Merge branch 'dev'

CHANGELOG.txt

@@ -1,3 +1,6 @@
+v0.2.0 (2014-03-29)
+- Switch to DESeq
+- Renaming from TRAPL to READemption (yes, another name change)
 v0.1.9 (2014-02-17)
 - Fix isssue with path for paired-end reads
 - Fix lib name sorting for gene quanti overview

Makefile

@@ -27,4 +27,4 @@ readme_clean:
 	rm -f README.tex README.html README.rst
 
 pylint:
-	pylint bin/trapl trapllib/* tests/*
+	pylint bin/reademption reademptionlib/* tests/*

README.md

@@ -1,26 +1,25 @@
 About
 -----
 
-The RNA-Seq Analysis PipeLine (TRAPL) is - as the name implies - a
-pipeline for the computational evaluation of RNA-Seq data. It was
-originally developed at the IMIB/ZINF to process dRNA-Seq reads (as
-introduced by Sharma et al., Nature, 2010 originating from bacterial
-samples. Meanwhile is has been extended to process data generated in
-different experimental setups and originating from all domains of life
-and is under active development. The subcommands which are provided
-by command-line interface cover read processing and aligning, coverage
-plot generation, gene expression quantification as well as
-differential gene expression analysis. TRAPL was applied to analyze
-numerous data sets. In order to set up analyses quickly TRAPL follows
-the principal of "convention over configuration": Once the input files
-are copied into defined folders no further parameters have to be
-given. Still, TRAPL's behavior can be adapted to specific needs of the
-user.
+READemption is a pipeline for the computational evaluation of RNA-Seq
+data. It was originally developed at the IMIB/ZINF to process dRNA-Seq
+reads (as introduced by Sharma et al., Nature, 2010 originating from
+bacterial samples. Meanwhile is has been extended to process data
+generated in different experimental setups and originating from all
+domains of life and is under active development. The subcommands which
+are provided by command-line interface cover read processing and
+aligning, coverage plot generation, gene expression quantification as
+well as differential gene expression analysis. READemption was applied
+to analyze numerous data sets. In order to set up analyses quickly
+READemption follows the principal of "convention over configuration":
+Once the input files are copied into defined folders no further
+parameters have to be given. Still, READemption's behavior can be
+adapted to specific needs of the user.
 
 License
 -------
 
-[ICS](https://en.wikipedia.org/wiki/ISC_license) - see LICENSE.txt
+[ICSL](https://en.wikipedia.org/wiki/ISC_license) - see LICENSE.txt
 
 Development
 -----------

bin/trapl → bin/reademption

@@ -1,15 +1,15 @@
-#!/usr/bin/env python
+#!/usr/bin/env python3
 
 """RAPL - A RNA-seq Analysis PipeLine"""
 
 import argparse
-from trapllib.controller import Controller
+from reademptionlib.controller import Controller
 
 __author__ = "Konrad Foerstner <[email protected]>"
 __copyright__ = "2011-2013 by Konrad Foerstner <[email protected]>"
 __license__ = "ISC license"
 __email__ = "[email protected]"
-__version__ = "0.1.9"
+__version__ = "0.2.0"
 
 def main():
     parser = argparse.ArgumentParser()
@@ -178,7 +178,7 @@ def main():
         help="Comma separated list of condition in the same order as "
         "their corresponding libraries.")
     deseq_parser.add_argument(
-        "--no_replicates", "-r", default=False, action="store_true")
+        "--cooks_cutoff_off", "-k", default=False, action="store_true")
     deseq_parser.set_defaults(func=run_deseq)
 
     # Parameters for viz_align

docs/source/conf.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 #
-# TRAPL documentation build configuration file, created by
+# READemption documentation build configuration file, created by
 # sphinx-quickstart on Thu May  2 08:33:05 2013.
 #
 # This file is execfile()d with the current directory set to its containing dir.
@@ -40,8 +40,8 @@
 master_doc = 'index'
 
 # General information about the project.
-project = u'TRAPL'
-copyright = u'2013, Konrad U. Förstner'
+project = u'READemption'
+copyright = u'2014, Konrad U. Förstner'
 
 # The version info for the project you're documenting, acts as replacement for
 # |version| and |release|, also used in various other places throughout the
@@ -164,7 +164,7 @@
 #html_file_suffix = None
 
