001b[0m in \u001b[0;36m__check\u001b[1;34m(self, status, responseHeaders, output)\u001b[0m\n\u001b[0;32m 177\u001b[0m \u001b[0moutput\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__structuredFromJson\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0moutput\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 178\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mstatus\u001b[0m \u001b[1;33m>=\u001b[0m \u001b[1;36m400\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 179\u001b[1;33m \u001b[1;32mraise\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__createException\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mstatus\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mresponseHeaders\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0moutput\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 180\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mresponseHeaders\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0moutput\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 181\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;31mUnknownObjectException\u001b[0m: 404 {u'documentation_url': u'https://developer.github.com/v3', u'message': u'Not Found'}" + "name": "stdout", + "output_type": "stream", + "text": [ + "Computation of Sensitivities in Model ODE Systems\n" ] } ], "source": [ - "cosmos = g.get_repo(\"/BioprocessdesignLab/COSMOS\")\n", + "cosmos = g.get_repo(\"BioprocessdesignLab/COSMOS\")\n", "print cosmos.description" ] } From 25310bfcb5eb4a8b826d06ad5b01843d6c657032 Mon Sep 17 00:00:00 2001 From: Melanie I Stefan Date: Wed, 13 Apr 2016 11:51:34 +0100 Subject: [PATCH 17/21] can parse most github urls now --- src/find_github_repo.ipynb | 1092 +++--------------------------------- 1 file changed, 71 insertions(+), 1021 deletions(-) diff --git a/src/find_github_repo.ipynb b/src/find_github_repo.ipynb index 782226b..69a25ce 100644 --- a/src/find_github_repo.ipynb +++ b/src/find_github_repo.ipynb @@ -24,7 +24,7 @@ }, { "cell_type": "code", - "execution_count": 274, + "execution_count": 7, "metadata": { "collapsed": false }, @@ -35,7 +35,7 @@ "['github_pubs.xml', 'README.md']" ] }, - "execution_count": 274, + "execution_count": 7, "metadata": {}, "output_type": "execute_result" } @@ -55,7 +55,7 @@ }, { "cell_type": "code", - "execution_count": 275, + "execution_count": 8, "metadata": { "collapsed": true }, @@ -74,7 +74,7 @@ }, { "cell_type": "code", - "execution_count": 276, + "execution_count": 9, "metadata": { "collapsed": true }, @@ -106,7 +106,7 @@ }, { "cell_type": "code", - "execution_count": 277, + "execution_count": 10, "metadata": { "collapsed": true }, @@ -150,7 +150,7 @@ }, { "cell_type": "code", - "execution_count": 278, + "execution_count": 11, "metadata": { "collapsed": false, "scrolled": true @@ -245,7 +245,7 @@ "25549775 Ann Biomed Eng " ] }, - "execution_count": 278, + "execution_count": 11, "metadata": {}, "output_type": "execute_result" } @@ -274,7 +274,7 @@ }, { "cell_type": "code", - "execution_count": 279, + "execution_count": 12, "metadata": { "collapsed": false }, @@ -285,7 +285,7 @@ "'Stability and sensitivity analyses of biological systems require the ad hocwriting of computer code, which is highly dependent on the particular model and burdensome for large systems. We propose a very accurate strategy to overcome this challenge. Its core concept is the conversion of the model into the format of biochemical systems theory (BST), which greatly facilitates the computation of sensitivities. First, the steady state of interest is determined by integrating the model equations toward the steady state and then using a Newton-Raphson method to fine-tune the result. The second step of conversion into the BST format requires several instances of numerical differentiation. The accuracy of this task is ensured by the use of a complex-variable Taylor scheme for all differentiation steps. The proposed strategy is implemented in a new software program, COSMOS, which automates the stability and sensitivity analysis of essentially arbitrary ODE models in a quick, yet highly accurate manner. The methods underlying the process are theoretically analyzed and illustrated with four representative examples: a simple metabolic reaction model; a model of aspartate-derived amino acid biosynthesis; a TCA-cycle model; and a modified TCA-cycle model. COSMOS has been deposited to https://github.com/BioprocessdesignLab/COSMOS.'" ] }, - "execution_count": 279, + "execution_count": 12, "metadata": {}, "output_type": "execute_result" } @@ -303,7 +303,7 @@ }, { "cell_type": "code", - "execution_count": 280, + "execution_count": 13, "metadata": { "collapsed": true }, @@ -315,7 +315,7 @@ }, { "cell_type": "code", - "execution_count": 281, + "execution_count": 14, "metadata": { "collapsed": true }, @@ -333,7 +333,7 @@ }, { "cell_type": "code", - "execution_count": 282, + "execution_count": 15, "metadata": { "collapsed": false }, @@ -344,7 +344,7 @@ }, { "cell_type": "code", - "execution_count": 283, + "execution_count": 16, "metadata": { "collapsed": true }, @@ -354,26 +354,34 @@ ] }, { - "cell_type": "code", - "execution_count": null, + "cell_type": "markdown", "metadata": { "collapsed": true }, - "outputs": [], "source": [ "Extracting urls containing the string github to create project url entry works well; need to work on parsing " ] }, { "cell_type": "code", - "execution_count": 300, + "execution_count": 134, "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "ename": "SyntaxError", + "evalue": "invalid syntax (, line 20)", + "output_type": "error", + "traceback": [ + "\u001b[1;36m File \u001b[1;32m\"\"\u001b[1;36m, line \u001b[1;32m20\u001b[0m\n\u001b[1;33m else\u001b[0m\n\u001b[1;37m ^\u001b[0m\n\u001b[1;31mSyntaxError\u001b[0m\u001b[1;31m:\u001b[0m invalid syntax\n" + ] + } + ], "source": [ "for i in range(0,(len(df.index)-1)): \n", " abstract = df.iat[i,0]\n", + " github_project = ''\n", " try:\n", " project_url_list = re.findall(URL_REGEX, abstract)\n", " \n", @@ -382,10 +390,16 @@ " \n", " df.iat[i,5] = project_url\n", "\n", - " if project_url.startswith('https://github.com'):\n", - " github_project = urlparse(project_url).path\n", + " if project_url.startswith('https://github.com') or project_url.startswith('http://github.com'):\n", + " github_project = urlparse(project_url).path[1:]\n", + " df.iat[i,3] = github_project\n", " \n", - " df.iat[i,3] = github_project\n", + " elif project_url.startswith('github.com'):\n", + " github_project = project_url[11:]\n", + " df.iat[i,3] = github_project\n", + " \n", + " else\n", + " df.iat[i,3] = ''\n", " \n", " except:\n", " except_no = except_no + 1 \n", @@ -412,933 +426,30 @@ }, { "cell_type": "code", - "execution_count": 285, + "execution_count": null, "metadata": { "collapsed": false, "scrolled": true }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "270\n" - ] - } - ], + "outputs": [], "source": [ "print except_no" ] }, { "cell_type": "code", - "execution_count": 301, + "execution_count": null, "metadata": { "collapsed": false }, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
AbstractAuthorsDateGithubJournalUrl
26357045Stability and sensitivity analyses of biologic...[(Shiraishi, Fumihide), (Yoshida, Erika), (Voi...2015-09-11/BioprocessdesignLab/COSMOSIEEE/ACM Trans Comput Biol Bioinformhttps://github.com/BioprocessdesignLab/COSMOS
25601296Most electronic data capture (EDC) and electro...[(Dixit, Abhishek), (Dobson, Richard J B)]2015-01-20JMIR Med Inform
25558360Remotely sensed data - available at medium to ...[(Tuck, Sean L), (Phillips, Helen Rp), (Hintze...2015-01-05/seantuck12/MODISToolsEcol Evolhttps://github.com/seantuck12/MODISTools
25553811Whole-genome bisulfite sequencing (WGBS) is an...[(Chen, Junfang), (Lutsik, Pavlo), (Akulenko, ...2015-01-02/Junfang/AKSmoothJ Bioinform Comput Biolhttps://github.com/Junfang/AKSmooth
25549775A number of computational approaches have been...[(Manini, Simone), (Antiga, Luca), (Botti, Lor...2015-06-09/Junfang/AKSmoothAnn Biomed Enghttp://archtk.github.com
25543048Sampling the conformational space of biologica...[(Bouvier, Guillaume), (Desdouits, Nathan), (F...2015-04-28Bioinformatics
25540185With rapidly increasing volumes of biological ...[(Meinicke, Peter)]2015-04-28Bioinformatics
25527832Current strategies for SNP and INDEL discovery...[(Lindberg, Michael R), (Hall, Ira M), (Quinla...2015-04-12Bioinformatics
25526884An absent word of a word y of length n is a wo...[(Barton, Carl), (Heliou, Alice), (Mouchard, L...2015-04-27BMC Bioinformatics
25524895VarSim is a framework for assessing alignment ...[(Mu, John C), (Mohiyuddin, Marghoob), (Li, Ji...2015-04-28Bioinformatics
25521965Thyroid cancer is the most common endocrine tu...[(Wu, Chengkun), (Schwartz, Jean-Marc), (Braba...2014-12-19BMC Med Genomics
25520192RNA performs a diverse array of important func...[(Gardner, Paul P), (Eldai, Hisham)]2015-01-24/ppgardne/RMfamNucleic Acids Res.https://github.com/ppgardne/RMfam
25514851We describe an open-source kPAL package that f...[(Anvar, Seyed Yahya), (Khachatryan, Lusine), ...2015-02-06/LUMC/kPALGenome Biol.https://github.com/LUMC/kPAL
25505094Circular permutation is an important type of p...[(Bliven, Spencer E), (Bourne, Philip E), (Prl...2015-04-12Bioinformatics
25505087In bioinformatic applications, computationally...[(Völkel, Gunnar), (Lausser, Ludwig), (Schmid,...2015-04-12Bioinformatics
25505086All current mitochondrial haplogroup classific...[(Navarro-Gomez, Daniel), (Leipzig, Jeremy), (...2015-04-12Bioinformatics
25504847A standard approach to classifying sets of gen...[(Haubold, Bernhard), (Klötzl, Fabian), (Pfaff...2015-04-12Bioinformatics
25481009ICMA, a software framework to create 3D finite...[(Hussan, Jagir R), (Hunter, Peter J), (Gladdi...2015-04-12Bioinformatics
25481007Kablammo is a web-based application that produ...[(Wintersinger, Jeff A), (Wasmuth, James D)]2015-04-12Bioinformatics
25480375Expression quantitative trait loci (eQTL) stud...[(Harvey, Chris T), (Moyerbrailean, Gregory A)...2015-04-12Bioinformatics
25474353Phylogenetic analyses which include fossils or...[(Gavryushkina, Alexandra), (Welch, David), (S...2014-12-05/CompEvol/sampled-ancestorsPLoS Comput. Biol.https://github.com/CompEvol/sampled-ancestors
25461763Since the read lengths of high throughput sequ...[(Zhu, Xiao), (Leung, Henry C M), (Chin, Franc...2014-12-03/hitbio/PERGAPLoS ONEhttps://github.com/hitbio/PERGA
25452688Mobile elements constitute greater than 45% of...[(Lee, Wan-Ping), (Wu, Jiantao), (Marth, Gabor...2014-12-02/jiantao/TangramCancer Informhttps://github.com/jiantao/Tangram
25435543Isobaric labeling techniques coupled with high...[(Sheng, Quanhu), (Li, Rongxia), (Dai, Jie), (...2015-01-31/shengqh/RCPA.Tools/releasesMol. Cell Proteomicshttps://github.com/shengqh/RCPA.Tools/releases
25431162Post-translational modifications (PTMs) consti...[(Warnecke, Andreas), (Sandalova, Tatyana), (A...2015-04-27BMC Bioinformatics
25428347Genetic screens of an unprecedented scale have...[(Diaz, Aaron A), (Qin, Han), (Ramalho-Santos,...2015-02-18/diazlab/HiTSelectNucleic Acids Res.https://github.com/diazlab/HiTSelect
25422674Rapid molecular typing of bacterial pathogens ...[(Inouye, Michael), (Dashnow, Harriet), (Raven...2014-11-25/diazlab/HiTSelectGenome Medhttp://katholt.github.io/srst2/
25414364Protein sequence and structure representation ...[(Hirsh, Layla), (Piovesan, Damiano), (Giollo,...2015-04-03Bioinformatics
25414349The emergence of new sequencing technologies h...[(Croucher, Nicholas J), (Page, Andrew J), (Co...2015-02-18/diazlab/HiTSelectNucleic Acids Res.github.com/sanger-pathogens/Gubbins
25410596Whole-genome sequences are now available for m...[(Treangen, Todd J), (Ondov, Brian D), (Koren,...2015-01-07/diazlab/HiTSelectGenome Biol.http://github.com/marbl/harvest
.....................
