# HG changeset patch
# User bgruening
# Date 1375460335 14400
# Node ID c6f1a059bc7d1529770baf7ab34db5b9bc80a6ad
# Parent 1a78aa9ea23427024249bfa484875dbde32d7601
Uploaded
diff -r 1a78aa9ea234 -r c6f1a059bc7d bamCompare.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/bamCompare.xml Fri Aug 02 12:18:55 2013 -0400
@@ -0,0 +1,213 @@
+
+ Normalize and compare two BAM files to output ratio, log2ratio or difference.
+
+ numpy
+ argsparse
+ pysam
+ numpy
+
+
+ bamCompare
+ --bamfile1 '$bamFile1'
+ -bai1 '${bamFile1.metadata.bam_index}'
+ --bamfile2 '$bamFile2'
+ -bai2 '${bamFile2.metadata.bam_index}'
+
+ --outFileName '$outFileName'
+ --outFileFormat '$outFileFormat'
+
+ --fragmentLength $fragmentLength
+ --binSize $binSize
+
+ #if $scaling.method == 'SES':
+ --scaleFactorsMethod SES
+ --sampleLength $scaling.sampleLength
+ #elif $scaling.method == 'readCount':
+ --scaleFactorsMethod readCount
+ #elif $scaling.method == 'own':
+ --scaleFactors '$scaling.scaleFactor1:$scaling.scaleFactor2'
+ #end if
+
+ --ratio $comparison.type
+
+
+ #if $comparison.type=='subtract':
+ #if $comparison.normalization.type=='rpkm':
+ --normalizeUsingRPKM
+ #elif $comparison.normalization.type=='1x':
+ --normalizeTo1x $comparison.normalization.normalizeTo1x
+ #end if
+ #end if
+
+ #if $advancedOpt.showAdvancedOpt == "yes":
+ #if $advancedOpt.smoothLength:
+ --smoothLength '$advancedOpt.smoothLength'
+ #end if
+
+ #if str($advancedOpt.region.value) != '':
+ --region '$advancedOpt.region'
+ #end if
+ $advancedOpt.doNotExtendPairedEnds
+ $advancedOpt.ignoreDuplicates
+
+ #if $advancedOpt.minMappingQuality:
+ --minMappingQuality '$advancedOpt.minMappingQuality'
+ #end if
+
+ --missingDataAsZero $advancedOpt.missingDataAsZero
+
+ #end if
+ --numberOfProcessors 4
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+**What it does**
+
+This tool compares two BAM files based on the number of mapped reads. To
+compare the BAM files the genome is partitioned into bins of equal size, then
+the number of reads found in each BAM file are counted for such bins and
+finally a summarizing value is reported. This vaule can be the ratio of the
+number of reads per bin, the log2 of the ratio or the difference. This tool
+can normalize the number of reads on each BAM file using the SES method
+proposed by Diaz et al. (2012). "Normalization, bias correction, and peak
+calling for ChIP-seq". Statistical applications in genetics and molecular
+biology, 11(3). Normalization based on read counts is also available. The
+output is either a bedgraph or a bigwig file containing the bin location and
+the resulting comparison values. By default if reads are mated the fragment
+length reported in the BAM file is used.
+
+-----
+
+.. class:: infomark
+
+Please acknowledge that this tool **is still in development** and we will be very happy to receive feedback from the users. If you run into any trouble please sent an email to `Fidel Ramirez`_.
+
+This tool is developed by the `Bioinformatics and Deep-Sequencing Unit`_ at the `Max Planck Institute for Immunobiology and Epigenetics`_.
