Repository 'deeptools_plot_correlation'
hg clone https://toolshed.g2.bx.psu.edu/repos/bgruening/deeptools_plot_correlation

Changeset 12:ed2767cdf4e8 (2017-03-31)
Previous changeset 11:cdc31a261f47 (2017-01-24) Next changeset 13:0e8cbe7d4ff4 (2017-03-31)
Commit message:
planemo upload for repository https://github.com/fidelram/deepTools/tree/master/galaxy/wrapper/ commit 09975f870c75347fba5c6777c9f3b442bdeeb289
modified:
deepTools_macros.xml
plotCorrelation.xml
test-data/bamCompare_result2.bw
test-data/bamCoverage_result1.bw
test-data/bamCoverage_result2.bw
test-data/bamCoverage_result6.bw
test-data/bamPEFragmentSize_histogram_result1.png
test-data/bigwigCompare_result1.bw
test-data/computeMatrixOperations.txt
test-data/computeMatrixOperations_result2.mat.gz
test-data/computeMatrix_result1.gz
test-data/computeMatrix_result2.gz
test-data/computeMatrix_result3.gz
test-data/correctGCBias_result1.bam
test-data/heatmapper_result1.png
test-data/heatmapper_result2.png
test-data/multiBamSummary_result1.npz
test-data/multiBamSummary_result2.npz
test-data/multiBigwigSummary_result1.npz
test-data/plotCorrelation_result1.png
test-data/plotCorrelation_result1.tabular
test-data/plotCorrelation_result2.png
test-data/plotCoverage_result1.png
test-data/plotEnrichment_output.png
test-data/plotFingerprint_quality_metrics.tabular
test-data/plotFingerprint_result1.png
test-data/plotFingerprint_result2.png
test-data/profiler_result1.png
test-data/profiler_result2.png
test-data/profiler_result2.tabular
tool_dependencies.xml
added:
test-data/multiBamSummary_result2b.npz
b
diff -r cdc31a261f47 -r ed2767cdf4e8 deepTools_macros.xml
--- a/deepTools_macros.xml Tue Jan 24 04:57:11 2017 -0500
+++ b/deepTools_macros.xml Fri Mar 31 09:27:20 2017 -0400
[
@@ -1,5 +1,17 @@
 <macros>
 
+    <token name="@THREADS@">--numberOfProcessors "\${GALAXY_SLOTS:-4}"</token>
+    <token name="@WRAPPER_VERSION@">2.5.0</token>
+    <xml name="requirements">
+        <requirements>
+            <requirement type="package" version="2.7.10">python</requirement>
+            <requirement type="package" version="@WRAPPER_VERSION@">deeptools</requirement>
+            <yield />
+        </requirements>
+        <expand macro="stdio" />
+        <version_command>@BINARY@ --version</version_command>
+    </xml>
+
     <xml name="advancedOpt_scaffold">
         <conditional name="advancedOpt">
             <param name="showAdvancedOpt" type="select" label="Show advanced options" >
@@ -97,18 +109,6 @@
         </param>
     </xml>
 
-    <token name="@THREADS@">--numberOfProcessors "\${GALAXY_SLOTS:-4}"</token>
-    <token name="@WRAPPER_VERSION@">2.4.2</token>
-    <xml name="requirements">
-        <requirements>
-            <requirement type="package" version="2.7.10">python</requirement>
-            <requirement type="package" version="2.4.2">deeptools</requirement>
-            <yield />
-        </requirements>
-        <expand macro="stdio" />
-        <version_command>@BINARY@ --version</version_command>
-    </xml>
-
     <xml name="smoothLength">
         <param argument="--smoothLength" type="integer" value="" optional="True" min="1"
             label="Smooth values using the following length (in bases)"
@@ -181,10 +181,10 @@
     <xml name="fragLength">
         <param argument="--minFragmentLength" type="integer" optional="True" value="0" min="0"
             label="Minimum fragment length for inclusion."
-            help="A value greater than 0 will filter out ALL single-end reads. This is primarily useful in things like ATACseq, where one would like to look specifically at mono- or di-nucleosome fragments." />
+            help="This is primarily useful in things like ATACseq, where one would like to look specifically at mono- or di-nucleosome fragments." />
         <param argument="--maxFragmentLength" type="integer" optional="True" value="0" min="0"
             label="Maximum fragment length for inclusion."