 # Output file base name for HTML help builder.
-htmlhelp_basename = 'TRAPLdoc'
+htmlhelp_basename = 'READdemptiondoc'
 
 
 # -- Options for LaTeX output --------------------------------------------------
@@ -183,8 +183,8 @@
 # Grouping the document tree into LaTeX files. List of tuples
 # (source start file, target name, title, author, documentclass [howto/manual]).
 latex_documents = [
-  ('index', 'TRAPL.tex', u'TRAPL Documentation',
-   u'Konrad Förstner', 'manual'),
+  ('index', 'READemption.tex', u'READemption Documentation',
+   u'Konrad U. Förstner', 'manual'),
 ]
 
 # The name of an image file (relative to this directory) to place at the top of
@@ -213,8 +213,8 @@
 # One entry per manual page. List of tuples
 # (source start file, name, description, authors, manual section).
 man_pages = [
-    ('index', 'rapl', u'TRAPL Documentation',
-     [u'Konrad Förstner'], 1)
+    ('index', 'rapl', u'READemption Documentation',
+     [u'Konrad U. Förstner'], 1)
 ]
 
 # If true, show URL addresses after external links.
@@ -227,8 +227,8 @@
 # (source start file, target name, title, author,
 #  dir menu entry, description, category)
 texinfo_documents = [
-  ('index', 'TRAPL', u'TRAPL Documentation',
-   u'Konrad Förstner', 'TRAPL', 'One line description of project.',
+  ('index', 'READemption', u'READemption Documentation',
+   u'Konrad U. Förstner', 'READemption', 'One line description of project.',
    'Miscellaneous'),
 ]
 

docs/source/example_analysis.rst

@@ -9,7 +9,7 @@ Generating a project
 
 Creating a new project::
 
-  $ trapl create my_rna_seq_analysis
+  $ reademption create my_rna_seq_analysis
   Created folder "my_rna_seq_analysis" and required subfolders.
   Please copy read files into folder "my_rna_seq_analysis/input/reads" and reference sequences files into folder "my_rna_seq_analysis/input/reference_sequences".
 

docs/source/index.rst

@@ -1,5 +1,5 @@
-TRAPL - The RNA-Seq Analysis PipeLine 
-*************************************
+READemption - A RNA-Seq Analysis Pipeline 
+*****************************************
 Table of content
 ================
 
@@ -13,51 +13,50 @@ Table of content
    license
    versions	      
 
-TRAPL in a nutshell
-===================
+READemption in a nutshell
+=========================
 
-*The RNA-Seq Analysis PipeLine* (*TRAPL*) is - as the name implies - a
-pipeline for the computational evaluation of RNA-Seq data. It was
-originally developed at the `IMIB/ZINF
+*READemption* is a pipeline for the computational evaluation of
+RNA-Seq data. It was originally developed at the `IMIB/ZINF
 <http://www.imib-wuerzburg.de/>`_ to process dRNA-Seq reads (as
 introduced by Sharma *et al.*, Nature, 2010 (`Pubmed
 <http://www.ncbi.nlm.nih.gov/pubmed/20164839>`_)) originating from
 bacterial samples. Meanwhile is has been extended to process data
 generated in different experimental setups and originating from all
 domains of life and is under `active development
-<https://github.com/konrad/trapl>`_. The `subcommands
+<https://github.com/konrad/READemption>`_. The `subcommands
 <subcommands.html>`_ which are provided by command-line interface
 cover read processing and aligning, coverage plot generation, gene
 expression quantification as well as differential gene expression
-analysis. TRAPL was applied to analyze numerous data sets. In order to
-set up analyses quickly TRAPL follows the principal of *convention
+analysis. READemption was applied to analyze numerous data sets. In order to
+set up analyses quickly READemption follows the principal of *convention
 over configuration*: Once the input files are copied into defined
-folders no further parameters have to be given. Still, TRAPL's
+folders no further parameters have to be given. Still, READemption's
 behavior can be adapted to specific needs of the user. This tools is
-available as open source under the `ICS <https://en.wikipedia.org/wiki/ISC_license>`_
-open source license.
+available as open source under open source license `ICSL
+<https://en.wikipedia.org/wiki/ISC_license>`_ .
 