+
+
+.. _Bioinformatics and Deep-Sequencing Unit: http://www3.ie-freiburg.mpg.de/facilities/research-facilities/bioinformatics-and-deep-sequencing-unit/
+.. _Max Planck Institute for Immunobiology and Epigenetics: http://www3.ie-freiburg.mpg.de
+.. _Fidel Ramirez: ramirez@ie-freiburg.mpg.de
+
+
+
+
diff -r 1a78aa9ea234 -r c6f1a059bc7d bamCorrelate.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/bamCorrelate.xml Fri Aug 02 12:18:55 2013 -0400
@@ -0,0 +1,165 @@
+
+ corrlates pairs of bam files
+
+
+ #set files=[]
+ #set labels=[]
+ #for $i in $inputs
+ #set $files += [str($i.bamfile)]
+ #if str($i.label.value) != "":
+ #set $labels += ["\"%s\"" % ($i.label.value)]
+ #else
+ #set $labels += ["\"%s\"" % ($i.bamfile.name)]
+ #end if
+ #end for
+ bamCorrelate
+ --bamfiles #echo " ".join($files)
+ --labels #echo " ".join($labels)
+
+ --fragmentLength $fragmentLength
+ --corMethod $corMethod
+
+ #set newoutFileName=str($outFileName)+".png"
+ --plotFile $newoutFileName
+
+ #if $outputOpt.showOutputOpt == "yes"
+ #if $outputOpt.outFileRawCounts:
+ --outRawCounts '$outputOpt.outFileRawCounts'
+ #end if
+ #if $outputOpt.outFileCorMatrix:
+ --outFileCorMatrix '$outputOpt.outFileCorMatrix'
+ #end if
+ #end if
+
+ #if $advancedOpt.showAdvancedOpt == "yes":
+ #if $advancedOpt.smoothLength:
+ --smoothLength '$advancedOpt.smoothLength'
+ #end if
+
+ #if str($advancedOpt.region.value) != '':
+ --region '$advancedOpt.region'
+ #end if
+
+ --binSize '$advancedOpt.binSize'
+ --numberOfSamples '$advancedOpt.numberOfSamples'
+
+ $advancedOpt.doNotExtendPairedEnds
+ $advancedOpt.ignoreDuplicates
+ $advancedOpt.includeZeros
+
+ #if $advancedOpt.minMappingQuality:
+ --minMappingQuality '$advancedOpt.minMappingQuality'
+ #end if
+ #end if
+
+ --numberOfProcessors 4; mv $newoutFileName $outFileName
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ (outputOpt['showOutputOpt'] == 'yes' and outputOpt['saveRawCounts'] == True)
+
+
+ (outputOpt['showOutputOpt'] == 'yes' and outputOpt['saveCorMatrix'] == True)
+
+
+
+
+**What it does**
+
+Genomes are split into bins of given length. For each bin the number of reads
+found for each of the bam files is counted. A correlation is computed for all
+pairs of bam files.
+
+-----
+
+.. class:: infomark
+
+Please acknowledge that this tool **is still in development** and we will be very happy to receive feedback from the users. If you run into any trouble please sent an email to `Fidel Ramirez`_.
+
+This tool is developed by the `Bioinformatics and Deep-Sequencing Unit`_ at the `Max Planck Institute for Immunobiology and Epigenetics`_.
+
+
+.. _Bioinformatics and Deep-Sequencing Unit: http://www3.ie-freiburg.mpg.de/facilities/research-facilities/bioinformatics-and-deep-sequencing-unit/
+.. _Max Planck Institute for Immunobiology and Epigenetics: http://www3.ie-freiburg.mpg.de
+.. _Fidel Ramirez: ramirez@ie-freiburg.mpg.de
+
+
+
+
diff -r 1a78aa9ea234 -r c6f1a059bc7d bamCoverage.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/bamCoverage.xml Fri Aug 02 12:18:55 2013 -0400
@@ -0,0 +1,144 @@
+
+ Given a BAM file, generates a coverage bigwig file. Multiple options available to count reads and normalize coverage.
+
+ numpy
+ argsparse
+ pysam
+ numpy
+
+ bamCoverage
+ --bam '$bamInput'
+ --bamIndex ${bamInput.metadata.bam_index}
+ --outFileName '$outFileName'
+ --outFileFormat '$outFileFormat'
+
+ --fragmentLength $fragmentLength
+ --binSize $binSize
+
+
+ #if $scaling.type=='rpkm':
+ --normalizeUsingRPKM
+ #elif $scaling.type=='1x':
+ --normalizeTo1x $scaling.normalizeTo1x
+ #elif $scaling.type=='own':
+ --scaleFactor $scaling.scaleFactor
+ #end if
+
+ #if $advancedOpt.showAdvancedOpt == "yes":
+ #if $advancedOpt.smoothLength:
+ --smoothLength '$advancedOpt.smoothLength'
+ #end if
+
+ #if str($advancedOpt.region.value) != '':
+ --region '$advancedOpt.region'
+ #end if
+ $advancedOpt.doNotExtendPairedEnds
+ $advancedOpt.ignoreDuplicates
+
+ #if $advancedOpt.minMappingQuality:
+ --minMappingQuality '$advancedOpt.minMappingQuality'
+ #end if
+
+ #end if
+ --numberOfProcessors 4
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+**What it does**
+
+Given a BAM file, this tool generates a bigWig or bedGraph file of fragment or read coverages. The way the method works is by first calculating all the number of reads (either extended to match the fragment length or not) that overlap each bin in the genome. Bins with zero counts are skipped, i.e. not added to the output file. The resulting read counts can be normalized using either a given scaling factor, the RPKM formula or to get a 1x depth of coverage (RPGC).