24728855Phylogenetic comparative methods are essential...[(Pennell, Matthew W), (Eastman, Jonathan M), ...2014-07-19Bioinformatics
24727652Genomic information is encoded on a wide range...[(Knijnenburg, Theo A), (Ramsey, Stephen A), (...2014-05-30/tknijnen/msr/Nat. Methodshttps://github.com/tknijnen/msr/
24715980Signaling pathways provide essential informati...[(Villaveces, Jose M), (Jimenez, Rafael C), (H...2014-04-09F1000Res
24707447Background Understanding the evolutionary rela...[(Grant, Jessica R), (Katz, Laura A)]2014-04-07PLoS Curr
24703969Advances in next-generation sequencing (NGS) t...[(Guo, Yan), (Zhao, Shilin), (Sheng, Quanhu), ...2014-06-14/slzhao/QC3Genomicshttps://github.com/slzhao/QC3
24700534We here present GradientOptimizer, an intuitiv...[(Moruz, Luminita), (Käll, Lukas)]2014-06-12/statisticalbiotechnology/NonlinearGradientsUIProteomicshttps://github.com/statisticalbiotechnology/No...
24695491The primary goal of genome-wide association st...[(Botta, Vincent), (Louppe, Gilles), (Geurts, ...2014-04-03/statisticalbiotechnology/NonlinearGradientsUIPLoS ONEgithub.com/0asa/TTree-source
24695406Next-generation sequencing (NGS) has revolutio...[(Li, Yi), (Xie, Xiaohui)]2014-07-19Bioinformatics
24688855We present a powerful Python library to quickl...[(Christensen, Anders S), (Hamelryck, Thomas),...2014-04-01/jensengroup/fragbuilder/PeerJhttps://github.com/jensengroup/fragbuilder/
24681267Symmetry is an important feature of protein te...[(Myers-Turnbull, Douglas), (Bliven, Spencer E...2014-05-06/rcsb/symmetryJ. Mol. Biol.https://github.com/rcsb/symmetry
24677618Transcript-based annotation and pedigree analy...[(Jäger, Marten), (Wang, Kai), (Bauer, Sebasti...2014-04-23/charite/jannovarHum. Mutat.https://github.com/charite/jannovar
24675810Virus populations can display high genetic div...[(Töpfer, Armin), (Marschall, Tobias), (Bull, ...2014-03-28/armintoepfer/haplocliquePLoS Comput. Biol.https://github.com/armintoepfer/haploclique
24672471Analysis of functional magnetic resonance imag...[(Eklund, Anders), (Dufort, Paul), (Villani, M...2014-03-27/wanderine/BROCCOLI/Front Neuroinformhttps://github.com/wanderine/BROCCOLI/
24667828Bioreactors are designed to support highly con...[(Burdge, David A), (Libourel, Igor G L)]2014-03-26/LibourelLab/BiofloSoftwarePLoS ONEhttps://github.com/LibourelLab/BiofloSoftware
24658388Power line interference may severely corrupt n...[(Keshtkaran, Mohammad Reza), (Yang, Zhi)]2014-04-03J Neural Eng
24657354The cerebellum has classically been linked to ...[(Park, Min Tae M), (Pipitone, Jon), (Baer, La...2014-06-03/pipitone/MAGeTbrainNeuroimagehttps://github.com/pipitone/MAGeTbrain
24653694Analysis of brain connectivity has become an i...[(Billinger, Martin), (Brunner, Clemens), (Mül...2014-03-21/pipitone/MAGeTbrainFront Neuroinformgithub.com/SCoT-dev/SCoT
24647222Genome-Wide Association Studies are widely use...[(Greshake, Bastian), (Bayer, Philipp E), (Rau...2014-03-20/pipitone/MAGeTbrainPLoS ONEhttp://github.com/gedankenstuecke/snpr
24627804The DAGViewer BioJS component is a reusable Ja...[(Kalderimis, Alexis), (Stepan, Radek), (Sulli...2014-03-14F1000Res
24618470High-throughput single-cell quantitative real-...[(Buettner, Florian), (Moignard, Victoria), (G...2014-06-27Bioinformatics
24602450The secondary structure that maximizes the num...[(Venkatachalam, Balaji), (Gusfield, Dan), (Fr...2014-03-24Algorithms Mol Biol
24588150All atom molecular dynamics (MD) models provid...[(Ljubetič, Ajasja), (Urbančič, Iztok), (Štran...2014-03-04/lbf-ijs/DiffusiveDynamicsJ Chem Physhttps://github.com/lbf-ijs/DiffusiveDynamics
24586045In eukaryotes, detailed surveys of recombinati...[(Yahara, Koji), (Didelot, Xavier), (Ansari, M...2014-05-26/bioprojects/orderedPaintingMol. Biol. Evol.https://github.com/bioprojects/orderedPainting
24574113Advances in typing methodologies have recently...[(Lärkeryd, Adrian), (Myrtennäs, Kerstin), (Ka...2014-06-16Bioinformatics
24567544The generation of large volumes of omics data ...[(Deu-Pons, Jordi), (Schroeder, Michael P), (L...2014-06-16Bioinformatics
24564867RNA-Seq methodology is a revolutionary transcr...[(Bu, Jingde), (Chi, Xuebin), (Jin, Zhong)]2014-02-25BMC Syst Biol
24564732The ISA-Tab format and software suite have bee...[(González-Beltrán, Alejandra), (Neumann, Stef...2014-02-25BMC Bioinformatics
24564706Among challenges that hamper reaping the benef...[(Soueidan, Hayssam), (Maurier, Florence), (Gr...2014-02-25BMC Bioinformatics
24564637Selecting genes and pathways indicative of dis...[(Zhang, Wen), (Wan, Ying-Wooi), (Allen, Genev...2014-02-25BMC Genomics
24564427Many biological processes are carried out by p...[(Wong, Daniel), (Li, Xiao-Li), (Wu, Min), (Zh...2014-02-25BMC Genomics
\n", - "

200 rows × 6 columns

\n", - "
" - ], - "text/plain": [ - " Abstract \\\n", - "26357045 Stability and sensitivity analyses of biologic... \n", - "25601296 Most electronic data capture (EDC) and electro... \n", - "25558360 Remotely sensed data - available at medium to ... \n", - "25553811 Whole-genome bisulfite sequencing (WGBS) is an... \n", - "25549775 A number of computational approaches have been... \n", - "25543048 Sampling the conformational space of biologica... \n", - "25540185 With rapidly increasing volumes of biological ... \n", - "25527832 Current strategies for SNP and INDEL discovery... \n", - "25526884 An absent word of a word y of length n is a wo... \n", - "25524895 VarSim is a framework for assessing alignment ... \n", - "25521965 Thyroid cancer is the most common endocrine tu... \n", - "25520192 RNA performs a diverse array of important func... \n", - "25514851 We describe an open-source kPAL package that f... \n", - "25505094 Circular permutation is an important type of p... \n", - "25505087 In bioinformatic applications, computationally... \n", - "25505086 All current mitochondrial haplogroup classific... \n", - "25504847 A standard approach to classifying sets of gen... \n", - "25481009 ICMA, a software framework to create 3D finite... \n", - "25481007 Kablammo is a web-based application that produ... \n", - "25480375 Expression quantitative trait loci (eQTL) stud... \n", - "25474353 Phylogenetic analyses which include fossils or... \n", - "25461763 Since the read lengths of high throughput sequ... \n", - "25452688 Mobile elements constitute greater than 45% of... \n", - "25435543 Isobaric labeling techniques coupled with high... \n", - "25431162 Post-translational modifications (PTMs) consti... \n", - "25428347 Genetic screens of an unprecedented scale have... \n", - "25422674 Rapid molecular typing of bacterial pathogens ... \n", - "25414364 Protein sequence and structure representation ... \n", - "25414349 The emergence of new sequencing technologies h... \n", - "25410596 Whole-genome sequences are now available for m... \n", - "... ... \n", - "24728855 Phylogenetic comparative methods are essential... \n", - "24727652 Genomic information is encoded on a wide range... \n", - "24715980 Signaling pathways provide essential informati... \n", - "24707447 Background Understanding the evolutionary rela... \n", - "24703969 Advances in next-generation sequencing (NGS) t... \n", - "24700534 We here present GradientOptimizer, an intuitiv... \n", - "24695491 The primary goal of genome-wide association st... \n", - "24695406 Next-generation sequencing (NGS) has revolutio... \n", - "24688855 We present a powerful Python library to quickl... \n", - "24681267 Symmetry is an important feature of protein te... \n", - "24677618 Transcript-based annotation and pedigree analy... \n", - "24675810 Virus populations can display high genetic div... \n", - "24672471 Analysis of functional magnetic resonance imag... \n", - "24667828 Bioreactors are designed to support highly con... \n", - "24658388 Power line interference may severely corrupt n... \n", - "24657354 The cerebellum has classically been linked to ... \n", - "24653694 Analysis of brain connectivity has become an i... \n", - "24647222 Genome-Wide Association Studies are widely use... \n", - "24627804 The DAGViewer BioJS component is a reusable Ja... \n", - "24618470 High-throughput single-cell quantitative real-... \n", - "24602450 The secondary structure that maximizes the num... \n", - "24588150 All atom molecular dynamics (MD) models provid... \n", - "24586045 In eukaryotes, detailed surveys of recombinati... \n", - "24574113 Advances in typing methodologies have recently... \n", - "24567544 The generation of large volumes of omics data ... \n", - "24564867 RNA-Seq methodology is a revolutionary transcr... \n", - "24564732 The ISA-Tab format and software suite have bee... \n", - "24564706 Among challenges that hamper reaping the benef... \n", - "24564637 Selecting genes and pathways indicative of dis... \n", - "24564427 Many biological processes are carried out by p... \n", - "\n", - " Authors Date \\\n", - "26357045 [(Shiraishi, Fumihide), (Yoshida, Erika), (Voi... 2015-09-11 \n", - "25601296 [(Dixit, Abhishek), (Dobson, Richard J B)] 2015-01-20 \n", - "25558360 [(Tuck, Sean L), (Phillips, Helen Rp), (Hintze... 2015-01-05 \n", - "25553811 [(Chen, Junfang), (Lutsik, Pavlo), (Akulenko, ... 2015-01-02 \n", - "25549775 [(Manini, Simone), (Antiga, Luca), (Botti, Lor... 2015-06-09 \n", - "25543048 [(Bouvier, Guillaume), (Desdouits, Nathan), (F... 2015-04-28 \n", - "25540185 [(Meinicke, Peter)] 2015-04-28 \n", - "25527832 [(Lindberg, Michael R), (Hall, Ira M), (Quinla... 2015-04-12 \n", - "25526884 [(Barton, Carl), (Heliou, Alice), (Mouchard, L... 2015-04-27 \n", - "25524895 [(Mu, John C), (Mohiyuddin, Marghoob), (Li, Ji... 2015-04-28 \n", - "25521965 [(Wu, Chengkun), (Schwartz, Jean-Marc), (Braba... 2014-12-19 \n", - "25520192 [(Gardner, Paul P), (Eldai, Hisham)] 2015-01-24 \n", - "25514851 [(Anvar, Seyed Yahya), (Khachatryan, Lusine), ... 2015-02-06 \n", - "25505094 [(Bliven, Spencer E), (Bourne, Philip E), (Prl... 2015-04-12 \n", - "25505087 [(Völkel, Gunnar), (Lausser, Ludwig), (Schmid,... 2015-04-12 \n", - "25505086 [(Navarro-Gomez, Daniel), (Leipzig, Jeremy), (... 2015-04-12 \n", - "25504847 [(Haubold, Bernhard), (Klötzl, Fabian), (Pfaff... 2015-04-12 \n", - "25481009 [(Hussan, Jagir R), (Hunter, Peter J), (Gladdi... 2015-04-12 \n", - "25481007 [(Wintersinger, Jeff A), (Wasmuth, James D)] 2015-04-12 \n", - "25480375 [(Harvey, Chris T), (Moyerbrailean, Gregory A)... 2015-04-12 \n", - "25474353 [(Gavryushkina, Alexandra), (Welch, David), (S... 2014-12-05 \n", - "25461763 [(Zhu, Xiao), (Leung, Henry C M), (Chin, Franc... 2014-12-03 \n", - "25452688 [(Lee, Wan-Ping), (Wu, Jiantao), (Marth, Gabor... 2014-12-02 \n", - "25435543 [(Sheng, Quanhu), (Li, Rongxia), (Dai, Jie), (... 2015-01-31 \n", - "25431162 [(Warnecke, Andreas), (Sandalova, Tatyana), (A... 2015-04-27 \n", - "25428347 [(Diaz, Aaron A), (Qin, Han), (Ramalho-Santos,... 2015-02-18 \n", - "25422674 [(Inouye, Michael), (Dashnow, Harriet), (Raven... 2014-11-25 \n", - "25414364 [(Hirsh, Layla), (Piovesan, Damiano), (Giollo,... 