Merge branch 'hotfix/1.2.1'

dputhier · Sep 16, 2020 · 5837b97 · 5837b97
2 parents b21465b + 08ccb66
commit 5837b97
Show file tree

Hide file tree

Showing 99 changed files with 258 additions and 455 deletions.
diff --git a/docs/_images/example_01.png b/docs/_images/example_01.png
diff --git a/docs/_images/example_01b.png b/docs/_images/example_01b.png
diff --git a/docs/_images/example_02.png b/docs/_images/example_02.png
diff --git a/docs/_images/example_05.png b/docs/_images/example_05.png
diff --git a/docs/_images/example_06.png b/docs/_images/example_06.png
diff --git a/docs/_images/example_06b.png b/docs/_images/example_06b.png
diff --git a/docs/_images/example_07.png b/docs/_images/example_07.png
diff --git a/docs/_images/example_08.png b/docs/_images/example_08.png
diff --git a/docs/_images/example_13.png b/docs/_images/example_13.png
diff --git a/docs/_sources/ologram.rst.txt b/docs/_sources/ologram.rst.txt
@@ -248,6 +248,9 @@ For a factor allowance of k and n final queried words, the matrix will be rebuil
 factor allowance is K in K*n words in step 1 where n is final queries nb of words.
 
 MODL and will discard combinations rarer than 1/10000 occurences to reduce computing times and will also reduce the abundance of all unique lines in the matrix to their square roots to reduce the emphasis on the most frequent elements.
+However, this can magnify the impact of the noise quadratically as well, and can be disabled when using the manual API.
+
+
 
 If you are passing a custom error function, it must have the signature error_function(X_true, X_rebuilt, code). X_true is the real data, X_rebuilt is the reconstruction to evaluate, and code is the encoded version which in our case is used to assess sparsity.  All are NumPY matrices.
 
@@ -268,7 +271,8 @@ Here is an example:
     multiple_overlap_max_number_of_combinations = 3,    # How many words to find ?
     nb_threads = 1,
     step_1_factor_allowance = 2,                        # How many words to ask for in each step 1 rebuilding, as a multiplier of multiple_overlap_max_number_of_combinations
-    error_function = None)                              # Custom error function in step 2
+    error_function = None,                              # Custom error function in step 2
+    smother = True)                                     # Should the smothering (quadratic reduction of abundance) be applied ?
   interesting_combis = combi_miner.find_interesting_combinations()   
 
 
@@ -327,7 +331,7 @@ We recommend this representation. The tsv file can be edited before passing it t
 
 On the graph, S designated the total number of basepairs in which this combinations is encountered in the real data. Fold change gives the ratio with the number of basepairs in the shuffles, with the associated Negative Binomial p-value.
 
-.. command-output:: gtftk ologram_modl_treeify -i multiple_overlap_trivial_ologram_stats.tsv -o ./results/treeified.pdf -l ThisWasTheNameOfTheQuery
+.. command-output:: gtftk ologram_modl_treeify -i multiple_overlap_trivial_ologram_stats.tsv -o treeified.pdf -l ThisWasTheNameOfTheQuery
 	:shell:
 
 .. raw:: html
@@ -336,7 +340,7 @@ On the graph, S designated the total number of basepairs in which this combinati
   <table>
   <tr>
   <td valign="top">
-  <iframe src="_static/example_ologram_treeify.pdf" title="your_title" align="top" width="500" height="620" width="50%" frameborder="0" scrolling="auto" target="Message">
+  <iframe src="_static/treeified.pdf" title="your_title" align="top" width="500" height="620" width="50%" frameborder="0" scrolling="auto" target="Message">
   </iframe>
   </td>
   </tr>

diff --git a/docs/_static/documentation_options.js b/docs/_static/documentation_options.js
@@ -1,6 +1,6 @@
 var DOCUMENTATION_OPTIONS = {
     URL_ROOT: document.getElementById("documentation_options").getAttribute('data-url_root'),
-    VERSION: '1.2.0',
+    VERSION: '1.2.1',
     LANGUAGE: 'en',
     COLLAPSE_INDEX: false,
     BUILDER: 'html',