-            help="As above, but the maximum length. A value of 0 (the default) is equivalent to no maximum." />
+            help="A value of 0 (the default) is equivalent to no maximum." />
     </xml>
 
     <xml name="read_processing_options">
@@ -324,9 +324,7 @@
 
     <xml name="scaleFactor">
         <param argument="--scaleFactor" type="float" value="1" label="Scaling factor"
-            help="When used in combination with --normalizeTo1x or
-                --normalizeUsingRPKM, the computed scaling factor will
-                be multiplied by the given scale factor." />
+            help="The computed scaling factor will be multiplied by this (default 1)." />
     </xml>
 
     <xml name="scaleFactors">
@@ -441,19 +439,22 @@
 <![CDATA[
         #set files=[]
         #set labels=[]
+        #import re
         #if $multibam_conditional.orderMatters == "No":
             #for $counter, $bamfile in enumerate($multibam_conditional.bamfiles):
+                #set identifier = re.sub('[^\.\s\w\-]', '_', str($bamfile.element_identifier))
                 ln -s "${bamfile}" "./${counter}.bam" &&
                 ln -s "${bamfile.metadata.bam_index}" "./${counter}.bam.bai" &&
                 #silent $files.append('%s.bam' % $counter)
-                #silent $labels.append("'%s'" % ($bamfile.display_name))
+                #silent $labels.append("'%s'" % identifier)
             #end for
         #else:
             #for $counter, $f in enumerate($multibam_conditional.multibam_repeats):
+                #set identifier = re.sub('[^\.\s\w\-]', '_', str($f.bamfiles.element_identifier))
                 ln -s "${f.bamfiles}" "./${counter}.bam" &&
                 ln -s "${f.bamfiles.metadata.bam_index}" "./${counter}.bam.bai" &&
                 #silent $files.append('%s.bam' % $counter)
-                #silent $labels.append("'%s'" % ($f.bamfiles.display_name))
+                #silent $labels.append("'%s'" % $identifier)
             #end for
         #end if
 ]]>
@@ -463,17 +464,20 @@
 <![CDATA[
         #set files=[]
         #set labels=[]
+        #import re
         #if $multibigwig_conditional.orderMatters == "No":
             #for $counter, $bigwig in enumerate($multibigwig_conditional.bigwigfiles):
+            #set identifier = re.sub('[^\.\s\w\-]', '_', str($bigwig.element_identifier))
                 ln -s "${bigwig}" "${counter}.bw" &&
                 #silent $files.append('%s.bw' % $counter)
-                #silent $labels.append("'%s'" % ($bigwig.display_name))
+                #silent $labels.append("'%s'" % $identifier)
             #end for
         #else:
             #for $counter, $f in enumerate($multibigwig_conditional.multibigwig_repeats):
+                #set identifier = re.sub('[^\.\s\w\-]', '_', str($f.bigwigfiles.element_identifier))
                 ln -s "${f.bigwigfiles}" "${counter}.bw" &&
                 #silent $files.append('%s.bw' % $counter)
-                #silent $labels.append("'%s'" % ($f.bigwigfiles.display_name))
+                #silent $labels.append("'%s'" % $identifier)
             #end for
         #end if
 ]]>
b
diff -r cdc31a261f47 -r ed2767cdf4e8 plotCorrelation.xml
--- a/plotCorrelation.xml Tue Jan 24 04:57:11 2017 -0500
+++ b/plotCorrelation.xml Fri Mar 31 09:27:20 2017 -0400
[