2015-04-03 \n", - "25414349 [(Croucher, Nicholas J), (Page, Andrew J), (Co... 2015-02-18 \n", - "25410596 [(Treangen, Todd J), (Ondov, Brian D), (Koren,... 2015-01-07 \n", - "... ... ... \n", - "24728855 [(Pennell, Matthew W), (Eastman, Jonathan M), ... 2014-07-19 \n", - "24727652 [(Knijnenburg, Theo A), (Ramsey, Stephen A), (... 2014-05-30 \n", - "24715980 [(Villaveces, Jose M), (Jimenez, Rafael C), (H... 2014-04-09 \n", - "24707447 [(Grant, Jessica R), (Katz, Laura A)] 2014-04-07 \n", - "24703969 [(Guo, Yan), (Zhao, Shilin), (Sheng, Quanhu), ... 2014-06-14 \n", - "24700534 [(Moruz, Luminita), (Käll, Lukas)] 2014-06-12 \n", - "24695491 [(Botta, Vincent), (Louppe, Gilles), (Geurts, ... 2014-04-03 \n", - "24695406 [(Li, Yi), (Xie, Xiaohui)] 2014-07-19 \n", - "24688855 [(Christensen, Anders S), (Hamelryck, Thomas),... 2014-04-01 \n", - "24681267 [(Myers-Turnbull, Douglas), (Bliven, Spencer E... 2014-05-06 \n", - "24677618 [(Jäger, Marten), (Wang, Kai), (Bauer, Sebasti... 2014-04-23 \n", - "24675810 [(Töpfer, Armin), (Marschall, Tobias), (Bull, ... 2014-03-28 \n", - "24672471 [(Eklund, Anders), (Dufort, Paul), (Villani, M... 2014-03-27 \n", - "24667828 [(Burdge, David A), (Libourel, Igor G L)] 2014-03-26 \n", - "24658388 [(Keshtkaran, Mohammad Reza), (Yang, Zhi)] 2014-04-03 \n", - "24657354 [(Park, Min Tae M), (Pipitone, Jon), (Baer, La... 2014-06-03 \n", - "24653694 [(Billinger, Martin), (Brunner, Clemens), (Mül... 2014-03-21 \n", - "24647222 [(Greshake, Bastian), (Bayer, Philipp E), (Rau... 2014-03-20 \n", - "24627804 [(Kalderimis, Alexis), (Stepan, Radek), (Sulli... 2014-03-14 \n", - "24618470 [(Buettner, Florian), (Moignard, Victoria), (G... 2014-06-27 \n", - "24602450 [(Venkatachalam, Balaji), (Gusfield, Dan), (Fr... 2014-03-24 \n", - "24588150 [(Ljubetič, Ajasja), (Urbančič, Iztok), (Štran... 2014-03-04 \n", - "24586045 [(Yahara, Koji), (Didelot, Xavier), (Ansari, M... 2014-05-26 \n", - "24574113 [(Lärkeryd, Adrian), (Myrtennäs, Kerstin), (Ka... 2014-06-16 \n", - "24567544 [(Deu-Pons, Jordi), (Schroeder, Michael P), (L... 2014-06-16 \n", - "24564867 [(Bu, Jingde), (Chi, Xuebin), (Jin, Zhong)] 2014-02-25 \n", - "24564732 [(González-Beltrán, Alejandra), (Neumann, Stef... 2014-02-25 \n", - "24564706 [(Soueidan, Hayssam), (Maurier, Florence), (Gr... 2014-02-25 \n", - "24564637 [(Zhang, Wen), (Wan, Ying-Wooi), (Allen, Genev... 2014-02-25 \n", - "24564427 [(Wong, Daniel), (Li, Xiao-Li), (Wu, Min), (Zh... 2014-02-25 \n", - "\n", - " Github \\\n", - "26357045 /BioprocessdesignLab/COSMOS \n", - "25601296 \n", - "25558360 /seantuck12/MODISTools \n", - "25553811 /Junfang/AKSmooth \n", - "25549775 /Junfang/AKSmooth \n", - "25543048 \n", - "25540185 \n", - "25527832 \n", - "25526884 \n", - "25524895 \n", - "25521965 \n", - "25520192 /ppgardne/RMfam \n", - "25514851 /LUMC/kPAL \n", - "25505094 \n", - "25505087 \n", - "25505086 \n", - "25504847 \n", - "25481009 \n", - "25481007 \n", - "25480375 \n", - "25474353 /CompEvol/sampled-ancestors \n", - "25461763 /hitbio/PERGA \n", - "25452688 /jiantao/Tangram \n", - "25435543 /shengqh/RCPA.Tools/releases \n", - "25431162 \n", - "25428347 /diazlab/HiTSelect \n", - "25422674 /diazlab/HiTSelect \n", - "25414364 \n", - "25414349 /diazlab/HiTSelect \n", - "25410596 /diazlab/HiTSelect \n", - "... ... \n", - "24728855 \n", - "24727652 /tknijnen/msr/ \n", - "24715980 \n", - "24707447 \n", - "24703969 /slzhao/QC3 \n", - "24700534 /statisticalbiotechnology/NonlinearGradientsUI \n", - "24695491 /statisticalbiotechnology/NonlinearGradientsUI \n", - "24695406 \n", - "24688855 /jensengroup/fragbuilder/ \n", - "24681267 /rcsb/symmetry \n", - "24677618 /charite/jannovar \n", - "24675810 /armintoepfer/haploclique \n", - "24672471 /wanderine/BROCCOLI/ \n", - "24667828 /LibourelLab/BiofloSoftware \n", - "24658388 \n", - "24657354 /pipitone/MAGeTbrain \n", - "24653694 /pipitone/MAGeTbrain \n", - "24647222 /pipitone/MAGeTbrain \n", - "24627804 \n", - "24618470 \n", - "24602450 \n", - "24588150 /lbf-ijs/DiffusiveDynamics \n", - "24586045 /bioprojects/orderedPainting \n", - "24574113 \n", - "24567544 \n", - "24564867 \n", - "24564732 \n", - "24564706 \n", - "24564637 \n", - "24564427 \n", - "\n", - " Journal \\\n", - "26357045 IEEE/ACM Trans Comput Biol Bioinform \n", - "25601296 JMIR Med Inform \n", - "25558360 Ecol Evol \n", - "25553811 J Bioinform Comput Biol \n", - "25549775 Ann Biomed Eng \n", - "25543048 Bioinformatics \n", - "25540185 Bioinformatics \n", - "25527832 Bioinformatics \n", - "25526884 BMC Bioinformatics \n", - "25524895 Bioinformatics \n", - "25521965 BMC Med Genomics \n", - "25520192 Nucleic Acids Res. \n", - "25514851 Genome Biol. \n", - "25505094 Bioinformatics \n", - "25505087 Bioinformatics \n", - "25505086 Bioinformatics \n", - "25504847 Bioinformatics \n", - "25481009 Bioinformatics \n", - "25481007 Bioinformatics \n", - "25480375 Bioinformatics \n", - "25474353 PLoS Comput. Biol. \n", - "25461763 PLoS ONE \n", - "25452688 Cancer Inform \n", - "25435543 Mol. Cell Proteomics \n", - "25431162 BMC Bioinformatics \n", - "25428347 Nucleic Acids Res. \n", - "25422674 Genome Med \n", - "25414364 Bioinformatics \n", - "25414349 Nucleic Acids Res. \n", - "25410596 Genome Biol. \n", - "... ... \n", - "24728855 Bioinformatics \n", - "24727652 Nat. Methods \n", - "24715980 F1000Res \n", - "24707447 PLoS Curr \n", - "24703969 Genomics \n", - "24700534 Proteomics \n", - "24695491 PLoS ONE \n", - "24695406 Bioinformatics \n", - "24688855 PeerJ \n", - "24681267 J. Mol. Biol. \n", - "24677618 Hum. Mutat. \n", - "24675810 PLoS Comput. Biol. \n", - "24672471 Front Neuroinform \n", - "24667828 PLoS ONE \n", - "24658388 J Neural Eng \n", - "24657354 Neuroimage \n", - "24653694 Front Neuroinform \n", - "24647222 PLoS ONE \n", - "24627804 F1000Res \n", - "24618470 Bioinformatics \n", - "24602450 Algorithms Mol Biol \n", - "24588150 J Chem Phys \n", - "24586045 Mol. Biol. Evol. \n", - "24574113 Bioinformatics \n", - "24567544 Bioinformatics \n", - "24564867 BMC Syst Biol \n", - "24564732 BMC Bioinformatics \n", - "24564706 BMC Bioinformatics \n", - "24564637 BMC Genomics \n", - "24564427 BMC Genomics \n", - "\n", - " Url \n", - "26357045 https://github.com/BioprocessdesignLab/COSMOS \n", - "25601296 \n", - "25558360 https://github.com/seantuck12/MODISTools \n", - "25553811 https://github.com/Junfang/AKSmooth \n", - "25549775 http://archtk.github.com \n", - "25543048 \n", - "25540185 \n", - "25527832 \n", - "25526884 \n", - "25524895 \n", - "25521965 \n", - "25520192 https://github.com/ppgardne/RMfam \n", - "25514851 https://github.com/LUMC/kPAL \n", - "25505094 \n", - "25505087 \n", - "25505086 \n", - "25504847 \n", - "25481009 \n", - "25481007 \n", - "25480375 \n", - "25474353 https://github.com/CompEvol/sampled-ancestors \n", - "25461763 https://github.com/hitbio/PERGA \n", - "25452688 https://github.com/jiantao/Tangram \n", - "25435543 https://github.com/shengqh/RCPA.Tools/releases \n", - "25431162 \n", - "25428347 https://github.com/diazlab/HiTSelect \n", - "25422674 http://katholt.github.io/srst2/ \n", - "25414364 \n", - "25414349 github.com/sanger-pathogens/Gubbins \n", - "25410596 http://github.com/marbl/harvest \n", - "... ... \n", - "24728855 \n", - "24727652 https://github.com/tknijnen/msr/ \n", - "24715980 \n", - "24707447 \n", - "24703969 https://github.com/slzhao/QC3 \n", - "24700534 https://github.com/statisticalbiotechnology/No... \n", - "24695491 github.com/0asa/TTree-source \n", - "24695406 \n", - "24688855 https://github.com/jensengroup/fragbuilder/ \n", - "24681267 https://github.com/rcsb/symmetry \n", - "24677618 https://github.com/charite/jannovar \n", - "24675810 https://github.com/armintoepfer/haploclique \n", - "24672471 https://github.com/wanderine/BROCCOLI/ \n", - "24667828 https://github.com/LibourelLab/BiofloSoftware \n", - "24658388 \n", - "24657354 https://github.com/pipitone/MAGeTbrain \n", - "24653694 github.com/SCoT-dev/SCoT \n", - "24647222 http://github.com/gedankenstuecke/snpr \n", - "24627804 \n", - "24618470 \n", - "24602450 \n", - "24588150 https://github.com/lbf-ijs/DiffusiveDynamics \n", - "24586045 https://github.com/bioprojects/orderedPainting \n", - "24574113 \n", - "24567544 \n", - "24564867 \n", - "24564732 \n", - "24564706 \n", - "24564637 \n", - "24564427 \n", - "\n", - "[200 rows x 6 columns]" - ] - }, - "execution_count": 301, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "df.head(200)" ] }, { "cell_type": "code", - "execution_count": 287, + "execution_count": null, "metadata": { "collapsed": true }, @@ -1358,19 +469,11 @@ }, { "cell_type": "code", - "execution_count": 288, + "execution_count": null, "metadata": { "collapsed": false }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "https://github.com/BioprocessdesignLab/COSMOS\n" - ] - } - ], + "outputs": [], "source": [ "test = str(df.iat[0,5])\n", "print test" @@ -1378,19 +481,11 @@ }, { "cell_type": "code", - "execution_count": 289, + "execution_count": null, "metadata": { "collapsed": false }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "http://archtk.github.com\n" - ] - } - ], + "outputs": [], "source": [ "test2 = str(df.iat[4,5])\n", "print test2" @@ -1398,51 +493,29 @@ }, { "cell_type": "code", - "execution_count": 290, + "execution_count": null, "metadata": { "collapsed": false }, - "outputs": [ - { - "data": { - "text/plain": [ - "ParseResult(scheme='https', netloc='github.com', path='/BioprocessdesignLab/COSMOS', params='', query='', fragment='')" - ] - }, - "execution_count": 290, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "urlparse(test)\n" ] }, { "cell_type": "code", - "execution_count": 291, + "execution_count": null, "metadata": { "collapsed": false }, - "outputs": [ - { - "data": { - "text/plain": [ - "ParseResult(scheme='http', netloc='archtk.github.com', path='', params='', query='', fragment='')" - ] - }, - "execution_count": 291, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "urlparse(test2)" ] }, { "cell_type": "code", - "execution_count": 292, + "execution_count": null, "metadata": { "collapsed": false }, @@ -1453,41 +526,22 @@ }, { "cell_type": "code", - "execution_count": 293, + "execution_count": null, "metadata": { "collapsed": false }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "/BioprosessdesignLab/COSMOS\n" - ] - } - ], + "outputs": [], "source": [ "print(gurl.path)" ] }, { "cell_type": "code", - "execution_count": 294, + "execution_count": null, "metadata": { "collapsed": false }, - "outputs": [ - { - "data": { - "text/plain": [ - "0" - ] - }, - "execution_count": 294, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "test.find(\"https://github.com/\")\n", "\n" @@ -1504,7 +558,7 @@ }, { "cell_type": "code", - "execution_count": 295, + "execution_count": null, "metadata": { "collapsed": false }, @@ -1517,19 +571,11 @@ }, { "cell_type": "code", - "execution_count": 296, + "execution_count": null, "metadata": { "collapsed": false }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Whisper is a file-based time-series database format for Graphite.