diff --git a/docs/_static/example_01.png b/docs/_static/example_01.png
diff --git a/docs/_static/example_01b.png b/docs/_static/example_01b.png
diff --git a/docs/_static/example_02.png b/docs/_static/example_02.png
diff --git a/docs/_static/example_05.png b/docs/_static/example_05.png
diff --git a/docs/_static/example_06.png b/docs/_static/example_06.png
diff --git a/docs/_static/example_06b.png b/docs/_static/example_06b.png
diff --git a/docs/_static/example_07.png b/docs/_static/example_07.png
diff --git a/docs/_static/example_08.png b/docs/_static/example_08.png
diff --git a/docs/_static/example_13.png b/docs/_static/example_13.png
diff --git a/docs/_static/example_pa_01.pdf b/docs/_static/example_pa_01.pdf
diff --git a/docs/_static/example_pa_02.pdf b/docs/_static/example_pa_02.pdf
diff --git a/docs/_static/example_pa_03.pdf b/docs/_static/example_pa_03.pdf
diff --git a/docs/_static/example_pa_04.pdf b/docs/_static/example_pa_04.pdf
diff --git a/docs/_static/merge_ologram_stats_01.pdf b/docs/_static/merge_ologram_stats_01.pdf
diff --git a/docs/_static/pygments.css b/docs/_static/pygments.css
@@ -1,5 +1,10 @@
+pre { line-height: 125%; margin: 0; }
+td.linenos pre { color: #000000; background-color: #f0f0f0; padding: 0 5px 0 5px; }
+span.linenos { color: #000000; background-color: #f0f0f0; padding: 0 5px 0 5px; }
+td.linenos pre.special { color: #000000; background-color: #ffffc0; padding: 0 5px 0 5px; }
+span.linenos.special { color: #000000; background-color: #ffffc0; padding: 0 5px 0 5px; }
 .highlight .hll { background-color: #ffffcc }
-.highlight  { background: #eeffcc; }
+.highlight { background: #eeffcc; }
 .highlight .c { color: #408090; font-style: italic } /* Comment */
 .highlight .err { border: 1px solid #FF0000 } /* Error */
 .highlight .k { color: #007020; font-weight: bold } /* Keyword */