+
+-----
+
+.. class:: infomark
+
+Please acknowledge that this tool **is still in development** and we will be very happy to receive feedback from the users. If you run into any trouble please sent an email to `Fidel Ramirez`_.
+
+This tool is developed by the `Bioinformatics and Deep-Sequencing Unit`_ at the `Max Planck Institute for Immunobiology and Epigenetics`_.
+
+
+.. _Bioinformatics and Deep-Sequencing Unit: http://www3.ie-freiburg.mpg.de/facilities/research-facilities/bioinformatics-and-deep-sequencing-unit/
+.. _Max Planck Institute for Immunobiology and Epigenetics: http://www3.ie-freiburg.mpg.de
+.. _Fidel Ramirez: ramirez@ie-freiburg.mpg.de
+
+
+
+
diff -r 1a78aa9ea234 -r c6f1a059bc7d bamFingerprint.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/bamFingerprint.xml Fri Aug 02 12:18:55 2013 -0400
@@ -0,0 +1,151 @@
+
+ plots profiles of bam files
+
+
+ #set files=[]
+ #set labels=[]
+ #for $i in $inputs
+ #set $files += [str($i.bamfile)]
+ #if str($i.label.value) != "":
+ #set $labels += ["\"%s\"" % ($i.label.value)]
+ #else
+ #set $labels += ["\"%s\"" % ($i.bamfile.name)]
+ #end if
+ #end for
+ bamFingerprint
+ --bamfiles #echo " ".join($files)
+ --labels #echo " ".join($labels)
+
+ --fragmentLength $fragmentLength
+
+ #set newoutFileName=str($outFileName)+".png"
+ --plotFile $newoutFileName
+
+ #if $outputOpt.showOutputOpt == "yes"
+ #if $outputOpt.saveRawCounts:
+ --outRawCounts '$outFileRawCounts'
+ #end if
+ #end if
+
+ #if $advancedOpt.showAdvancedOpt == "yes":
+ #if $advancedOpt.smoothLength:
+ --smoothLength '$advancedOpt.smoothLength'
+ #end if
+
+ #if str($advancedOpt.region.value) != '':
+ --region '$advancedOpt.region'
+ #end if
+
+ --binSize '$advancedOpt.binSize'
+ --numberOfSamples '$advancedOpt.numberOfSamples'
+
+ $advancedOpt.doNotExtendPairedEnds
+ $advancedOpt.ignoreDuplicates
+ $advancedOpt.skipZeros
+
+ #if $advancedOpt.minMappingQuality:
+ --minMappingQuality '$advancedOpt.minMappingQuality'
+ #end if
+ #end if
+
+ --numberOfProcessors 4; mv $newoutFileName $outFileName
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ (outputOpt['showOutputOpt'] == 'yes' and outputOpt['saveRawCounts'] == True)
+
+
+
+
+**What it does**
+
+Samples indexed bam files and plots a profile for each bam file. At each
+sample position all reads overlaping a window (bin) of specified length are
+counted. This counts are then sorted and the cumulative sum plotted
+
+-----
+
+.. class:: infomark
+
+Please acknowledge that this tool **is still in development** and we will be very happy to receive feedback from the users. If you run into any trouble please sent an email to `Fidel Ramirez`_.
+
+This tool is developed by the `Bioinformatics and Deep-Sequencing Unit`_ at the `Max Planck Institute for Immunobiology and Epigenetics`_.