\n" - ] - } - ], + "outputs": [], "source": [ "whisper = g.get_repo(\"graphite-project/whisper\")\n", "print whisper.description" @@ -1537,23 +583,27 @@ }, { "cell_type": "code", - "execution_count": 297, + "execution_count": null, "metadata": { "collapsed": false }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Computation of Sensitivities in Model ODE Systems\n" - ] - } - ], + "outputs": [], "source": [ "cosmos = g.get_repo(\"BioprocessdesignLab/COSMOS\")\n", "print cosmos.description" ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "archtk = g.get_repo(\"archtk\")\n", + "print archtk.description" + ] } ], "metadata": { @@ -1572,7 +622,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython2", - "version": "2.7.6" + "version": "2.7.10" } }, "nbformat": 4, From e352b11e5b0b6d4175f87547b0b979bd542c8843 Mon Sep 17 00:00:00 2001 From: Melanie I Stefan Date: Thu, 14 Apr 2016 10:34:57 +0100 Subject: [PATCH 18/21] confirmed that we can get a github repo for almost 29% of entries --- src/find_github_repo.ipynb | 1190 +++++++++++++++++++++++++++++++++--- 1 file changed, 1099 insertions(+), 91 deletions(-) diff --git a/src/find_github_repo.ipynb b/src/find_github_repo.ipynb index 69a25ce..13c40d3 100644 --- a/src/find_github_repo.ipynb +++ b/src/find_github_repo.ipynb @@ -24,7 +24,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 71, "metadata": { "collapsed": false }, @@ -35,7 +35,7 @@ "['github_pubs.xml', 'README.md']" ] }, - "execution_count": 7, + "execution_count": 71, "metadata": {}, "output_type": "execute_result" } @@ -55,7 +55,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 72, "metadata": { "collapsed": true }, @@ -74,7 +74,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 73, "metadata": { "collapsed": true }, @@ -106,7 +106,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 74, "metadata": { "collapsed": true }, @@ -150,7 +150,7 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 75, "metadata": { "collapsed": false, "scrolled": true @@ -245,7 +245,7 @@ "25549775 Ann Biomed Eng " ] }, - "execution_count": 11, + "execution_count": 75, "metadata": {}, "output_type": "execute_result" } @@ -274,7 +274,7 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 76, "metadata": { "collapsed": false }, @@ -285,7 +285,7 @@ "'Stability and sensitivity analyses of biological systems require the ad hocwriting of computer code, which is highly dependent on the particular model and burdensome for large systems. We propose a very accurate strategy to overcome this challenge. Its core concept is the conversion of the model into the format of biochemical systems theory (BST), which greatly facilitates the computation of sensitivities. First, the steady state of interest is determined by integrating the model equations toward the steady state and then using a Newton-Raphson method to fine-tune the result. The second step of conversion into the BST format requires several instances of numerical differentiation. The accuracy of this task is ensured by the use of a complex-variable Taylor scheme for all differentiation steps. The proposed strategy is implemented in a new software program, COSMOS, which automates the stability and sensitivity analysis of essentially arbitrary ODE models in a quick, yet highly accurate manner. The methods underlying the process are theoretically analyzed and illustrated with four representative examples: a simple metabolic reaction model; a model of aspartate-derived amino acid biosynthesis; a TCA-cycle model; and a modified TCA-cycle model. COSMOS has been deposited to https://github.com/BioprocessdesignLab/COSMOS.'" ] }, - "execution_count": 12, + "execution_count": 76, "metadata": {}, "output_type": "execute_result" } @@ -303,7 +303,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 77, "metadata": { "collapsed": true }, @@ -313,27 +313,16 @@ "URL_REGEX = r\"\"\"(?i)\\b((?:https?:(?:/{1,3}|[a-z0-9%])|[a-z0-9.\\-]+[.](?:com|net|org|edu|gov|mil|aero|asia|biz|cat|coop|info|int|jobs|mobi|museum|name|post|pro|tel|travel|xxx|ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cs|cu|cv|cx|cy|cz|dd|de|dj|dk|dm|do|dz|ec|ee|eg|eh|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|Ja|sk|sl|sm|sn|so|sr|ss|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|yu|za|zm|zw)/)(?:[^\\s()<>{}\\[\\]]+|\\([^\\s()]*?\\([^\\s()]+\\)[^\\s()]*?\\)|\\([^\\s]+?\\))+(?:\\([^\\s()]*?\\([^\\s()]+\\)[^\\s()]*?\\)|\\([^\\s]+?\\)|[^\\s`!()\\[\\]{};:'\".,<>?«»“”‘’])|(?:(?, line 20)", - "output_type": "error", - "traceback": [ - "\u001b[1;36m File \u001b[1;32m\"\"\u001b[1;36m, line \u001b[1;32m20\u001b[0m\n\u001b[1;33m else\u001b[0m\n\u001b[1;37m ^\u001b[0m\n\u001b[1;31mSyntaxError\u001b[0m\u001b[1;31m:\u001b[0m invalid syntax\n" - ] - } - ], + "outputs": [], "source": [ + "except_no = 0\n", + "no_project_from_url = 0\n", + "project_from_url = 0\n", + "\n", + "\n", "for i in range(0,(len(df.index)-1)): \n", " abstract = df.iat[i,0]\n", " github_project = ''\n", @@ -393,87 +373,1032 @@ " if project_url.startswith('https://github.com') or project_url.startswith('http://github.com'):\n", " github_project = urlparse(project_url).path[1:]\n", " df.iat[i,3] = github_project\n", + " project_from_url = project_from_url + 1 \n", " \n", " elif project_url.startswith('github.com'):\n", " github_project = project_url[11:]\n", " df.iat[i,3] = github_project\n", + " project_from_url = project_from_url + 1 \n", + " \n", + " else:\n", + " no_project_from_url = no_project_from_url + 1\n", " \n", - " else\n", - " df.iat[i,3] = ''\n", - " \n", " except:\n", " except_no = except_no + 1 \n", " pass" ] }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "collapsed": true - }, - "outputs": [], - "source": [] - }, { "cell_type": "markdown", "metadata": { "collapsed": false }, "source": [ - "Check that this worked for most entries" + "Check how many abstracts did not have a github url associated with it" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 80, "metadata": { "collapsed": false, "scrolled": true }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "270\n" + ] + } + ], "source": [ "print except_no" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 81, "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
AbstractAuthorsDateGithubJournalUrl
26357045Stability and sensitivity analyses of biologic...[(Shiraishi, Fumihide), (Yoshida, Erika), (Voi...2015-09-11BioprocessdesignLab/COSMOSIEEE/ACM Trans Comput Biol Bioinformhttps://github.com/BioprocessdesignLab/COSMOS
25601296Most electronic data capture (EDC) and electro...[(Dixit, Abhishek), (Dobson, Richard J B)]2015-01-20JMIR Med Inform
25558360Remotely sensed data - available at medium to ...[(Tuck, Sean L), (Phillips, Helen Rp), (Hintze...2015-01-05seantuck12/MODISToolsEcol Evolhttps://github.com/seantuck12/MODISTools
25553811Whole-genome bisulfite sequencing (WGBS) is an...[(Chen, Junfang), (Lutsik, Pavlo), (Akulenko, ...2015-01-02Junfang/AKSmoothJ Bioinform Comput Biolhttps://github.com/Junfang/AKSmooth
25549775A number of computational approaches have been...[(Manini, Simone), (Antiga, Luca), (Botti, Lor...2015-06-09Ann Biomed Enghttp://archtk.github.com
25543048Sampling the conformational space of biologica...[(Bouvier, Guillaume), (Desdouits, Nathan), (F...2015-04-28Bioinformatics
25540185With rapidly increasing volumes of biological ...[(Meinicke, Peter)]2015-04-28Bioinformatics
25527832Current strategies for SNP and INDEL discovery...[(Lindberg, Michael R), (Hall, Ira M), (Quinla...2015-04-12Bioinformatics
25526884An absent word of a word y of length n is a wo...[(Barton, Carl), (Heliou, Alice), (Mouchard, L...2015-04-27BMC Bioinformatics
25524895VarSim is a framework for assessing alignment ...[(Mu, John C), (Mohiyuddin, Marghoob), (Li, Ji...2015-04-28Bioinformatics
25521965Thyroid cancer is the most common endocrine tu...[(Wu, Chengkun), (Schwartz, Jean-Marc), (Braba...2014-12-19BMC Med Genomics
25520192RNA performs a diverse array of important func...[(Gardner, Paul P), (Eldai, Hisham)]2015-01-24ppgardne/RMfamNucleic Acids Res.https://github.com/ppgardne/RMfam
25514851We describe an open-source kPAL package that f...[(Anvar, Seyed Yahya), (Khachatryan, Lusine), ...2015-02-06LUMC/kPALGenome Biol.https://github.com/LUMC/kPAL
25505094Circular permutation is an important type of p...[(Bliven, Spencer E), (Bourne, Philip E), (Prl...2015-04-12Bioinformatics
25505087In bioinformatic applications, computationally...[(Völkel, Gunnar), (Lausser, Ludwig), (Schmid,...2015-04-12Bioinformatics
25505086All current mitochondrial haplogroup classific...[(Navarro-Gomez, Daniel), (Leipzig, Jeremy), (...2015-04-12Bioinformatics
25504847A standard approach to classifying sets of gen...[(Haubold, Bernhard), (Klötzl, Fabian), (Pfaff...2015-04-12Bioinformatics
25481009ICMA, a software framework to create 3D finite...[(Hussan, Jagir R), (Hunter, Peter J), (Gladdi...2015-04-12Bioinformatics
25481007Kablammo is a web-based application that produ...[(Wintersinger, Jeff A), (Wasmuth, James D)]2015-04-12Bioinformatics
25480375Expression quantitative trait loci (eQTL) stud...[(Harvey, Chris T), (Moyerbrailean, Gregory A)...2015-04-12Bioinformatics
25474353Phylogenetic analyses which include fossils or...[(Gavryushkina, Alexandra), (Welch, David), (S...2014-12-05CompEvol/sampled-ancestorsPLoS Comput. Biol.https://github.com/CompEvol/sampled-ancestors
25461763Since the read lengths of high throughput sequ...[(Zhu, Xiao), (Leung, Henry C M), (Chin, Franc...2014-12-03hitbio/PERGAPLoS ONEhttps://github.com/hitbio/PERGA
25452688Mobile elements constitute greater than 45% of...[(Lee, Wan-Ping), (Wu, Jiantao), (Marth, Gabor...2014-12-02jiantao/TangramCancer Informhttps://github.com/jiantao/Tangram
25435543Isobaric labeling techniques coupled with high...[(Sheng, Quanhu), (Li, Rongxia), (Dai, Jie), (...2015-01-31shengqh/RCPA.Tools/releasesMol. Cell Proteomicshttps://github.com/shengqh/RCPA.Tools/releases
25431162Post-translational modifications (PTMs) consti...[(Warnecke, Andreas), (Sandalova, Tatyana), (A...2015-04-27BMC Bioinformatics
25428347Genetic screens of an unprecedented scale have...[(Diaz, Aaron A), (Qin, Han), (Ramalho-Santos,...2015-02-18diazlab/HiTSelectNucleic Acids Res.https://github.com/diazlab/HiTSelect
25422674Rapid molecular typing of bacterial pathogens ...[(Inouye, Michael), (Dashnow, Harriet), (Raven...2014-11-25Genome Medhttp://katholt.github.io/srst2/
25414364Protein sequence and structure representation ...[(Hirsh, Layla), (Piovesan, Damiano), (Giollo,...2015-04-03Bioinformatics
25414349The emergence of new sequencing technologies h...[(Croucher, Nicholas J), (Page, Andrew J), (Co...2015-02-18sanger-pathogens/GubbinsNucleic Acids Res.github.com/sanger-pathogens/Gubbins
25410596Whole-genome sequences are now available for m...[(Treangen, Todd J), (Ondov, Brian D), (Koren,...2015-01-07marbl/harvestGenome Biol.http://github.com/marbl/harvest
.....................