diff --git a/docs/_static/treeified.pdf b/docs/_static/treeified.pdf
diff --git a/docs/about.html b/docs/about.html
@@ -16,7 +16,7 @@
         var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s);
       })();
     </script>
-    <title>Warning about supported GTF file formats &#8212; gtftk 1.2.0 documentation</title>
+    <title>Warning about supported GTF file formats &#8212; gtftk 1.2.1 documentation</title>
     <link rel="stylesheet" href="_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="_static/pygments.css" type="text/css" />
     <script id="documentation_options" data-url_root="./" src="_static/documentation_options.js"></script>
@@ -45,7 +45,7 @@ <h3>Navigation</h3>
         <li class="right" >
           <a href="index.html" title="Welcome to pygtftk documentation page"
              accesskey="P">previous</a> |</li>
-        <li class="nav-item nav-item-0"><a href="index.html">gtftk 1.2.0 documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="index.html">gtftk 1.2.1 documentation</a> &#187;</li>
         <li class="nav-item nav-item-this"><a href="">Warning about supported GTF file formats</a></li> 
       </ul>
     </div>  
@@ -64,8 +64,6 @@ <h1>Warning about supported GTF file formats<a class="headerlink" href="#warning
 <p>You can use the <strong>convert_ensembl</strong> subcommand to convert your non- (or old) ensembl format to current ensembl format.</p>
 <p>Below an example in which we first select only exon features then use <strong>convert_ensembl</strong> to re-generate gene and transcript features using <strong>convert_ensembl</strong> .</p>
 <div class="highlight-text notranslate"><div class="highlight"><pre><span></span>$ gtftk get_example | gtftk select_by_key -k feature  -v exon | head -n 10
- |-- 10:40-INFO : Checking configuration file.
- |-- 10:40-INFO : Checking configuration file.
 chr1	gtftk	exon	125	138	.	+	.	gene_id &quot;G0001&quot;; transcript_id &quot;G0001T002&quot;; exon_id &quot;G0001T002E001&quot;;
 chr1	gtftk	exon	125	138	.	+	.	gene_id &quot;G0001&quot;; transcript_id &quot;G0001T001&quot;; exon_id &quot;G0001T001E001&quot;;
 chr1	gtftk	exon	180	189	.	+	.	gene_id &quot;G0002&quot;; transcript_id &quot;G0002T001&quot;; exon_id &quot;G0002T001E001&quot;;
@@ -79,9 +77,6 @@ <h1>Warning about supported GTF file formats<a class="headerlink" href="#warning
 </pre></div>
 </div>
 <div class="highlight-text notranslate"><div class="highlight"><pre><span></span>$ gtftk get_example | gtftk select_by_key -k feature  -v exon | gtftk  convert_ensembl | head -n 10
- |-- 10:40-INFO : Checking configuration file.
- |-- 10:40-INFO : Checking configuration file.
- |-- 10:40-INFO : Checking configuration file.
 chr1	gtftk	gene	125	138	.	+	.	gene_id &quot;G0001&quot;;
 chr1	gtftk	transcript	125	138	.	+	.	gene_id &quot;G0001&quot;; transcript_id &quot;G0001T002&quot;;
 chr1	gtftk	exon	125	138	.	+	.	gene_id &quot;G0001&quot;; transcript_id &quot;G0001T002&quot;; exon_id &quot;G0001T002E001&quot;;
@@ -96,7 +91,6 @@ <h1>Warning about supported GTF file formats<a class="headerlink" href="#warning
 </div>
 <p><strong>Arguments:</strong></p>
 <div class="highlight-text notranslate"><div class="highlight"><pre><span></span>$ gtftk convert_ensembl -h
- |-- 10:40-INFO : Checking configuration file.
   Usage: gtftk convert_ensembl [-i GTF] [-o GTF] [-n] [-h] [-V [verbosity]] [-D] [-C] [-K tmp_dir] [-A] [-L logger_file] [-W write_message_to_file]
 
   Description: 
@@ -145,8 +139,6 @@ <h2>Naming conventions<a class="headerlink" href="#naming-conventions" title="Pe
 <p>We will use the terms <strong>attribute or key</strong> for any descriptor found in the 9th column (<em>e.g.</em> transcript_id) and the term <strong>value</strong> for its associated string (e.g. “NM_334567”). The eight first columns of the GTF file (chrom/seqid, source, type, start, end, score, strand, frame) will be refered as <strong>basic attributes</strong>. In the example below, gene_id is the attribute and ‘G0001’ is the associated value.</p>
 </div>
 <div class="highlight-text notranslate"><div class="highlight"><pre><span></span>$ gtftk get_example| gtftk select_by_key -k feature -v gene| head -1
- |-- 10:40-INFO : Checking configuration file.
- |-- 10:40-INFO : Checking configuration file.
 chr1	gtftk	gene	125	138	.	+	.	gene_id &quot;G0001&quot;;
 </pre></div>
 </div>
@@ -210,13 +202,13 @@ <h3>Navigation</h3>
         <li class="right" >
           <a href="index.html" title="Welcome to pygtftk documentation page"
              >previous</a> |</li>
-        <li class="nav-item nav-item-0"><a href="index.html">gtftk 1.2.0 documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="index.html">gtftk 1.2.1 documentation</a> &#187;</li>
         <li class="nav-item nav-item-this"><a href="">Warning about supported GTF file formats</a></li> 
       </ul>
     </div>
     <div class="footer" role="contentinfo">
         &#169; Copyright 2018, F. Lopez and D. Puthier.
-      Last updated on Sep 10, 2020.
+      Last updated on Sep 16, 2020.
       Created using <a href="https://www.sphinx-doc.org/">Sphinx</a> 3.2.1.
     </div>
   </body>