 Download
 ========
 
-TRAPL can be download from `its PyPI page
-<https://pypi.python.org/pypi/trapl/>`_. Please read the
+READemption can be download from `its PyPI page
+<https://pypi.python.org/pypi/READemption/>`_. Please read the
 `installation instructions <installation.html>`_.
 
 Source code
 ===========
 
-The source code of TRAPL can be found at https://github.com/konrad/trapl.
+The source code of READemption can be found at https://github.com/konrad/READemption.
 
 Cite
 ====
 
-If you apply TRALP in you data analysis please cite the following
-reference: *The RNA-Seq Analysis PipeLine (TRAPL) – A tool for the
-computational analysis of deep-sequencing based transcriptome data*.
-Konrad U. Förstner, Jörg Vogel, Cynthia M. Sharma; (in preparation). A
-`pre-preprint version <http://biorxiv.org/content/early/2014/XXX>`_ of the
-manuscript is hosted at bioRxiv.
+If you apply READemption in you data analysis please cite the
+following reference: *READemption – A tool for the computational
+analysis of deep-sequencing-based transcriptome data*.
+Konrad U. Förstner, Jörg Vogel, Cynthia M. Sharma; (submitted). A
+`pre-preprint version <http://biorxiv.org/content/early/2014/XXX>`_ of
+the manuscript is hosted at bioRxiv.
 
 Contact
 =======

docs/source/installation.rst

@@ -4,21 +4,21 @@ Installation
 Requirements
 ------------
 
-TRAPL was developed using Python 3.3 and for best performance the user
-is advised to run TRAPL with this version, too. Any other Python 3
-version should work as well. Also Python 2.7 can be used if the
-library `futures <https://pypi.python.org/pypi/futures>`_ is
-installed. In any case, the third party modules `pysam
-<https://code.google.com/p/pysam>`_ as well as `setuptool
-<https://pypi.python.org/pypi/setuptools>`_ and `pip
-<http://www.pip-installer.org>`_ in order to make the installation
-easy by retrieving are required. TRAPL uses the short read mapper
-`segemehl <http://www.bioinf.uni-leipzig.de/Software/segemehl/>`_ for
-the mapping and this software needs to be installed. The subcommand
+READemption was developed using Python 3.3 and for best performance
+the user is advised to run READemptionL with this or a higher versoin,
+too. Also Python 2.7 can be used if the library `futures
+<https://pypi.python.org/pypi/futures>`_ is installed. In any case,
+the third party modules `pysam <https://code.google.com/p/pysam>`_ as
+well as `setuptool <https://pypi.python.org/pypi/setuptools>`_ and
+`pip <http://www.pip-installer.org>`_ in order to make the
+installation easy by retrieving are required. READemption uses the
+short read mapper `segemehl
+<http://www.bioinf.uni-leipzig.de/Software/segemehl/>`_ for the
+mapping and this software needs to be installed. The subcommand
 `viz_align`, `viz_gene_quanti`, `viz_deseq` require the Python library
 `Matplotlib <http://matplotlib.org/>`_. `R
-<http://www.r-project.org/>`_ and the bioconductor package `DESeq
-<http://bioconductor.org/packages/release/bioc/html/DESeq.html>`_ are
+<http://www.r-project.org/>`_ and the bioconductor package `DESeq2
+<http://bioconductor.org/packages/release/bioc/html/DESeq2.html>`_ are
 necessary for the subcommand `deseq` which performs differential gene
 expression analysis. Don't worry - in the following the installation
 of all these requirements will be covered.
@@ -58,10 +58,10 @@ If PIP is not yet install you should get this, too.::
   curl https://raw.github.com/pypa/pip/master/contrib/get-pip.py > get-pip.py
   sudo python3.3 get-pip.py
 
-Now you can use PIP to install pysam and TRAPL::
+Now you can use PIP to install pysam and READemption::
 
   pip-3.3 install pysam
-  pip-3.3 install trapl
+  pip-3.3 install READemption
 
 Install make and ncurses dev library.::
 
@@ -91,9 +91,9 @@ and libxml2 which is required for the installation of some R-packages.::
 
  sudo apt-get install libxml2-dev
 
-Install DESeq in ::
+Install DESeq2 in ::
 
-  echo 'source("http://bioconductor.org/biocLite.R");biocLite("DESeq")' | Rscript -
+  echo 'source("http://bioconductor.org/biocLite.R");biocLite("DESeq2")' | Rscript -
 
 
 ..

docs/source/license.rst

@@ -1,7 +1,7 @@
 License
 =======
 
-TRAPL is open source software and available under the ISC license.
+READemption is open source software and available under the ISC license.
 