24728855Phylogenetic comparative methods are essential...[(Pennell, Matthew W), (Eastman, Jonathan M), ...2014-07-19Bioinformatics
24727652Genomic information is encoded on a wide range...[(Knijnenburg, Theo A), (Ramsey, Stephen A), (...2014-05-30tknijnen/msr/Nat. Methodshttps://github.com/tknijnen/msr/
24715980Signaling pathways provide essential informati...[(Villaveces, Jose M), (Jimenez, Rafael C), (H...2014-04-09F1000Res
24707447Background Understanding the evolutionary rela...[(Grant, Jessica R), (Katz, Laura A)]2014-04-07PLoS Curr
24703969Advances in next-generation sequencing (NGS) t...[(Guo, Yan), (Zhao, Shilin), (Sheng, Quanhu), ...2014-06-14slzhao/QC3Genomicshttps://github.com/slzhao/QC3
24700534We here present GradientOptimizer, an intuitiv...[(Moruz, Luminita), (Käll, Lukas)]2014-06-12statisticalbiotechnology/NonlinearGradientsUIProteomicshttps://github.com/statisticalbiotechnology/No...
24695491The primary goal of genome-wide association st...[(Botta, Vincent), (Louppe, Gilles), (Geurts, ...2014-04-030asa/TTree-sourcePLoS ONEgithub.com/0asa/TTree-source
24695406Next-generation sequencing (NGS) has revolutio...[(Li, Yi), (Xie, Xiaohui)]2014-07-19Bioinformatics
24688855We present a powerful Python library to quickl...[(Christensen, Anders S), (Hamelryck, Thomas),...2014-04-01jensengroup/fragbuilder/PeerJhttps://github.com/jensengroup/fragbuilder/
24681267Symmetry is an important feature of protein te...[(Myers-Turnbull, Douglas), (Bliven, Spencer E...2014-05-06rcsb/symmetryJ. Mol. Biol.https://github.com/rcsb/symmetry
24677618Transcript-based annotation and pedigree analy...[(Jäger, Marten), (Wang, Kai), (Bauer, Sebasti...2014-04-23charite/jannovarHum. Mutat.https://github.com/charite/jannovar
24675810Virus populations can display high genetic div...[(Töpfer, Armin), (Marschall, Tobias), (Bull, ...2014-03-28armintoepfer/haplocliquePLoS Comput. Biol.https://github.com/armintoepfer/haploclique
24672471Analysis of functional magnetic resonance imag...[(Eklund, Anders), (Dufort, Paul), (Villani, M...2014-03-27wanderine/BROCCOLI/Front Neuroinformhttps://github.com/wanderine/BROCCOLI/
24667828Bioreactors are designed to support highly con...[(Burdge, David A), (Libourel, Igor G L)]2014-03-26LibourelLab/BiofloSoftwarePLoS ONEhttps://github.com/LibourelLab/BiofloSoftware
24658388Power line interference may severely corrupt n...[(Keshtkaran, Mohammad Reza), (Yang, Zhi)]2014-04-03J Neural Eng
24657354The cerebellum has classically been linked to ...[(Park, Min Tae M), (Pipitone, Jon), (Baer, La...2014-06-03pipitone/MAGeTbrainNeuroimagehttps://github.com/pipitone/MAGeTbrain
24653694Analysis of brain connectivity has become an i...[(Billinger, Martin), (Brunner, Clemens), (Mül...2014-03-21SCoT-dev/SCoTFront Neuroinformgithub.com/SCoT-dev/SCoT
24647222Genome-Wide Association Studies are widely use...[(Greshake, Bastian), (Bayer, Philipp E), (Rau...2014-03-20gedankenstuecke/snprPLoS ONEhttp://github.com/gedankenstuecke/snpr
24627804The DAGViewer BioJS component is a reusable Ja...[(Kalderimis, Alexis), (Stepan, Radek), (Sulli...2014-03-14F1000Res
24618470High-throughput single-cell quantitative real-...[(Buettner, Florian), (Moignard, Victoria), (G...2014-06-27Bioinformatics
24602450The secondary structure that maximizes the num...[(Venkatachalam, Balaji), (Gusfield, Dan), (Fr...2014-03-24Algorithms Mol Biol
24588150All atom molecular dynamics (MD) models provid...[(Ljubetič, Ajasja), (Urbančič, Iztok), (Štran...2014-03-04lbf-ijs/DiffusiveDynamicsJ Chem Physhttps://github.com/lbf-ijs/DiffusiveDynamics
24586045In eukaryotes, detailed surveys of recombinati...[(Yahara, Koji), (Didelot, Xavier), (Ansari, M...2014-05-26bioprojects/orderedPaintingMol. Biol. Evol.https://github.com/bioprojects/orderedPainting
24574113Advances in typing methodologies have recently...[(Lärkeryd, Adrian), (Myrtennäs, Kerstin), (Ka...2014-06-16Bioinformatics
24567544The generation of large volumes of omics data ...[(Deu-Pons, Jordi), (Schroeder, Michael P), (L...2014-06-16Bioinformatics
24564867RNA-Seq methodology is a revolutionary transcr...[(Bu, Jingde), (Chi, Xuebin), (Jin, Zhong)]2014-02-25BMC Syst Biol
24564732The ISA-Tab format and software suite have bee...[(González-Beltrán, Alejandra), (Neumann, Stef...2014-02-25BMC Bioinformatics
24564706Among challenges that hamper reaping the benef...[(Soueidan, Hayssam), (Maurier, Florence), (Gr...2014-02-25BMC Bioinformatics
24564637Selecting genes and pathways indicative of dis...[(Zhang, Wen), (Wan, Ying-Wooi), (Allen, Genev...2014-02-25BMC Genomics
24564427Many biological processes are carried out by p...[(Wong, Daniel), (Li, Xiao-Li), (Wu, Min), (Zh...2014-02-25BMC Genomics
\n", + "

200 rows × 6 columns

\n", + "
" + ], + "text/plain": [ + " Abstract \\\n", + "26357045 Stability and sensitivity analyses of biologic... \n", + "25601296 Most electronic data capture (EDC) and electro... \n", + "25558360 Remotely sensed data - available at medium to ... \n", + "25553811 Whole-genome bisulfite sequencing (WGBS) is an... \n", + "25549775 A number of computational approaches have been... \n", + "25543048 Sampling the conformational space of biologica... \n", + "25540185 With rapidly increasing volumes of biological ... \n", + "25527832 Current strategies for SNP and INDEL discovery... \n", + "25526884 An absent word of a word y of length n is a wo... \n", + "25524895 VarSim is a framework for assessing alignment ... \n", + "25521965 Thyroid cancer is the most common endocrine tu... \n", + "25520192 RNA performs a diverse array of important func... \n", + "25514851 We describe an open-source kPAL package that f... \n", + "25505094 Circular permutation is an important type of p... \n", + "25505087 In bioinformatic applications, computationally... \n", + "25505086 All current mitochondrial haplogroup classific... \n", + "25504847 A standard approach to classifying sets of gen... \n", + "25481009 ICMA, a software framework to create 3D finite... \n", + "25481007 Kablammo is a web-based application that produ... \n", + "25480375 Expression quantitative trait loci (eQTL) stud... \n", + "25474353 Phylogenetic analyses which include fossils or... \n", + "25461763 Since the read lengths of high throughput sequ... \n", + "25452688 Mobile elements constitute greater than 45% of... \n", + "25435543 Isobaric labeling techniques coupled with high... \n", + "25431162 Post-translational modifications (PTMs) consti... \n", + "25428347 Genetic screens of an unprecedented scale have... \n", + "25422674 Rapid molecular typing of bacterial pathogens ... \n", + "25414364 Protein sequence and structure representation ... \n", + "25414349 The emergence of new sequencing technologies h... \n", + "25410596 Whole-genome sequences are now available for m... \n", + "... ... \n", + "24728855 Phylogenetic comparative methods are essential... \n", + "24727652 Genomic information is encoded on a wide range... \n", + "24715980 Signaling pathways provide essential informati... \n", + "24707447 Background Understanding the evolutionary rela... \n", + "24703969 Advances in next-generation sequencing (NGS) t... \n", + "24700534 We here present GradientOptimizer, an intuitiv... \n", + "24695491 The primary goal of genome-wide association st... \n", + "24695406 Next-generation sequencing (NGS) has revolutio... \n", + "24688855 We present a powerful Python library to quickl... \n", + "24681267 Symmetry is an important feature of protein te... \n", + "24677618 Transcript-based annotation and pedigree analy... \n", + "24675810 Virus populations can display high genetic div... \n", + "24672471 Analysis of functional magnetic resonance imag... \n", + "24667828 Bioreactors are designed to support highly con... \n", + "24658388 Power line interference may severely corrupt n... \n", + "24657354 The cerebellum has classically been linked to ... \n", + "24653694 Analysis of brain connectivity has become an i... \n", + "24647222 Genome-Wide Association Studies are widely use... \n", + "24627804 The DAGViewer BioJS component is a reusable Ja... \n", + "24618470 High-throughput single-cell quantitative real-... \n", + "24602450 The secondary structure that maximizes the num... \n", + "24588150 All atom molecular dynamics (MD) models provid... \n", + "24586045 In eukaryotes, detailed surveys of recombinati... \n", + "24574113 Advances in typing methodologies have recently... \n", + "24567544 The generation of large volumes of omics data ... \n", + "24564867 RNA-Seq methodology is a revolutionary transcr... \n", + "24564732 The ISA-Tab format and software suite have bee... \n", + "24564706 Among challenges that hamper reaping the benef... \n", + "24564637 Selecting genes and pathways indicative of dis... \n", + "24564427 Many biological processes are carried out by p... \n", + "\n", + " Authors Date \\\n", + "26357045 [(Shiraishi, Fumihide), (Yoshida, Erika), (Voi... 2015-09-11 \n", + "25601296 [(Dixit, Abhishek), (Dobson, Richard J B)] 2015-01-20 \n", + "25558360 [(Tuck, Sean L), (Phillips, Helen Rp), (Hintze... 2015-01-05 \n", + "25553811 [(Chen, Junfang), (Lutsik, Pavlo), (Akulenko, ... 2015-01-02 \n", + "25549775 [(Manini, Simone), (Antiga, Luca), (Botti, Lor... 2015-06-09 \n", + "25543048 [(Bouvier, Guillaume), (Desdouits, Nathan), (F... 2015-04-28 \n", + "25540185 [(Meinicke, Peter)] 2015-04-28 \n", + "25527832 [(Lindberg, Michael R), (Hall, Ira M), (Quinla... 2015-04-12 \n", + "25526884 [(Barton, Carl), (Heliou, Alice), (Mouchard, L... 2015-04-27 \n", + "25524895 [(Mu, John C), (Mohiyuddin, Marghoob), (Li, Ji... 2015-04-28 \n", + "25521965 [(Wu, Chengkun), (Schwartz, Jean-Marc), (Braba... 2014-12-19 \n", + "25520192 [(Gardner, Paul P), (Eldai, Hisham)] 2015-01-24 \n", + "25514851 [(Anvar, Seyed Yahya), (Khachatryan, Lusine), ... 2015-02-06 \n", + "25505094 [(Bliven, Spencer E), (Bourne, Philip E), (Prl... 2015-04-12 \n", + "25505087 [(Völkel, Gunnar), (Lausser, Ludwig), (Schmid,... 2015-04-12 \n", + "25505086 [(Navarro-Gomez, Daniel), (Leipzig, Jeremy), (... 2015-04-12 \n", + "25504847 [(Haubold, Bernhard), (Klötzl, Fabian), (Pfaff... 2015-04-12 \n", + "25481009 [(Hussan, Jagir R), (Hunter, Peter J), (Gladdi... 2015-04-12 \n", + "25481007 [(Wintersinger, Jeff A), (Wasmuth, James D)] 2015-04-12 \n", + "25480375 [(Harvey, Chris T), (Moyerbrailean, Gregory A)... 2015-04-12 \n", + "25474353 [(Gavryushkina, Alexandra), (Welch, David), (S... 2014-12-05 \n", + "25461763 [(Zhu, Xiao), (Leung, Henry C M), (Chin, Franc... 2014-12-03 \n", + "25452688 [(Lee, Wan-Ping), (Wu, Jiantao), (Marth, Gabor... 2014-12-02 \n", + "25435543 [(Sheng, Quanhu), (Li, Rongxia), (Dai, Jie), (... 2015-01-31 \n", + "25431162 [(Warnecke, Andreas), (Sandalova, Tatyana), (A... 2015-04-27 \n", + "25428347 [(Diaz, Aaron A), (Qin, Han), (Ramalho-Santos,... 2015-02-18 \n", + "25422674 [(Inouye, Michael), (Dashnow, Harriet), (Raven... 2014-11-25 \n", + "25414364 [(Hirsh, Layla), (Piovesan, Damiano), (Giollo,... 2015-04-03 \n", + "25414349 [(Croucher, Nicholas J), (Page, Andrew J), (Co... 2015-02-18 \n", + "25410596 [(Treangen, Todd J), (Ondov, Brian D), (Koren,... 2015-01-07 \n", + "... ... ... \n", + "24728855 [(Pennell, Matthew W), (Eastman, Jonathan M), ... 2014-07-19 \n", + "24727652 [(Knijnenburg, Theo A), (Ramsey, Stephen A), (... 2014-05-30 \n", + "24715980 [(Villaveces, Jose M), (Jimenez, Rafael C), (H... 2014-04-09 \n", + "24707447 [(Grant, Jessica R), (Katz, Laura A)] 2014-04-07 \n", + "24703969 [(Guo, Yan), (Zhao, Shilin), (Sheng, Quanhu), ... 2014-06-14 \n", + "24700534 [(Moruz, Luminita), (Käll, Lukas)] 2014-06-12 \n", + "24695491 [(Botta, Vincent), (Louppe, Gilles), (Geurts, ... 2014-04-03 \n", + "24695406 [(Li, Yi), (Xie, Xiaohui)] 2014-07-19 \n", + "24688855 [(Christensen, Anders S), (Hamelryck, Thomas),... 2014-04-01 \n", + "24681267 [(Myers-Turnbull, Douglas), (Bliven, Spencer E... 2014-05-06 \n", + "24677618 [(Jäger, Marten), (Wang, Kai), (Bauer, Sebasti... 2014-04-23 \n", + "24675810 [(Töpfer, Armin), (Marschall, Tobias), (Bull, ... 2014-03-28 \n", + "24672471 [(Eklund, Anders), (Dufort, Paul), (Villani, M... 2014-03-27 \n", + "24667828 [(Burdge, David A), (Libourel, Igor G L)] 2014-03-26 \n", + "24658388 [(Keshtkaran, Mohammad Reza), (Yang, Zhi)] 2014-04-03 \n", + "24657354 [(Park, Min Tae M), (Pipitone, Jon), (Baer, La... 2014-06-03 \n", + "24653694 [(Billinger, Martin), (Brunner, Clemens), (Mül... 2014-03-21 \n", + "24647222 [(Greshake, Bastian), (Bayer, Philipp E), (Rau... 2014-03-20 \n", + "24627804 [(Kalderimis, Alexis), (Stepan, Radek), (Sulli... 2014-03-14 \n", + "24618470 [(Buettner, Florian), (Moignard, Victoria), (G... 2014-06-27 \n", + "24602450 [(Venkatachalam, Balaji), (Gusfield, Dan), (Fr... 2014-03-24 \n", + "24588150 [(Ljubetič, Ajasja), (Urbančič, Iztok), (Štran... 2014-03-04 \n", + "24586045 [(Yahara, Koji), (Didelot, Xavier), (Ansari, M... 2014-05-26 \n", + "24574113 [(Lärkeryd, Adrian), (Myrtennäs, Kerstin), (Ka... 2014-06-16 \n", + "24567544 [(Deu-Pons, Jordi), (Schroeder, Michael P), (L... 2014-06-16 \n", + "24564867 [(Bu, Jingde), (Chi, Xuebin), (Jin, Zhong)] 2014-02-25 \n", + "24564732 [(González-Beltrán, Alejandra), (Neumann, Stef... 2014-02-25 \n", + "24564706 [(Soueidan, Hayssam), (Maurier, Florence), (Gr... 2014-02-25 \n", + "24564637 [(Zhang, Wen), (Wan, Ying-Wooi), (Allen, Genev... 