diff --git a/docs/annotation.html b/docs/annotation.html
@@ -16,7 +16,7 @@
         var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s);
       })();
     </script>
-    <title>Commands from section ‘annotation’ &#8212; gtftk 1.2.0 documentation</title>
+    <title>Commands from section ‘annotation’ &#8212; gtftk 1.2.1 documentation</title>
     <link rel="stylesheet" href="_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="_static/pygments.css" type="text/css" />
     <script id="documentation_options" data-url_root="./" src="_static/documentation_options.js"></script>
@@ -45,7 +45,7 @@ <h3>Navigation</h3>
         <li class="right" >
           <a href="conversion.html" title="Commands from section ‘conversion’"
              accesskey="P">previous</a> |</li>
-        <li class="nav-item nav-item-0"><a href="index.html">gtftk 1.2.0 documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="index.html">gtftk 1.2.1 documentation</a> &#187;</li>
         <li class="nav-item nav-item-this"><a href="">Commands from section ‘annotation’</a></li> 
       </ul>
     </div>  
@@ -59,15 +59,12 @@ <h3>Navigation</h3>
 <h1>Commands from section ‘annotation’<a class="headerlink" href="#commands-from-section-annotation" title="Permalink to this headline">¶</a></h1>
 <p>In the example of this section we will need the following example files:</p>
 <div class="highlight-text notranslate"><div class="highlight"><pre><span></span>$ gtftk get_example -q -d simple -f &#39;*&#39;
- |-- 10:41-INFO : Checking configuration file.
 </pre></div>
 </div>
 <div class="highlight-text notranslate"><div class="highlight"><pre><span></span>$ gtftk get_example -q -d mini_real -f &#39;*&#39;
- |-- 10:41-INFO : Checking configuration file.
 </pre></div>
 </div>
 <div class="highlight-text notranslate"><div class="highlight"><pre><span></span>$ gtftk get_example -q -d hg38_chr1 -f &#39;*&#39;
- |-- 10:41-INFO : Checking configuration file.
 </pre></div>
 </div>
 <hr class="docutils" />
@@ -76,7 +73,6 @@ <h2>closest_genes<a class="headerlink" href="#closest-genes" title="Permalink to
 <p><strong>Description:</strong> Find the n closest genes for each transcript.</p>
 <p><strong>Example:</strong></p>
 <div class="highlight-text notranslate"><div class="highlight"><pre><span></span>$ gtftk closest_genes  -i simple.gtf -f
- |-- 10:41-INFO : Checking configuration file.
 genes	closest_genes	distances
 G0001	G0007	18
 G0002	G0010	4
@@ -92,7 +88,6 @@ <h2>closest_genes<a class="headerlink" href="#closest-genes" title="Permalink to
 </div>
 <p><strong>Arguments:</strong></p>
 <div class="highlight-text notranslate"><div class="highlight"><pre><span></span>$ gtftk closest_genes -h
- |-- 10:41-INFO : Checking configuration file.
   Usage: gtftk closest_genes [-i GTF] [-o GTF/TXT] [-r {tss,tts,gene}] [-nb nb_neighbors] [-t {tss,tts,gene}] [-s] [-S] [-f] [-H] [-k] [-id {gene_id,gene_name}] [-h] [-V [verbosity]] [-D] [-C] [-K tmp_dir] [-A] [-L logger_file] [-W write_message_to_file]
 