 Copyright (c) 2011-2014, Konrad Förstner <[email protected]>
 

docs/source/subcommands.rst

@@ -1,5 +1,5 @@
-TRAPL's subcommands
-===================
+READemption's subcommands
+=========================
 
 create
 ------

docs/source/versions.rst

@@ -1,2 +1,4 @@
 Versions/Change log
 ===================
+
+See https://github.com/konrad/READemption/blob/master/CHANGELOG.txt

trapllib/controller.py → reademptionlib/controller.py

@@ -3,21 +3,21 @@
 import sys
 import json
 import pysam
-from trapllib.bammerger import BamMerger
-from trapllib.coveragecalculator import CoverageCalculator
-from trapllib.deseq import DESeqRunner
-from trapllib.fasta import FastaParser
-from trapllib.genewisequanti import GeneWiseQuantification, GeneWiseOverview
-from trapllib.paths import Paths
-from trapllib.projectcreator import ProjectCreator
-from trapllib.rawstatdata import RawStatDataWriter, RawStatDataReader
-from trapllib.readaligner import ReadAligner
-from trapllib.readalignerstats import ReadAlignerStats
-from trapllib.readrealigner import ReadRealigner
-from trapllib.readalignerstatstable import ReadAlignerStatsTable
-from trapllib.readprocessor import ReadProcessor
-from trapllib.sambamconverter import SamToBamConverter
-from trapllib.wiggle import WiggleWriter
+from reademptionlib.bammerger import BamMerger
+from reademptionlib.coveragecalculator import CoverageCalculator
+from reademptionlib.deseq import DESeqRunner
+from reademptionlib.fasta import FastaParser
+from reademptionlib.genewisequanti import GeneWiseQuantification, GeneWiseOverview
+from reademptionlib.paths import Paths
+from reademptionlib.projectcreator import ProjectCreator
+from reademptionlib.rawstatdata import RawStatDataWriter, RawStatDataReader
+from reademptionlib.readaligner import ReadAligner
+from reademptionlib.readalignerstats import ReadAlignerStats
+from reademptionlib.readrealigner import ReadRealigner
+from reademptionlib.readalignerstatstable import ReadAlignerStatsTable
+from reademptionlib.readprocessor import ReadProcessor
+from reademptionlib.sambamconverter import SamToBamConverter
+from reademptionlib.wiggle import WiggleWriter
 
 class Controller(object):
 
@@ -627,7 +627,7 @@ def compare_with_deseq(self):
             self._paths.gene_wise_quanti_combined_path, 
             self._paths.deseq_tmp_session_info_script,
             self._paths.deseq_session_info,
-            no_replicates=self._args.no_replicates)
+            self._args.cooks_cutoff_off)
         deseq_runner.create_deseq_script_file()
         deseq_runner.write_session_info_file()
         deseq_runner.run_deseq()
@@ -665,7 +665,7 @@ def _write_err_msg_and_quit(self, msg):
 
     def viz_align(self):
         """Generate plots based on the read processing and mapping"""
-        from trapllib.vizalign import AlignViz
+        from reademptionlib.vizalign import AlignViz
         align_viz = AlignViz(
             self._paths.get_lib_names_single_end(),
             self._paths.read_processing_stats_path,
@@ -678,7 +678,7 @@ def viz_align(self):
 
     def viz_gene_quanti(self):
         """Generate plots based on the gene-wise read countings"""
-        from trapllib.vizgenequanti import GeneQuantiViz
+        from reademptionlib.vizgenequanti import GeneQuantiViz
         gene_quanti_viz = GeneQuantiViz(
             self._paths.gene_wise_quanti_combined_path, 
             self._paths.get_lib_names_single_end())
@@ -690,7 +690,7 @@ def viz_gene_quanti(self):
 
     def viz_deseq(self):
         """Generate plots based on the DESeq analysis"""
-        from trapllib.vizdeseq import DESeqViz
+        from reademptionlib.vizdeseq import DESeqViz
         deseq_path_template = (
             self._paths.deseq_raw_folder + "/deseq_comp_%s_vs_%s.csv")
         deseq_viz = DESeqViz(self._paths.deseq_script_path, deseq_path_template)