+
+
+.. _Bioinformatics and Deep-Sequencing Unit: http://www3.ie-freiburg.mpg.de/facilities/research-facilities/bioinformatics-and-deep-sequencing-unit/
+.. _Max Planck Institute for Immunobiology and Epigenetics: http://www3.ie-freiburg.mpg.de
+.. _Fidel Ramirez: ramirez@ie-freiburg.mpg.de
+
+
+
+
diff -r 1a78aa9ea234 -r c6f1a059bc7d bigwigCompare.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/bigwigCompare.xml Fri Aug 02 12:18:55 2013 -0400
@@ -0,0 +1,120 @@
+
+ compares two bigwig files based on the number of mapped reads
+
+
+ bigwigCompare
+ --bigwig1 '$bigwigFile1'
+ --bigwig2 '$bigwigFile2'
+
+ --outFileName '$outFileName'
+ --outFileFormat '$outFileFormat'
+
+ --ratio $comparison_type
+
+ #if $advancedOpt.showAdvancedOpt == "yes":
+ #if str($advancedOpt.region.value) != '':
+ --region '$advancedOpt.region'
+ #end if
+
+ --missingDataAsZero $advancedOpt.missingDataAsZero
+ --scaleFactors '$advancedOpt.scaleFactor1:$advancedOpt.scaleFactor2'
+ --pseudocount '$advancedOpt.pseudocount'
+ --binSize $advancedOpt.binSize
+
+ #end if
+ --numberOfProcessors 4
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ argsparse
+ pysam
+ numpy
+
+
+
+
+**What it does**
+
+This tool compares two bigwig files based on the number of mapped reads. To
+compare the bigwig files the genome is partitioned into bins of equal size,
+then the number of reads found in each BAM file are counted for such bins and
+finally a summarizing value is reported. This vaule can be the ratio of the
+number of readsper bin, the log2 of the ratio, the sum or the difference.
+
+-----
+
+.. class:: infomark
+
+Please acknowledge that this tool **is still in development** and we will be very happy to receive feedback from the users. If you run into any trouble please sent an email to `Fidel Ramirez`_.
+
+This tool is developed by the `Bioinformatics and Deep-Sequencing Unit`_ at the `Max Planck Institute for Immunobiology and Epigenetics`_.
+
+
+.. _Bioinformatics and Deep-Sequencing Unit: http://www3.ie-freiburg.mpg.de/facilities/research-facilities/bioinformatics-and-deep-sequencing-unit/
+.. _Max Planck Institute for Immunobiology and Epigenetics: http://www3.ie-freiburg.mpg.de
+.. _Fidel Ramirez: ramirez@ie-freiburg.mpg.de
+
+
+
+
diff -r 1a78aa9ea234 -r c6f1a059bc7d computeGCBias.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/computeGCBias.xml Fri Aug 02 12:18:55 2013 -0400
@@ -0,0 +1,144 @@
+
+
+
+
+
+
+ computeGCBias
+ --bamfile '$bamInput'
+ --species '$species'
+ --GCbiasFrequenciesFile $outFileName
+ --fragmentLength $fragmentLength
+
+ #if $source.ref_source=="history":
+ --genome $source.input1
+ #else:
+ --genome "${source.input1_2bit.fields.path}"
+ #end if
+
+ #if $advancedOpt.showAdvancedOpt == "yes":
+ #if str($advancedOpt.region.value) != '':
+ --region '$advancedOpt.region'
+ #end if
+
+ --binSize '$advancedOpt.binSize'
+ --sampleSize '$advancedOpt.sampleSize'
+ --regionSize '$advancedOpt.regionSize'
+
+ #if $advancedOpt.filterOut:
+ --filterOut $advancedOpt.filterOut
+ #end if
+
+ #if $advancedOpt.extraSampling:
+ --extraSampling $advancedOpt.extraSampling
+ #end if
+
+ #end if
+
+ #set move=""
+ #if $output.showOutputSettings == "yes"
+ #if $output.saveBiasPlot:
+ --biasPlot biasPlot.png
+ #set move="mv biasPlot.png $biasPlot"
+ #end if
+ #end if
+ ; $move
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ (output['showOutputSettings'] == 'yes' and output['saveBiasPlot'] == True)
+
+
+
+
+**What it does**
+
+Computes the GC bias ussing Benjamini's method [citation]. The resulting GC
+bias can later be used to plot the bias or to correct the bias.