   Description: 
@@ -139,9 +134,6 @@ <h2>overlapping<a class="headerlink" href="#overlapping" title="Permalink to thi
 <p><strong>Description:</strong> Find transcripts whose body/TSS/TTS region extended in 5’ and 3’ (-u/-d) overlaps with any transcript from another gene. Strandness is not considered by default. Used –invert-match to find those that do not overlap. If –annotate-gtf is used, all lines of the input GTF file will be printed and a new key containing the list of overlapping transcripts will be added to the transcript features/lines (key will be ‘overlapping_*’ with * one of body/TSS/TTS). The –annotate-gtf and –invert-match arguments are mutually exclusive.</p>
 <p><strong>Example:</strong> Find transcript whose promoter overlap transcript from other genes.</p>
 <div class="highlight-text notranslate"><div class="highlight"><pre><span></span>$ gtftk overlapping -i simple.gtf -c simple.chromInfo -t promoter -u 10 -d 10 -a    | gtftk select_by_key -k feature -v transcript | gtftk tabulate -k transcript_id,overlap_promoter_u0.01k_d0.01k | head
- |-- 10:41-INFO : Checking configuration file.
- |-- 10:41-INFO : Checking configuration file.
- |-- 10:41-INFO : Checking configuration file.
 transcript_id	overlap_promoter_u0.01k_d0.01k
 G0001T002	G0007T001,G0007T002
 G0001T001	G0007T001,G0007T002
@@ -156,7 +148,6 @@ <h2>overlapping<a class="headerlink" href="#overlapping" title="Permalink to thi
 </div>
 <p><strong>Arguments:</strong></p>
 <div class="highlight-text notranslate"><div class="highlight"><pre><span></span>$ gtftk overlapping -h
- |-- 10:41-INFO : Checking configuration file.
   Usage: gtftk overlapping [-i GTF] [-o GTF] -c CHROMINFO [-u UPSTREAM] [-d DOWNSTREAM] [-t {transcript,promoter,tts}] [-s] [-S] [-n] [-a] [-k key_name] [-b] [-@] [-h] [-V [verbosity]] [-D] [-C] [-K tmp_dir] [-A] [-L logger_file] [-W write_message_to_file]
 
   Description: 
@@ -216,9 +207,6 @@ <h2>divergent<a class="headerlink" href="#divergent" title="Permalink to this he
 also provided as an additional key (dist_to_divergent).</p>
 <p><strong>Example:</strong> Flag divergent transcripts in the example dataset. Select them and produce a tabulated output.</p>
 <div class="highlight-text notranslate"><div class="highlight"><pre><span></span>$ gtftk divergent -i simple.gtf -c simple.chromInfo -u 10 -d 10| gtftk select_by_key -k feature -v transcript | gtftk tabulate -k transcript_id,divergent,dist_to_divergent | head  -n 7
- |-- 10:41-INFO : Checking configuration file.
- |-- 10:41-INFO : Checking configuration file.
- |-- 10:41-INFO : Checking configuration file.
 transcript_id	divergent	dist_to_divergent
 G0003T001	G0004T002	4
 G0004T002	G0003T001	4
@@ -227,7 +215,6 @@ <h2>divergent<a class="headerlink" href="#divergent" title="Permalink to this he
 </div>
 <p><strong>Arguments:</strong></p>
 <div class="highlight-text notranslate"><div class="highlight"><pre><span></span>$ gtftk divergent -h
- |-- 10:41-INFO : Checking configuration file.
   Usage: gtftk divergent [-i GTF] [-o GTF] -c CHROMINFO [-u UPSTREAM] [-d DOWNSTREAM] [-n] [-S] [-a key_name] [-h] [-V [verbosity]] [-D] [-C] [-K tmp_dir] [-A] [-L logger_file] [-W write_message_to_file]
 
   Description: 
@@ -282,9 +269,6 @@ <h2>convergent<a class="headerlink" href="#convergent" title="Permalink to this
 The tts to tts distance is also provided as an additional key (dist_to_convergent).</p>
 <p><strong>Example:</strong> Flag divergent transcripts in the example dataset. Select them and produce a tabulated output.</p>
 <div class="highlight-text notranslate"><div class="highlight"><pre><span></span>$ gtftk convergent -i simple.gtf -c simple.chromInfo -u 25 -d 25| gtftk select_by_key -k feature -v transcript | gtftk tabulate -k transcript_id,convergent,dist_to_convergent| head -n 4
- |-- 10:41-INFO : Checking configuration file.
- |-- 10:41-INFO : Checking configuration file.
- |-- 10:41-INFO : Checking configuration file.
 transcript_id	convergent	dist_to_convergent
 G0002T001	G0008T001	21
 G0008T001	G0002T001	21
@@ -293,7 +277,6 @@ <h2>convergent<a class="headerlink" href="#convergent" title="Permalink to this
 </div>
 <p><strong>Arguments:</strong></p>
 <div class="highlight-text notranslate"><div class="highlight"><pre><span></span>$ gtftk convergent -h
- |-- 10:41-INFO : Checking configuration file.
   Usage: gtftk convergent [-i GTF] [-o GTF] -c CHROMINFO [-u UPSTREAM] [-d DOWNSTREAM] [-h] [-V [verbosity]] [-D] [-C] [-K tmp_dir] [-A] [-L logger_file] [-W write_message_to_file]
 