2014-02-25 \n", + "24564427 [(Wong, Daniel), (Li, Xiao-Li), (Wu, Min), (Zh... 2014-02-25 \n", + "\n", + " Github \\\n", + "26357045 BioprocessdesignLab/COSMOS \n", + "25601296 \n", + "25558360 seantuck12/MODISTools \n", + "25553811 Junfang/AKSmooth \n", + "25549775 \n", + "25543048 \n", + "25540185 \n", + "25527832 \n", + "25526884 \n", + "25524895 \n", + "25521965 \n", + "25520192 ppgardne/RMfam \n", + "25514851 LUMC/kPAL \n", + "25505094 \n", + "25505087 \n", + "25505086 \n", + "25504847 \n", + "25481009 \n", + "25481007 \n", + "25480375 \n", + "25474353 CompEvol/sampled-ancestors \n", + "25461763 hitbio/PERGA \n", + "25452688 jiantao/Tangram \n", + "25435543 shengqh/RCPA.Tools/releases \n", + "25431162 \n", + "25428347 diazlab/HiTSelect \n", + "25422674 \n", + "25414364 \n", + "25414349 sanger-pathogens/Gubbins \n", + "25410596 marbl/harvest \n", + "... ... \n", + "24728855 \n", + "24727652 tknijnen/msr/ \n", + "24715980 \n", + "24707447 \n", + "24703969 slzhao/QC3 \n", + "24700534 statisticalbiotechnology/NonlinearGradientsUI \n", + "24695491 0asa/TTree-source \n", + "24695406 \n", + "24688855 jensengroup/fragbuilder/ \n", + "24681267 rcsb/symmetry \n", + "24677618 charite/jannovar \n", + "24675810 armintoepfer/haploclique \n", + "24672471 wanderine/BROCCOLI/ \n", + "24667828 LibourelLab/BiofloSoftware \n", + "24658388 \n", + "24657354 pipitone/MAGeTbrain \n", + "24653694 SCoT-dev/SCoT \n", + "24647222 gedankenstuecke/snpr \n", + "24627804 \n", + "24618470 \n", + "24602450 \n", + "24588150 lbf-ijs/DiffusiveDynamics \n", + "24586045 bioprojects/orderedPainting \n", + "24574113 \n", + "24567544 \n", + "24564867 \n", + "24564732 \n", + "24564706 \n", + "24564637 \n", + "24564427 \n", + "\n", + " Journal \\\n", + "26357045 IEEE/ACM Trans Comput Biol Bioinform \n", + "25601296 JMIR Med Inform \n", + "25558360 Ecol Evol \n", + "25553811 J Bioinform Comput Biol \n", + "25549775 Ann Biomed Eng \n", + "25543048 Bioinformatics \n", + "25540185 Bioinformatics \n", + "25527832 Bioinformatics \n", + "25526884 BMC Bioinformatics \n", + "25524895 Bioinformatics \n", + "25521965 BMC Med Genomics \n", + "25520192 Nucleic Acids Res. \n", + "25514851 Genome Biol. \n", + "25505094 Bioinformatics \n", + "25505087 Bioinformatics \n", + "25505086 Bioinformatics \n", + "25504847 Bioinformatics \n", + "25481009 Bioinformatics \n", + "25481007 Bioinformatics \n", + "25480375 Bioinformatics \n", + "25474353 PLoS Comput. Biol. \n", + "25461763 PLoS ONE \n", + "25452688 Cancer Inform \n", + "25435543 Mol. Cell Proteomics \n", + "25431162 BMC Bioinformatics \n", + "25428347 Nucleic Acids Res. \n", + "25422674 Genome Med \n", + "25414364 Bioinformatics \n", + "25414349 Nucleic Acids Res. \n", + "25410596 Genome Biol. \n", + "... ... \n", + "24728855 Bioinformatics \n", + "24727652 Nat. Methods \n", + "24715980 F1000Res \n", + "24707447 PLoS Curr \n", + "24703969 Genomics \n", + "24700534 Proteomics \n", + "24695491 PLoS ONE \n", + "24695406 Bioinformatics \n", + "24688855 PeerJ \n", + "24681267 J. Mol. Biol. \n", + "24677618 Hum. Mutat. \n", + "24675810 PLoS Comput. Biol. \n", + "24672471 Front Neuroinform \n", + "24667828 PLoS ONE \n", + "24658388 J Neural Eng \n", + "24657354 Neuroimage \n", + "24653694 Front Neuroinform \n", + "24647222 PLoS ONE \n", + "24627804 F1000Res \n", + "24618470 Bioinformatics \n", + "24602450 Algorithms Mol Biol \n", + "24588150 J Chem Phys \n", + "24586045 Mol. Biol. Evol. \n", + "24574113 Bioinformatics \n", + "24567544 Bioinformatics \n", + "24564867 BMC Syst Biol \n", + "24564732 BMC Bioinformatics \n", + "24564706 BMC Bioinformatics \n", + "24564637 BMC Genomics \n", + "24564427 BMC Genomics \n", + "\n", + " Url \n", + "26357045 https://github.com/BioprocessdesignLab/COSMOS \n", + "25601296 \n", + "25558360 https://github.com/seantuck12/MODISTools \n", + "25553811 https://github.com/Junfang/AKSmooth \n", + "25549775 http://archtk.github.com \n", + "25543048 \n", + "25540185 \n", + "25527832 \n", + "25526884 \n", + "25524895 \n", + "25521965 \n", + "25520192 https://github.com/ppgardne/RMfam \n", + "25514851 https://github.com/LUMC/kPAL \n", + "25505094 \n", + "25505087 \n", + "25505086 \n", + "25504847 \n", + "25481009 \n", + "25481007 \n", + "25480375 \n", + "25474353 https://github.com/CompEvol/sampled-ancestors \n", + "25461763 https://github.com/hitbio/PERGA \n", + "25452688 https://github.com/jiantao/Tangram \n", + "25435543 https://github.com/shengqh/RCPA.Tools/releases \n", + "25431162 \n", + "25428347 https://github.com/diazlab/HiTSelect \n", + "25422674 http://katholt.github.io/srst2/ \n", + "25414364 \n", + "25414349 github.com/sanger-pathogens/Gubbins \n", + "25410596 http://github.com/marbl/harvest \n", + "... ... \n", + "24728855 \n", + "24727652 https://github.com/tknijnen/msr/ \n", + "24715980 \n", + "24707447 \n", + "24703969 https://github.com/slzhao/QC3 \n", + "24700534 https://github.com/statisticalbiotechnology/No... \n", + "24695491 github.com/0asa/TTree-source \n", + "24695406 \n", + "24688855 https://github.com/jensengroup/fragbuilder/ \n", + "24681267 https://github.com/rcsb/symmetry \n", + "24677618 https://github.com/charite/jannovar \n", + "24675810 https://github.com/armintoepfer/haploclique \n", + "24672471 https://github.com/wanderine/BROCCOLI/ \n", + "24667828 https://github.com/LibourelLab/BiofloSoftware \n", + "24658388 \n", + "24657354 https://github.com/pipitone/MAGeTbrain \n", + "24653694 github.com/SCoT-dev/SCoT \n", + "24647222 http://github.com/gedankenstuecke/snpr \n", + "24627804 \n", + "24618470 \n", + "24602450 \n", + "24588150 https://github.com/lbf-ijs/DiffusiveDynamics \n", + "24586045 https://github.com/bioprojects/orderedPainting \n", + "24574113 \n", + "24567544 \n", + "24564867 \n", + "24564732 \n", + "24564706 \n", + "24564637 \n", + "24564427 \n", + "\n", + "[200 rows x 6 columns]" + ] + }, + "execution_count": 81, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "df.head(200)" ] }, { - "cell_type": "code", - "execution_count": null, + "cell_type": "markdown", "metadata": { "collapsed": true }, - "outputs": [], "source": [ - "github_regexp = r\"\"\"(?i)(https?://[.]*github[.]*)\"\"\"" + "Quality control: see for how many urls the extraction of a github project has worked" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 82, "metadata": { - "collapsed": true + "collapsed": false }, - "outputs": [], - "source": [] + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "15\n", + "116\n" + ] + } + ], + "source": [ + "print no_project_from_url\n", + "print project_from_url" + ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 83, "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "403\n", + "Entries without url: 0.000000\n", + "Entries with url: 0.000000\n", + "Of those, urls with github project: 0.000000\n" + ] + } + ], + "source": [ + "total_rows = len(df.index)+1\n", + "print total_rows\n", + "\n", + "percent_with_url = (no_project_from_url+project_from_url)/total_rows*100.0\n", + "percent_no_url = except_no/total_rows*100.0\n", + "urls_with_github = project_from_url/(project_from_url+no_project_from_url)*100.0\n", + "\n", + "print \"Entries without url: %f\" % percent_no_url\n", + "print \"Entries with url: %f\" % percent_with_url\n", + "print \"Of those, urls with github project: %f\" % urls_with_github\n" + ] + }, + { + "cell_type": "code", + "execution_count": 84, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "https://github.com/BioprocessdesignLab/COSMOS\n" + ] + } + ], "source": [ "test = str(df.iat[0,5])\n", "print test" @@ -481,11 +1406,19 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 85, "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "http://archtk.github.com\n" + ] + } + ], "source": [ "test2 = str(df.iat[4,5])\n", "print test2" @@ -493,29 +1426,51 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 86, "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "ParseResult(scheme='https', netloc='github.com', path='/BioprocessdesignLab/COSMOS', params='', query='', fragment='')" + ] + }, + "execution_count": 86, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "urlparse(test)\n" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 87, "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "ParseResult(scheme='http', netloc='archtk.github.com', path='', params='', query='', fragment='')" + ] + }, + "execution_count": 87, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "urlparse(test2)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 88, "metadata": { "collapsed": false }, @@ -526,22 +1481,41 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 89, "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "/BioprosessdesignLab/COSMOS\n" + ] + } + ], "source": [ "print(gurl.path)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 90, "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "0" + ] + }, + "execution_count": 90, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "test.find(\"https://github.com/\")\n", "\n" @@ -558,7 +1532,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 91, "metadata": { "collapsed": false }, @@ -571,11 +1545,19 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 92, "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Whisper is a file-based time-series database format for Graphite.\n" + ] + } + ], "source": [ "whisper = g.get_repo(\"graphite-project/whisper\")\n", "print whisper.description" @@ -583,11 +1565,19 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 93, "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Computation of Sensitivities in Model ODE Systems\n" + ] + } + ], "source": [ "cosmos = g.get_repo(\"BioprocessdesignLab/COSMOS\")\n", "print cosmos.description" @@ -595,11 +1585,29 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 94, "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "ename": "UnknownObjectException", + "evalue": "404 {u'documentation_url': u'https://developer.github.com/v3', u'message': u'Not Found'}", + "output_type": "error", + "traceback": [ + "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[1;31mUnknownObjectException\u001b[0m Traceback (most recent call last)", + "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m()\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[0marchtk\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mg\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_repo\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"archtk\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 2\u001b[1;33m \u001b[1;32mprint\u001b[0m \u001b[0marchtk\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdescription\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m", + "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/Repository.pyc\u001b[0m in \u001b[0;36mdescription\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 185\u001b[0m \u001b[1;33m:\u001b[0m\u001b[0mtype\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mstring\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 186\u001b[0m \"\"\"\n\u001b[1;32m--> 187\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_completeIfNotSet\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_description\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 188\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_description\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvalue\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 189\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/GithubObject.pyc\u001b[0m in \u001b[0;36m_completeIfNotSet\u001b[1;34m(self, value)\u001b[0m\n\u001b[0;32m 226\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_completeIfNotSet\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 227\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mvalue\u001b[0m \u001b[1;32mis\u001b[0m \u001b[0mNotSet\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 228\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_completeIfNeeded\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 229\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 230\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_completeIfNeeded\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/GithubObject.pyc\u001b[0m in \u001b[0;36m_completeIfNeeded\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 230\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_completeIfNeeded\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 231\u001b[0m \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__completed\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 232\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__complete\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 233\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 234\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m__complete\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/GithubObject.pyc\u001b[0m in \u001b[0;36m__complete\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 235\u001b[0m headers, data = self._requester.requestJsonAndCheck(\n\u001b[0;32m 236\u001b[0m \u001b[1;34m\"GET\"\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 237\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_url\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvalue\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 238\u001b[0m )\n\u001b[0;32m 239\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_storeAndUseAttributes\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mheaders\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/Requester.pyc\u001b[0m in \u001b[0;36mrequestJsonAndCheck\u001b[1;34m(self, verb, url, parameters, headers, input, cnx)\u001b[0m\n\u001b[0;32m 169\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 170\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mrequestJsonAndCheck\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mverb\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mheaders\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minput\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcnx\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 171\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__check\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrequestJson\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mverb\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mheaders\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minput\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcnx\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 172\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 173\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mrequestMultipartAndCheck\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mverb\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mheaders\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minput\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/Requester.pyc\u001b[0m in \u001b[0;36m__check\u001b[1;34m(self, status, responseHeaders, output)\u001b[0m\n\u001b[0;32m 177\u001b[0m \u001b[0moutput\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__structuredFromJson\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0moutput\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 