b'@@ -1,142 +1,142 @@\n-<tool id="deeptools_plot_correlation" name="plotCorrelation" version="@WRAPPER_VERSION@.0">\r\n-    <description>Create a heatmap or scatterplot of correlation scores between different samples </description>\r\n-    <macros>\r\n-        <token name="@BINARY@">plotCorrelation</token>\r\n-        <import>deepTools_macros.xml</import>\r\n-    </macros>\r\n-    <expand macro="requirements"/>\r\n-    <command>\r\n-<![CDATA[\r\n-        @BINARY@\r\n-            --corData "$corData"\r\n-            --plotFile "$outFileName"\r\n-            --corMethod "$corMethod"\r\n-            --whatToPlot "$plotting_type.whatToPlot"\r\n-            #if str($plotting_type.whatToPlot) == \'heatmap\':\r\n-                @HEATMAP_OPTIONS@\r\n-            #else:\r\n-                --plotTitle \'$plotting_type.plotTitle\'\r\n-            #end if\r\n-            $skipZeros\r\n-            --plotFileFormat "$outFileFormat"\r\n-            $removeOutliers\r\n-            #if $outFileCorMatrix:\r\n-                --outFileCorMatrix "$matrix"\r\n-            #end if\r\n-\r\n-]]>\r\n-    </command>\r\n-    <inputs>\r\n-        <param name="corData" format="deeptools_coverage_matrix" type="data" label="Matrix file from the multiBamSummary tool"/>\r\n-        <expand macro="corMethod" />\r\n-\r\n-        <conditional name="plotting_type" >\r\n-            <param argument="--whatToPlot" type="select" label="Plotting type">\r\n-                <option value="heatmap" selected="True">Heatmap</option>\r\n-                <option value="scatterplot">Scatterplot</option>\r\n-            </param>\r\n-            <when value="heatmap">\r\n-                <expand macro="heatmap_options" />\r\n-            </when>\r\n-            <when value="scatterplot">\r\n-                <expand macro="plotTitle" />\r\n-            </when>\r\n-        </conditional>\r\n-\r\n-        <expand macro="skipZeros" />\r\n-\r\n-        <expand macro="input_image_file_format" />\r\n-\r\n-        <param argument="--removeOutliers" type="boolean"\r\n-            truevalue="--removeOutliers" falsevalue="" label="Remove regions with very large counts"\r\n-            help="If set, bins with very large counts are removed. Bins\r\n-                with abnormally high reads counts artificially\r\n-                increase pearson correlation; that\'s why, by default,\r\n-                plotCorrelation tries to remove outliers using the median\r\n-                absolute deviation (MAD) method applying a threshold\r\n-                of 200 to only consider extremely large deviations\r\n-                from the median. ENCODE blacklist page (https://sites.\r\n-                google.com/site/anshulkundaje/projects/blacklists)\r\n-                contains useful information about regions with\r\n-                unusually high counts."/>\r\n-\r\n-        <param name="outFileCorMatrix" type="boolean" label="Save the matrix of values underlying the heatmap"/>\r\n-\r\n-    </inputs>\r\n-    <outputs>\r\n-        <expand macro="output_image_file_format_not_nested" />\r\n-        <data format="tabular" name="matrix" label="${tool.name} on ${on_string}: Correlation matrix">\r\n-            <filter>outFileCorMatrix is True</filter>\r\n-        </data>\r\n-    </outputs>\r\n-    <tests>\r\n-        <test>\r\n-            <param name="corData" value="multiBamSummary_result1.npz" ftype="deeptools_coverage_matrix" />\r\n-            <param name="outFileFormat" value="png" />\r\n-            <param name="outFileCorMatrix" value="True" />\r\n-            <output name="matrix" file="plotCorrelation_result1.tabular" ftype="tabular" />\r\n-            <output name="outFileName" file="plotCorrelation_result1.png" ftype="png" compare="sim_size" delta="300" />\r\n-        </test>\r\n-        <test>\r\n-            <param name="corData" value="multiBamSummary_result1.npz" ftype="deeptools_coverage_matrix" />\r\n-            <param name="outFileFormat" value="png" />\r\n-            <param name="whatToPlot" value="scatterplot" />\r\n-            <param name="removeOutliers" value="True" />\r\n-            <param name="plotTitle" value="Test Plot" />\r\n-        '..b'         with abnormally high reads counts artificially\n+                increase pearson correlation; that\'s why, by default,\n+                plotCorrelation tries to remove outliers using the median\n+                absolute deviation (MAD) method applying a threshold\n+                of 200 to only consider extremely large deviations\n+                from the median. ENCODE blacklist page (https://sites.\n+                google.com/site/anshulkundaje/projects/blacklists)\n+                contains useful information about regions with\n+                unusually high counts."/>\n+\n+        <param name="outFileCorMatrix" type="boolean" label="Save the matrix of values underlying the heatmap"/>\n+\n+    </inputs>\n+    <outputs>\n+        <expand macro="output_image_file_format_not_nested" />\n+        <data format="tabular" name="matrix" label="${tool.name} on ${on_string}: Correlation matrix">\n+            <filter>outFileCorMatrix is True</filter>\n+        </data>\n+    </outputs>\n+    <tests>\n+        <test>\n+            <param name="corData" value="multiBamSummary_result1.npz" ftype="deeptools_coverage_matrix" />\n+            <param name="outFileFormat" value="png" />\n+            <param name="outFileCorMatrix" value="True" />\n+            <output name="matrix" file="plotCorrelation_result1.tabular" ftype="tabular" />\n+            <output name="outFileName" file="plotCorrelation_result1.png" ftype="png" compare="sim_size" delta="300" />\n+        </test>\n+        <test>\n+            <param name="corData" value="multiBamSummary_result1.npz" ftype="deeptools_coverage_matrix" />\n+            <param name="outFileFormat" value="png" />\n+            <param name="whatToPlot" value="scatterplot" />\n+            <param name="removeOutliers" value="True" />\n+            <param name="plotTitle" value="Test Plot" />\n+            <output name="outFileName" file="plotCorrelation_result2.png" ftype="png" compare="sim_size" delta="300" />\n+        </test>\n+    </tests>\n+    <help>\n+<![CDATA[\n+What it does\n+------------\n+\n+This tools takes the default output of ``multiBamSummary`` or ``multiBigwigSummary``, and computes the pairwise correlation among samples.\n+Results can be visualized as **scatterplots** or as a **heatmap** of correlation coefficients (see below for examples).\n+\n+Theoretical Background\n+----------------------\n+\n+The result of the correlation computation is a **table of correlation coefficients** that indicates how "strong" the relationship between two samples is and it will consist of numbers between -1 and 1. (-1 indicates perfect anti-correlation, 1 perfect correlation.)\n+\n+We offer two different functions for the correlation computation: *Pearson* or *Spearman*.\n+\n+The *Pearson method* measures the **metric differences** between samples and is therefore influenced by outliers.\n+The *Spearman method* is based on **rankings**.\n+\n+Output\n+------\n+\n+The default output is a **diagnostic plot** -- either a scatterplot or a clustered heatmap displaying the values for each pair-wise correlation (see below for example plots).\n+\n+Optionally, you can also obtain a table of the pairwise correlation coefficients.\n+\n+.. image:: $PATH_TO_IMAGES/plotCorrelation_output.png\n+    :width: 600\n+    :height: 271\n+\n+Example plots\n+-------------\n+\n+The following is the output of ``plotCorrelation`` with our test ChIP-Seq datasets (to be found under "Shared Data" --> "Data Library").