   Description: 
@@ -336,9 +319,6 @@ <h2>exon_sizes<a class="headerlink" href="#exon-sizes" title="Permalink to this
 <p><strong>Description:</strong> Add a new key to transcript features containing a comma-separated list of exon sizes.</p>
 <p><strong>Example:</strong></p>
 <div class="highlight-text notranslate"><div class="highlight"><pre><span></span>$ gtftk exon_sizes -i simple.gtf | gtftk select_by_key -t | gtftk tabulate -k transcript_id,exon_sizes
- |-- 10:41-INFO : Checking configuration file.
- |-- 10:41-INFO : Checking configuration file.
- |-- 10:41-INFO : Checking configuration file.
 transcript_id	exon_sizes
 G0001T002	14
 G0001T001	14
@@ -359,7 +339,6 @@ <h2>exon_sizes<a class="headerlink" href="#exon-sizes" title="Permalink to this
 </div>
 <p><strong>Arguments:</strong></p>
 <div class="highlight-text notranslate"><div class="highlight"><pre><span></span>$ gtftk exon_sizes -h
- |-- 10:41-INFO : Checking configuration file.
   Usage: gtftk exon_sizes [-i GTF] [-o TXT] [-a key_name] [-h] [-V [verbosity]] [-D] [-C] [-K tmp_dir] [-A] [-L logger_file] [-W write_message_to_file]
 
   Description: 
@@ -390,9 +369,6 @@ <h2>intron_sizes<a class="headerlink" href="#intron-sizes" title="Permalink to t
 <p><strong>Description:</strong> Add a new key to transcript features containing a comma-separated list of intron sizes.</p>
 <p><strong>Example:</strong></p>
 <div class="highlight-text notranslate"><div class="highlight"><pre><span></span>$ gtftk intron_sizes -i simple.gtf | gtftk select_by_key -t | gtftk tabulate -k transcript_id,intron_sizes
- |-- 10:41-INFO : Checking configuration file.
- |-- 10:41-INFO : Checking configuration file.
- |-- 10:41-INFO : Checking configuration file.
 transcript_id	intron_sizes
 G0001T002	0
 G0001T001	0
@@ -413,7 +389,6 @@ <h2>intron_sizes<a class="headerlink" href="#intron-sizes" title="Permalink to t
 </div>
 <p><strong>Arguments:</strong></p>
 <div class="highlight-text notranslate"><div class="highlight"><pre><span></span>$ gtftk intron_sizes -h
- |-- 10:41-INFO : Checking configuration file.
   Usage: gtftk intron_sizes [-i GTF] [-o GTF] [-a key_name] [-h] [-V [verbosity]] [-D] [-C] [-K tmp_dir] [-A] [-L logger_file] [-W write_message_to_file]
 
   Description: 
@@ -502,13 +477,13 @@ <h3>Navigation</h3>
         <li class="right" >
           <a href="conversion.html" title="Commands from section ‘conversion’"
              >previous</a> |</li>
-        <li class="nav-item nav-item-0"><a href="index.html">gtftk 1.2.0 documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="index.html">gtftk 1.2.1 documentation</a> &#187;</li>
         <li class="nav-item nav-item-this"><a href="">Commands from section ‘annotation’</a></li> 
       </ul>
     </div>
     <div class="footer" role="contentinfo">
         &#169; Copyright 2018, F. Lopez and D. Puthier.
-      Last updated on Sep 10, 2020.
+      Last updated on Sep 16, 2020.
       Created using <a href="https://www.sphinx-doc.org/">Sphinx</a> 3.2.1.
     </div>
   </body>