178\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mstatus\u001b[0m \u001b[1;33m>=\u001b[0m \u001b[1;36m400\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 179\u001b[1;33m \u001b[1;32mraise\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__createException\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mstatus\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mresponseHeaders\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0moutput\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 180\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mresponseHeaders\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0moutput\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 181\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;31mUnknownObjectException\u001b[0m: 404 {u'documentation_url': u'https://developer.github.com/v3', u'message': u'Not Found'}" + ] + } + ], "source": [ "archtk = g.get_repo(\"archtk\")\n", "print archtk.description" From 608566c455dd084cc51e5bb5cc04f02507b07321 Mon Sep 17 00:00:00 2001 From: Melanie I Stefan Date: Thu, 14 Apr 2016 10:35:55 +0100 Subject: [PATCH 19/21] (and 89% of abstracts with have a github url) --- src/find_github_repo.ipynb | 46 ++++---------------------------------- 1 file changed, 4 insertions(+), 42 deletions(-) diff --git a/src/find_github_repo.ipynb b/src/find_github_repo.ipynb index 13c40d3..3294cc5 100644 --- a/src/find_github_repo.ipynb +++ b/src/find_github_repo.ipynb @@ -1355,7 +1355,7 @@ }, { "cell_type": "code", - "execution_count": 83, + "execution_count": 96, "metadata": { "collapsed": false }, @@ -1364,24 +1364,16 @@ "name": "stdout", "output_type": "stream", "text": [ - "403\n", - "Entries without url: 0.000000\n", - "Entries with url: 0.000000\n", - "Of those, urls with github project: 0.000000\n" + "28.7841191067\n" ] } ], "source": [ "total_rows = len(df.index)+1\n", - "print total_rows\n", "\n", - "percent_with_url = (no_project_from_url+project_from_url)/total_rows*100.0\n", - "percent_no_url = except_no/total_rows*100.0\n", - "urls_with_github = project_from_url/(project_from_url+no_project_from_url)*100.0\n", + "print project_from_url*100.0/total_rows\n", "\n", - "print \"Entries without url: %f\" % percent_no_url\n", - "print \"Entries with url: %f\" % percent_with_url\n", - "print \"Of those, urls with github project: %f\" % urls_with_github\n" + "print project_from_url*100.0/(total)" ] }, { @@ -1582,36 +1574,6 @@ "cosmos = g.get_repo(\"BioprocessdesignLab/COSMOS\")\n", "print cosmos.description" ] - }, - { - "cell_type": "code", - "execution_count": 94, - "metadata": { - "collapsed": false - }, - "outputs": [ - { - "ename": "UnknownObjectException", - "evalue": "404 {u'documentation_url': u'https://developer.github.com/v3', u'message': u'Not Found'}", - "output_type": "error", - "traceback": [ - "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[1;31mUnknownObjectException\u001b[0m Traceback (most recent call last)", - "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m()\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[0marchtk\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mg\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_repo\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"archtk\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 2\u001b[1;33m \u001b[1;32mprint\u001b[0m \u001b[0marchtk\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdescription\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m", - "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/Repository.pyc\u001b[0m in \u001b[0;36mdescription\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 185\u001b[0m \u001b[1;33m:\u001b[0m\u001b[0mtype\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mstring\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 186\u001b[0m \"\"\"\n\u001b[1;32m--> 187\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_completeIfNotSet\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_description\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 188\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_description\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvalue\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 189\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/GithubObject.pyc\u001b[0m in \u001b[0;36m_completeIfNotSet\u001b[1;34m(self, value)\u001b[0m\n\u001b[0;32m 226\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_completeIfNotSet\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 227\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mvalue\u001b[0m \u001b[1;32mis\u001b[0m \u001b[0mNotSet\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 228\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_completeIfNeeded\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 229\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 230\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_completeIfNeeded\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/GithubObject.pyc\u001b[0m in \u001b[0;36m_completeIfNeeded\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 230\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_completeIfNeeded\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 231\u001b[0m \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__completed\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 232\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__complete\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 233\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 234\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m__complete\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/GithubObject.pyc\u001b[0m in \u001b[0;36m__complete\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 235\u001b[0m headers, data = self._requester.requestJsonAndCheck(\n\u001b[0;32m 236\u001b[0m \u001b[1;34m\"GET\"\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 237\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_url\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvalue\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 238\u001b[0m )\n\u001b[0;32m 239\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_storeAndUseAttributes\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mheaders\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/Requester.pyc\u001b[0m in \u001b[0;36mrequestJsonAndCheck\u001b[1;34m(self, verb, url, parameters, headers, input, cnx)\u001b[0m\n\u001b[0;32m 169\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 170\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mrequestJsonAndCheck\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mverb\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mheaders\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minput\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcnx\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 171\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__check\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrequestJson\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mverb\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mheaders\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minput\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcnx\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 172\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 173\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mrequestMultipartAndCheck\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mverb\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mheaders\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minput\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/Requester.pyc\u001b[0m in \u001b[0;36m__check\u001b[1;34m(self, status, responseHeaders, output)\u001b[0m\n\u001b[0;32m 177\u001b[0m \u001b[0moutput\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__structuredFromJson\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0moutput\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 178\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mstatus\u001b[0m \u001b[1;33m>=\u001b[0m \u001b[1;36m400\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 179\u001b[1;33m \u001b[1;32mraise\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__createException\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mstatus\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mresponseHeaders\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0moutput\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 180\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mresponseHeaders\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0moutput\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 181\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;31mUnknownObjectException\u001b[0m: 404 {u'documentation_url': u'https://developer.github.com/v3', u'message': u'Not Found'}" - ] - } - ], - "source": [ - "archtk = g.get_repo(\"archtk\")\n", - "print archtk.description" - ] } ], "metadata": { From bf0e1f7e268e8d02f192fe73119ec0633a47fb6f Mon Sep 17 00:00:00 2001 From: Melanie I Stefan Date: Thu, 14 Apr 2016 10:40:19 +0100 Subject: [PATCH 20/21] start looking into how to get contributor info --- src/find_github_repo.ipynb | 159 +++++-------------------------------- 1 file changed, 21 insertions(+), 138 deletions(-) diff --git a/src/find_github_repo.ipynb b/src/find_github_repo.ipynb index 3294cc5..4f5650b 100644 --- a/src/find_github_repo.ipynb +++ b/src/find_github_repo.ipynb @@ -1355,7 +1355,7 @@ }, { "cell_type": "code", - "execution_count": 96, + "execution_count": 97, "metadata": { "collapsed": false }, @@ -1364,7 +1364,8 @@ "name": "stdout", "output_type": "stream", "text": [ - "28.7841191067\n" + "28.7841191067\n", + "88.5496183206\n" ] } ], @@ -1373,107 +1374,34 @@ "\n", "print project_from_url*100.0/total_rows\n", "\n", - "print project_from_url*100.0/(total)" + "print project_from_url*100.0/(project_from_url+no_project_from_url)" ] }, { - "cell_type": "code", - "execution_count": 84, - "metadata": { - "collapsed": false - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "https://github.com/BioprocessdesignLab/COSMOS\n" - ] - } - ], - "source": [ - "test = str(df.iat[0,5])\n", - "print test" - ] - }, - { - "cell_type": "code", - "execution_count": 85, - "metadata": { - "collapsed": false - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "http://archtk.github.com\n" - ] - } - ], - "source": [ - "test2 = str(df.iat[4,5])\n", - "print test2" - ] - }, - { - "cell_type": "code", - "execution_count": 86, - "metadata": { - "collapsed": false - }, - "outputs": [ - { - "data": { - "text/plain": [ - "ParseResult(scheme='https', netloc='github.com', path='/BioprocessdesignLab/COSMOS', params='', query='', fragment='')" - ] - }, - "execution_count": 86, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "urlparse(test)\n" - ] - }, - { - "cell_type": "code", - "execution_count": 87, + "cell_type": "markdown", "metadata": { "collapsed": false }, - "outputs": [ - { - "data": { - "text/plain": [ - "ParseResult(scheme='http', netloc='archtk.github.com', path='', params='', query='', fragment='')" - ] - }, - "execution_count": 87, - "metadata": {}, - "output_type": "execute_result" - } - ], "source": [ - "urlparse(test2)" + "access github api using pygithub\n" ] }, { "cell_type": "code", - "execution_count": 88, + "execution_count": 91, "metadata": { "collapsed": false }, "outputs": [], "source": [ - "gurl = urlparse(\"https://github.com/BioprosessdesignLab/COSMOS\")" + "from github import Github\n", + "\n", + "g = Github()" ] }, { "cell_type": "code", - "execution_count": 89, + "execution_count": 92, "metadata": { "collapsed": false }, @@ -1482,62 +1410,18 @@ "name": "stdout", "output_type": "stream", "text": [ - "/BioprosessdesignLab/COSMOS\n" + "Whisper is a file-based time-series database format for Graphite.\n" ] } ], "source": [ - "print(gurl.path)" - ] - }, - { - "cell_type": "code", - "execution_count": 90, - "metadata": { - "collapsed": false - }, - "outputs": [ - { - "data": { - "text/plain": [ - "0" - ] - }, - "execution_count": 90, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "test.find(\"https://github.com/\")\n", - "\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "collapsed": false - }, - "source": [ - "access github api using pygithub\n" - ] - }, - { - "cell_type": "code", - "execution_count": 91, - "metadata": { - "collapsed": false - }, - "outputs": [], - "source": [ - "from github import Github\n", - "\n", - "g = Github()" + "whisper = g.get_repo(\"graphite-project/whisper\")\n", + "print whisper.description" ] }, { "cell_type": "code", - "execution_count": 92, + "execution_count": 93, "metadata": { "collapsed": false }, @@ -1546,18 +1430,18 @@ "name": "stdout", "output_type": "stream", "text": [ - "Whisper is a file-based time-series database format for Graphite.