\n+\n+Average coverages were computed over 10 kb bins for chromosome X,\n+from bigWig files using ``multiBigwigSummary``. This was then used with ``plotCorrelation`` to make a heatmap of Spearman correlation coefficients.\n+\n+.. image:: $PATH_TO_IMAGES/plotCorrelation_galaxy_bw_heatmap_output.png\n+    :width: 600\n+    :height: 518\n+\n+The scatterplot could look like this:\n+\n+.. image:: $PATH_TO_IMAGES/plotCorrelation_scatterplot_PearsonCorr_bigwigScores.png\n+    :width: 600\n+    :height: 600\n+\n+-----\n+\n+@REFERENCES@\n+]]>\n+    </help>\n+    <expand macro="citations" />\n+</tool>\n'
b
diff -r cdc31a261f47 -r ed2767cdf4e8 test-data/bamCompare_result2.bw
b
Binary file test-data/bamCompare_result2.bw has changed
b
diff -r cdc31a261f47 -r ed2767cdf4e8 test-data/bamCoverage_result1.bw
b
Binary file test-data/bamCoverage_result1.bw has changed
b
diff -r cdc31a261f47 -r ed2767cdf4e8 test-data/bamCoverage_result2.bw
b
Binary file test-data/bamCoverage_result2.bw has changed
b
diff -r cdc31a261f47 -r ed2767cdf4e8 test-data/bamCoverage_result6.bw
b
Binary file test-data/bamCoverage_result6.bw has changed
b
diff -r cdc31a261f47 -r ed2767cdf4e8 test-data/bamPEFragmentSize_histogram_result1.png
b
Binary file test-data/bamPEFragmentSize_histogram_result1.png has changed
b
diff -r cdc31a261f47 -r ed2767cdf4e8 test-data/bigwigCompare_result1.bw
b
Binary file test-data/bigwigCompare_result1.bw has changed
b
diff -r cdc31a261f47 -r ed2767cdf4e8 test-data/computeMatrixOperations.txt
--- a/test-data/computeMatrixOperations.txt Tue Jan 24 04:57:11 2017 -0500
+++ b/test-data/computeMatrixOperations.txt Fri Mar 31 09:27:20 2017 -0400
b
@@ -1,4 +1,4 @@
 Groups:
  genes
 Samples:
- file_0
+ bamCoverage_result4_bw_0
b
diff -r cdc31a261f47 -r ed2767cdf4e8 test-data/computeMatrixOperations_result2.mat.gz
b
Binary file test-data/computeMatrixOperations_result2.mat.gz has changed
b
diff -r cdc31a261f47 -r ed2767cdf4e8 test-data/computeMatrix_result1.gz
b
Binary file test-data/computeMatrix_result1.gz has changed
b
diff -r cdc31a261f47 -r ed2767cdf4e8 test-data/computeMatrix_result2.gz
b
Binary file test-data/computeMatrix_result2.gz has changed
b
diff -r cdc31a261f47 -r ed2767cdf4e8 test-data/computeMatrix_result3.gz
b
Binary file test-data/computeMatrix_result3.gz has changed
b
diff -r cdc31a261f47 -r ed2767cdf4e8 test-data/correctGCBias_result1.bam
b
Binary file test-data/correctGCBias_result1.bam has changed
b
diff -r cdc31a261f47 -r ed2767cdf4e8 test-data/heatmapper_result1.png
b
Binary file test-data/heatmapper_result1.png has changed
b
diff -r cdc31a261f47 -r ed2767cdf4e8 test-data/heatmapper_result2.png
b
Binary file test-data/heatmapper_result2.png has changed
b
diff -r cdc31a261f47 -r ed2767cdf4e8 test-data/multiBamSummary_result1.npz
b
Binary file test-data/multiBamSummary_result1.npz has changed
b
diff -r cdc31a261f47 -r ed2767cdf4e8 test-data/multiBamSummary_result2.npz
b
Binary file test-data/multiBamSummary_result2.npz has changed
b
diff -r cdc31a261f47 -r ed2767cdf4e8 test-data/multiBamSummary_result2b.npz
b
Binary file test-data/multiBamSummary_result2b.npz has changed
b
diff -r cdc31a261f47 -r ed2767cdf4e8 test-data/multiBigwigSummary_result1.npz
b
Binary file test-data/multiBigwigSummary_result1.npz has changed
b
diff -r cdc31a261f47 -r ed2767cdf4e8 test-data/plotCorrelation_result1.png
b
Binary file test-data/plotCorrelation_result1.png has changed
b
diff -r cdc31a261f47 -r ed2767cdf4e8 test-data/plotCorrelation_result1.tabular