+
+-----
+
+.. class:: infomark
+
+Please acknowledge that this tool **is still in development** and we will be very happy to receive feedback from the users. If you run into any trouble please sent an email to `Fidel Ramirez`_.
+
+This tool is developed by the `Bioinformatics and Deep-Sequencing Unit`_ at the `Max Planck Institute for Immunobiology and Epigenetics`_.
+
+
+.. _Bioinformatics and Deep-Sequencing Unit: http://www3.ie-freiburg.mpg.de/facilities/research-facilities/bioinformatics-and-deep-sequencing-unit/
+.. _Max Planck Institute for Immunobiology and Epigenetics: http://www3.ie-freiburg.mpg.de
+.. _Fidel Ramirez: ramirez@ie-freiburg.mpg.de
+
+
+
+
diff -r 1a78aa9ea234 -r c6f1a059bc7d computeMatrix.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/computeMatrix.xml Fri Aug 02 12:18:55 2013 -0400
@@ -0,0 +1,191 @@
+
+ summarizes and prepares an intermediary file containing scores associated with genomic regions that can be used afterwards to plot a heatmap or a profile
+
+ computeMatrix
+ $mode.mode_select
+ --regionsFileName '$regionsFile'
+ --scoreFileName '$scoreFile'
+ --outFileName '$outFileName'
+
+ #if $output.showOutputSettings == "yes"
+ #if $output.saveData:
+ --outFileNameData '$outFileNameData'
+ #end if
+ #if $output.saveMatrix:
+ --outFileNameMatrix '$outFileNameMatrix'
+ #end if
+
+ #if $output.saveSortedRegions:
+ --outFileSortedRegions '$outFileSortedRegions'
+ #end if
+ #end if
+
+ #if $mode.mode_select == "reference-point":
+ --referencePoint $mode.referencePoint
+ $mode.nanAfterEnd
+ --beforeRegionStartLength $mode.beforeRegionStartLength
+ --afterRegionStartLength $mode.afterRegionStartLength
+ #else
+ --regionBodyLength $mode.regionBodyLength
+ --startLabel $mode.startLabel
+ --endLabel $mode.endLabel
+ #if $mode.regionStartLength.regionStartLength_select == "yes":
+ --beforeRegionStartLength $mode.regionStartLength.beforeRegionStartLength
+ --afterRegionStartLength $mode.regionStartLength.afterRegionStartLength
+ #end if
+ #end if
+
+ #if $advancedOpt.showAdvancedOpt == "yes":
+ --sortRegions '$advancedOpt.sortRegions'
+ --sortUsing '$advancedOpt.sortUsing'
+ --averageTypeBins '$advancedOpt.averageTypeBins'
+ $advancedOpt.missingDataAsZero
+ $advancedOpt.skipZeros
+
+ #if $advancedOpt.minThreshold:
+ --minThreshold $advancedOpt.minThreshold
+ #end if
+ #if $advancedOpt.maxThreshold:
+ --maxThreshold $advancedOpt.maxThreshold
+ #end if
+ #if $advancedOpt.scale:
+ --scale $advancedOpt.scale
+ #end if
+
+ #end if
+ --numberOfProcessors 4
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ (output['showOutputSettings'] == 'yes' and output['saveData'] == True)
+
+
+ (output['showOutputSettings'] == 'yes' and output['saveMatrix'] == True)
+
+
+ (output['showOutputSettings'] == 'yes' and output['saveSortedRegions'] == True)
+
+
+
+**What it does**
+
+This tool summarizes and prepares an intermediary file containing scores associated with genomic regions that can be used afterwards to plot a heatmap or a profile. Typically, these genomic regions are genes, but any other regions defined in a BED or GFF format can be used. This tool can also be used to filter and sort regions according to their score.
+
+-----
+
+.. class:: infomark
+
+Please acknowledge that this tool **is still in development** and we will be very happy to receive feedback from the users. If you run into any trouble please sent an email to `Fidel Ramirez`_.
+
+This tool is developed by the `Bioinformatics and Deep-Sequencing Unit`_ at the `Max Planck Institute for Immunobiology and Epigenetics`_.