\n" + "Computation of Sensitivities in Model ODE Systems\n" ] } ], "source": [ - "whisper = g.get_repo(\"graphite-project/whisper\")\n", - "print whisper.description" + "cosmos = g.get_repo(\"BioprocessdesignLab/COSMOS\")\n", + "print cosmos.description" ] }, { "cell_type": "code", - "execution_count": 93, + "execution_count": 98, "metadata": { "collapsed": false }, @@ -1566,13 +1450,12 @@ "name": "stdout", "output_type": "stream", "text": [ - "Computation of Sensitivities in Model ODE Systems\n" + ">\n" ] } ], "source": [ - "cosmos = g.get_repo(\"BioprocessdesignLab/COSMOS\")\n", - "print cosmos.description" + "print cosmos." ] } ], From f811aa06b66e143ba55c9734ca0f256f75e15c93 Mon Sep 17 00:00:00 2001 From: Melanie I Stefan Date: Tue, 3 May 2016 14:11:02 +0100 Subject: [PATCH 21/21] OK, I can get contributor names from github repos. Exceeding rate limit, but that can be fixed --- src/find_github_repo.ipynb | 117 +++++++++++++++++++++++++------------ 1 file changed, 80 insertions(+), 37 deletions(-) diff --git a/src/find_github_repo.ipynb b/src/find_github_repo.ipynb index 4f5650b..e64cf41 100644 --- a/src/find_github_repo.ipynb +++ b/src/find_github_repo.ipynb @@ -24,7 +24,7 @@ }, { "cell_type": "code", - "execution_count": 71, + "execution_count": 1, "metadata": { "collapsed": false }, @@ -35,7 +35,7 @@ "['github_pubs.xml', 'README.md']" ] }, - "execution_count": 71, + "execution_count": 1, "metadata": {}, "output_type": "execute_result" } @@ -55,7 +55,7 @@ }, { "cell_type": "code", - "execution_count": 72, + "execution_count": 2, "metadata": { "collapsed": true }, @@ -74,7 +74,7 @@ }, { "cell_type": "code", - "execution_count": 73, + "execution_count": 3, "metadata": { "collapsed": true }, @@ -106,7 +106,7 @@ }, { "cell_type": "code", - "execution_count": 74, + "execution_count": 4, "metadata": { "collapsed": true }, @@ -150,7 +150,7 @@ }, { "cell_type": "code", - "execution_count": 75, + "execution_count": 5, "metadata": { "collapsed": false, "scrolled": true @@ -245,7 +245,7 @@ "25549775 Ann Biomed Eng " ] }, - "execution_count": 75, + "execution_count": 5, "metadata": {}, "output_type": "execute_result" } @@ -274,7 +274,7 @@ }, { "cell_type": "code", - "execution_count": 76, + "execution_count": 6, "metadata": { "collapsed": false }, @@ -282,16 +282,16 @@ { "data": { "text/plain": [ - "'Stability and sensitivity analyses of biological systems require the ad hocwriting of computer code, which is highly dependent on the particular model and burdensome for large systems. We propose a very accurate strategy to overcome this challenge. Its core concept is the conversion of the model into the format of biochemical systems theory (BST), which greatly facilitates the computation of sensitivities. First, the steady state of interest is determined by integrating the model equations toward the steady state and then using a Newton-Raphson method to fine-tune the result. The second step of conversion into the BST format requires several instances of numerical differentiation. The accuracy of this task is ensured by the use of a complex-variable Taylor scheme for all differentiation steps. The proposed strategy is implemented in a new software program, COSMOS, which automates the stability and sensitivity analysis of essentially arbitrary ODE models in a quick, yet highly accurate manner. The methods underlying the process are theoretically analyzed and illustrated with four representative examples: a simple metabolic reaction model; a model of aspartate-derived amino acid biosynthesis; a TCA-cycle model; and a modified TCA-cycle model. COSMOS has been deposited to https://github.com/BioprocessdesignLab/COSMOS.'" + "\"Remotely sensed data - available at medium to high resolution across global spatial and temporal scales - are a valuable resource for ecologists. In particular, products from NASA's MODerate-resolution Imaging Spectroradiometer (MODIS), providing twice-daily global coverage, have been widely used for ecological applications. We present MODISTools, an R package designed to improve the accessing, downloading, and processing of remotely sensed MODIS data. MODISTools automates the process of data downloading and processing from any number of locations, time periods, and MODIS products. This automation reduces the risk of human error, and the researcher effort required compared to manual per-location downloads. The package will be particularly useful for ecological studies that include multiple sites, such as meta-analyses, observation networks, and globally distributed experiments. We give examples of the simple, reproducible workflow that MODISTools provides and of the checks that are carried out in the process. The end product is in a format that is amenable to statistical modeling. We analyzed the relationship between species richness across multiple higher taxa observed at 526 sites in temperate forests and vegetation indices, measures of aboveground net primary productivity. We downloaded MODIS derived vegetation index time series for each location where the species richness had been sampled, and summarized the data into three measures: maximum time-series value, temporal mean, and temporal variability. On average, species richness covaried positively with our vegetation index measures. Different higher taxa show different positive relationships with vegetation indices. Models had high R (2) values, suggesting higher taxon identity and a gradient of vegetation index together explain most of the variation in species richness in our data. MODISTools can be used on Windows, Mac, and Linux platforms, and is available from CRAN and GitHub (https://github.com/seantuck12/MODISTools).\"" ] }, - "execution_count": 76, + "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "df.iat[0,0]" + "df.iat[2,0]" ] }, { @@ -303,7 +303,7 @@ }, { "cell_type": "code", - "execution_count": 77, + "execution_count": 7, "metadata": { "collapsed": true }, @@ -322,7 +322,7 @@ }, { "cell_type": "code", - "execution_count": 78, + "execution_count": 8, "metadata": { "collapsed": false }, @@ -348,7 +348,7 @@ }, { "cell_type": "code", - "execution_count": 79, + "execution_count": 9, "metadata": { "collapsed": false }, @@ -399,7 +399,7 @@ }, { "cell_type": "code", - "execution_count": 80, + "execution_count": 10, "metadata": { "collapsed": false, "scrolled": true @@ -419,7 +419,7 @@ }, { "cell_type": "code", - "execution_count": 81, + "execution_count": 11, "metadata": { "collapsed": false }, @@ -1314,7 +1314,7 @@ "[200 rows x 6 columns]" ] }, - "execution_count": 81, + "execution_count": 11, "metadata": {}, "output_type": "execute_result" } @@ -1334,7 +1334,7 @@ }, { "cell_type": "code", - "execution_count": 82, + "execution_count": 12, "metadata": { "collapsed": false }, @@ -1355,7 +1355,7 @@ }, { "cell_type": "code", - "execution_count": 97, + "execution_count": 13, "metadata": { "collapsed": false }, @@ -1388,7 +1388,7 @@ }, { "cell_type": "code", - "execution_count": 91, + "execution_count": 14, "metadata": { "collapsed": false }, @@ -1401,7 +1401,7 @@ }, { "cell_type": "code", - "execution_count": 92, + "execution_count": 33, "metadata": { "collapsed": false }, @@ -1410,18 +1410,71 @@ "name": "stdout", "output_type": "stream", "text": [ - "Whisper is a file-based time-series database format for Graphite.\n" + "Whisper is a file-based time-series database format for Graphite.\n", + "Jeff Schroeder\n", + "Michael Leinartas\n", + "None\n", + "Bruno Renié\n", + "Jason Dixon\n", + "None\n", + "Fairiz 'Fi' Azizi\n", + "Valentin Haenel\n", + "Roman Koblov\n", + "Aman Gupta\n", + "None\n", + "Dieter Plaetinck\n", + "Denis Zhdanov\n", + "Dan Rowe\n", + "James Macdonell\n", + "Ben Meier\n", + "Denys Zhdanov\n", + "None\n", + "Dave Rawks\n", + "Elliot Murphy\n", + "Jordan Sissel\n", + "y_uuki\n", + "Tim O'Brien\n", + "Amos Shapira\n", + "Daniel\n", + "Marc Abramowitz\n", + "Alex Jablonski\n", + "Alexander Akulov\n", + "Brian Hatfield\n", + "Chris Adams\n" + ] + }, + { + "ename": "GithubException", + "evalue": "403 {u'documentation_url': u'https://developer.github.com/v3/#rate-limiting', u'message': u\"API rate limit exceeded for 129.215.83.91. (But here's the good news: Authenticated requests get a higher rate limit. Check out the documentation for more details.)\"}", + "output_type": "error", + "traceback": [ + "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[1;31mGithubException\u001b[0m Traceback (most recent call last)", + "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m()\u001b[0m\n\u001b[0;32m 3\u001b[0m \u001b[0mwhisper_cont\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mwhisper\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_contributors\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mcontributor\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mwhisper_cont\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 5\u001b[1;33m \u001b[1;32mprint\u001b[0m \u001b[0mcontributor\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mname\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 6\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 7\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/NamedUser.pyc\u001b[0m in \u001b[0;36mname\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 215\u001b[0m \u001b[1;33m:\u001b[0m\u001b[0mtype\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mstring\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 216\u001b[0m \"\"\"\n\u001b[1;32m--> 217\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_completeIfNotSet\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_name\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 218\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_name\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvalue\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 219\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/GithubObject.pyc\u001b[0m in \u001b[0;36m_completeIfNotSet\u001b[1;34m(self, value)\u001b[0m\n\u001b[0;32m 226\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_completeIfNotSet\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 227\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mvalue\u001b[0m \u001b[1;32mis\u001b[0m \u001b[0mNotSet\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 228\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_completeIfNeeded\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 229\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 230\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_completeIfNeeded\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/GithubObject.pyc\u001b[0m in \u001b[0;36m_completeIfNeeded\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 230\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_completeIfNeeded\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 231\u001b[0m \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__completed\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 232\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__complete\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 233\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 234\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m__complete\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/GithubObject.pyc\u001b[0m in \u001b[0;36m__complete\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 235\u001b[0m headers, data = self._requester.requestJsonAndCheck(\n\u001b[0;32m 236\u001b[0m \u001b[1;34m\"GET\"\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 237\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_url\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvalue\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 238\u001b[0m )\n\u001b[0;32m 239\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_storeAndUseAttributes\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mheaders\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/Requester.pyc\u001b[0m in \u001b[0;36mrequestJsonAndCheck\u001b[1;34m(self, verb, url, parameters, headers, input, cnx)\u001b[0m\n\u001b[0;32m 169\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 170\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mrequestJsonAndCheck\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mverb\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mheaders\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minput\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcnx\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 171\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__check\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrequestJson\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mverb\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mheaders\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minput\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcnx\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 172\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 173\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mrequestMultipartAndCheck\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mverb\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mheaders\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minput\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32m/usr/local/lib/python2.7/dist-packages/github/Requester.pyc\u001b[0m in \u001b[0;36m__check\u001b[1;34m(self, status, responseHeaders, output)\u001b[0m\n\u001b[0;32m 177\u001b[0m \u001b[0moutput\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__structuredFromJson\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0moutput\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 178\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mstatus\u001b[0m \u001b[1;33m>=\u001b[0m \u001b[1;36m400\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 179\u001b[1;33m \u001b[1;32mraise\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__createException\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mstatus\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mresponseHeaders\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0moutput\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 180\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mresponseHeaders\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0moutput\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 181\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;31mGithubException\u001b[0m: 403 {u'documentation_url': u'https://developer.github.com/v3/#rate-limiting', u'message': u\"API rate limit exceeded for 129.215.83.91. (But here's the good news: Authenticated requests get a higher rate limit. Check out the documentation for more details.)\"}" ] } ], "source": [ "whisper = g.get_repo(\"graphite-project/whisper\")\n", - "print whisper.description" + "print whisper.description\n", + "whisper_cont = whisper.get_contributors()\n", + "for contributor in whisper_cont:\n", + " print contributor.name\n", + "\n", + "\n", + "\n" ] }, { "cell_type": "code", - "execution_count": 93, + "execution_count": 16, "metadata": { "collapsed": false }, @@ -1441,22 +1494,12 @@ }, { "cell_type": "code", - "execution_count": 98, + "execution_count": null, "metadata": { "collapsed": false }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - ">\n" - ] - } - ], - "source": [ - "print cosmos." - ] + "outputs": [], + "source": [] } ], "metadata": {