--- a/test-data/plotCorrelation_result1.tabular Tue Jan 24 04:57:11 2017 -0500
+++ b/test-data/plotCorrelation_result1.tabular Fri Mar 31 09:27:20 2017 -0400
b
@@ -1,3 +1,3 @@
- 'bowtie2-test1.bam' 'bowtie2-test1.bam'
-'bowtie2-test1.bam' 1.0000 1.0000
-'bowtie2-test1.bam' 1.0000 1.0000
+ 'bowtie2 test1.bam' 'bowtie2 test1.bam'
+'bowtie2 test1.bam' 1.0000 1.0000
+'bowtie2 test1.bam' 1.0000 1.0000
b
diff -r cdc31a261f47 -r ed2767cdf4e8 test-data/plotCorrelation_result2.png
b
Binary file test-data/plotCorrelation_result2.png has changed
b
diff -r cdc31a261f47 -r ed2767cdf4e8 test-data/plotCoverage_result1.png
b
Binary file test-data/plotCoverage_result1.png has changed
b
diff -r cdc31a261f47 -r ed2767cdf4e8 test-data/plotEnrichment_output.png
b
Binary file test-data/plotEnrichment_output.png has changed
b
diff -r cdc31a261f47 -r ed2767cdf4e8 test-data/plotFingerprint_quality_metrics.tabular
--- a/test-data/plotFingerprint_quality_metrics.tabular Tue Jan 24 04:57:11 2017 -0500
+++ b/test-data/plotFingerprint_quality_metrics.tabular Fri Mar 31 09:27:20 2017 -0400
b
@@ -1,3 +1,3 @@
 Sample AUC Synthetic AUC X-intercept Synthetic X-intercept Elbow Point Synthetic Elbow Point JS Distance Synthetic JS Distance % genome enriched diff. enrichment CHANCE divergence
-bowtie2 test1.bam 0.00493632029864 0.481650684758 0.984443061605 1.15310443503e-24 0.984940883634 0.523268829811 NA 0.269861238192 NA NA NA
-bowtie2 test1.bam 0.00493632029864 0.481650684758 0.984443061605 1.15310443503e-24 0.984940883634 0.523268829811 NA 0.269861238192 NA NA NA
+bowtie2 test1.bam 0.00493632029864 0.481650684758 0.984443061605 1.15310443503e-24 0.984940883634 0.523268829811 NA 0.269004498068 NA NA NA
+bowtie2 test1.bam 0.00493632029864 0.481650684758 0.984443061605 1.15310443503e-24 0.984940883634 0.523268829811 NA 0.269004498068 NA NA NA
b
diff -r cdc31a261f47 -r ed2767cdf4e8 test-data/plotFingerprint_result1.png
b
Binary file test-data/plotFingerprint_result1.png has changed
b
diff -r cdc31a261f47 -r ed2767cdf4e8 test-data/plotFingerprint_result2.png
b
Binary file test-data/plotFingerprint_result2.png has changed
b
diff -r cdc31a261f47 -r ed2767cdf4e8 test-data/profiler_result1.png
b
Binary file test-data/profiler_result1.png has changed
b
diff -r cdc31a261f47 -r ed2767cdf4e8 test-data/profiler_result2.png
b
Binary file test-data/profiler_result2.png has changed
b
diff -r cdc31a261f47 -r ed2767cdf4e8 test-data/profiler_result2.tabular
--- a/test-data/profiler_result2.tabular Tue Jan 24 04:57:11 2017 -0500
+++ b/test-data/profiler_result2.tabular Fri Mar 31 09:27:20 2017 -0400
b
@@ -1,3 +1,3 @@
 bin labels -0.0Kb 0.0Kb
 bins 1 2
-file_0 genes 2477942.34473 2610259.65234
+bamCoverage_result4_bw_0 genes 2477942.875 2610260.125
b
diff -r cdc31a261f47 -r ed2767cdf4e8 tool_dependencies.xml
--- a/tool_dependencies.xml Tue Jan 24 04:57:11 2017 -0500
+++ b/tool_dependencies.xml Fri Mar 31 09:27:20 2017 -0400
b
@@ -1,7 +1,7 @@
 <?xml version="1.0"?>
 <tool_dependency>
     <package name="python" version="2.7.10">
-        <repository changeset_revision="0339c4a9b87b" name="package_python_2_7_10" owner="iuc" prior_installation_required="True" toolshed="https://toolshed.g2.bx.psu.edu" />
+        <repository changeset_revision="bd7165ea6526" name="package_python_2_7_10" owner="iuc" prior_installation_required="True" toolshed="https://toolshed.g2.bx.psu.edu" />
     </package>
     <package name="deeptools" version="2.4.2">
         <repository changeset_revision="efc55c226f11" name="package_python_2_7_deeptools_2_4_2" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" />