+
+
+.. _Bioinformatics and Deep-Sequencing Unit: http://www3.ie-freiburg.mpg.de/facilities/research-facilities/bioinformatics-and-deep-sequencing-unit/
+.. _Max Planck Institute for Immunobiology and Epigenetics: http://www3.ie-freiburg.mpg.de
+.. _Fidel Ramirez: ramirez@ie-freiburg.mpg.de
+
+
+
diff -r 1a78aa9ea234 -r c6f1a059bc7d correctGCBias.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/correctGCBias.xml Fri Aug 02 12:18:55 2013 -0400
@@ -0,0 +1,109 @@
+
+
+
+
+ correctGCBias
+ --bamfile '$bamInput'
+ --species '$species'
+ --GCbiasFrequenciesFile $GCbiasFrequenciesFile
+
+ #if $source.ref_source=="history":
+ --genome $source.input1
+ #else:
+ --genome "${source.input1_2bit.fields.path}"
+ #end if
+
+ #if $advancedOpt.showAdvancedOpt == "yes":
+ #if str($advancedOpt.region.value) != '':
+ --region '$advancedOpt.region'
+ #end if
+
+ --binSize '$advancedOpt.binSize'
+ #end if
+
+ #set newoutFileName="corrected."+str($outFileFormat)
+
+ --correctedFile $newoutFileName; mv $newoutFileName $outFileName
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+**What it does**
+
+Computes the GC bias ussing Benjamini's method [citation]. The resulting GC
+bias can later be used to plot the bias or to correct the bias.
+
+-----
+
+.. class:: infomark
+
+Please acknowledge that this tool **is still in development** and we will be very happy to receive feedback from the users. If you run into any trouble please sent an email to `Fidel Ramirez`_.
+
+This tool is developed by the `Bioinformatics and Deep-Sequencing Unit`_ at the `Max Planck Institute for Immunobiology and Epigenetics`_.
+
+
+.. _Bioinformatics and Deep-Sequencing Unit: http://www3.ie-freiburg.mpg.de/facilities/research-facilities/bioinformatics-and-deep-sequencing-unit/
+.. _Max Planck Institute for Immunobiology and Epigenetics: http://www3.ie-freiburg.mpg.de
+.. _Fidel Ramirez: ramirez@ie-freiburg.mpg.de
+
+
+
+
diff -r 1a78aa9ea234 -r c6f1a059bc7d heatmapper.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/heatmapper.xml Fri Aug 02 12:18:55 2013 -0400
@@ -0,0 +1,365 @@
+
+ creates a heatmap for a score associated to genomic regions
+
+
+ samtools
+ numpy
+ matplotlib
+ scipy
+ ucsc_tools
+ deepTools
+
+
+
+ heatmapper
+ --matrixFile $matrixFile
+ #if $output.showOutputSettings == "yes"
+ #set newoutFileName=str($outFileName)+"."+str($output.outFileFormat)
+ --outFileName $newoutFileName
+ #if $outFileNameData:
+ --outFileNameData '$outFileNameData'
+ #end if
+
+ #if $outFileNameMatrix:
+ --outFileNameMatrix '$outFileNameMatrix'
+ #end if
+
+ #if $outFileSortedRegions:
+ --outFileSortedRegions '$outFileSortedRegions'
+ #end if
+ #else
+ #set newoutFileName=str($outFileName)+".png"
+ --outFileName $newoutFileName
+ #end if
+
+ #if $advancedOpt.showAdvancedOpt == "yes"
+ #if $advancedOpt.sortRegions:
+ --sortRegions '$advancedOpt.sortRegions'
+ #end if
+
+ #if $advancedOpt.sortUsing:
+ --sortUsing '$advancedOpt.sortUsing'
+ #end if
+
+ #if $advancedOpt.averageTypeSummaryPlot:
+ --averageTypeSummaryPlot '$advancedOpt.averageTypeSummaryPlot'
+ #end if
+
+ #if str($advancedOpt.missingDataColor.value) != "None":
+ --missingDataColor '$advancedOpt.missingDataColor'
+ #end if
+
+ --colorMap '$advancedOpt.colorMap'
+
+ #if $advancedOpt.zMin:
+ --zMin $advancedOpt.zMin
+ #end if
+ #if $advancedOpt.zMax:
+ --zMax $advancedOpt.zMax
+ #end if
+
+ #if $advancedOpt.yMin:
+ --yMin $advancedOpt.yMin
+ #end if
+ #if $advancedOpt.yMax:
+ --yMax $advancedOpt.yMax
+ #end if
+
+ --xAxisLabel '$advancedOpt.xAxisLabel'
+ --yAxisLabel '$advancedOpt.yAxisLabel'
+
+ --heatmapWidth $advancedOpt.heatmapWidth
+ --heatmapHeight $advancedOpt.heatmapHeight
+
+ --whatToShow '$advancedOpt.whatToShow'
+
+ --startLabel '$advancedOpt.startLabel'
+ --endLabel '$advancedOpt.endLabel'
+ --refPointLabel '$advancedOpt.referencePointLabel'
+ --regionsLabel '$advancedOpt.regionsLabel'
+
+ #if str($advancedOpt.plotTitle.value) != "None":
+ --plotTitle '$advancedOpt.plotTitle'
+ #end if
+
+ $advancedOpt.onePlotPerGroup
+ #end if
+ ; mv $newoutFileName $outFileName
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ (output['showOutputSettings'] == 'yes' and output['saveData'] == True)
+
+
+ (output['showOutputSettings'] == 'yes' and output['saveMatrix'] == True)
+
+
+ (output['showOutputSettings'] == 'yes' and output['saveSortedRegions'] == True)
+
+
+
+
+
+**What it does**
+
+HeatMapper visualizes scores associated with genomic regions, for example log2 fold change values obtained from ChIP-seq experiments. Those values can be visualized individually along each of the regions provided by the user.
+
+-----
+
+.. class:: infomark
+
+Please acknowledge that this tool **is still in development** and we will be very happy to receive feedback from the users. If you run into any trouble please sent an email to `Fidel Ramirez`_.
+
+This tool is developed by the `Bioinformatics and Deep-Sequencing Unit`_ at the `Max Planck Institute for Immunobiology and Epigenetics`_.
+
+
+.. _Bioinformatics and Deep-Sequencing Unit: http://www3.ie-freiburg.mpg.de/facilities/research-facilities/bioinformatics-and-deep-sequencing-unit/
+.. _Max Planck Institute for Immunobiology and Epigenetics: http://www3.ie-freiburg.mpg.de
+.. _Fidel Ramirez: ramirez@ie-freiburg.mpg.de
+
+
+
diff -r 1a78aa9ea234 -r c6f1a059bc7d profiler.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/profiler.xml Fri Aug 02 12:18:55 2013 -0400
@@ -0,0 +1,194 @@
+
+
+ creates a profile plot for a score associated to genomic regions
+
+
+
+ profiler
+ --matrixFile $matrixFile
+
+ #if $output.showOutputSettings == "yes"
+ #set newoutFileName=str($outFileName)+"."+str($output.outFileFormat)
+ --outFileName $newoutFilename
+ #if $output.outFileNameData:
+ --outFileNameData '$output.outFileNameData'
+ #end if
+
+ #if $output.outFileNameMatrix:
+ --outFileNameMatrix '$output.outFileNameMatrix'
+ #end if
+
+ #if $output.outFileSortedRegions:
+ --outFileSortedRegions '$output.outFileSortedRegions'
+ #end if
+ #else
+ #set newoutFileName=str($outFileName)+".png"
+ --outFileName $newoutFileName
+ #end if
+
+ #if $scaleRegions.showScaleRegionsOpt == "yes":
+ --startLabel $scaleRegions.startLabel
+ --endLabel $scaleRegions.endLabel
+ --refPointLabel $scaleRegions.refPointLabel
+ #end if
+
+ #if $advancedOpt.showAdvancedOpt == "yes"
+ #if $advancedOpt.averageType:
+ --averageType '$advancedOpt.averageType'
+ #end if
+ --plotHeight $advancedOpt.plotHeight
+ --plotWidth $advancedOpt.plotWidth
+ --plotType $advancedOpt.plotType
+
+ --regionsLabel '$advancedOpt.regionsLabel'
+
+ #if str($advancedOpt.plotTitle.value) != "None":
+ --plotTitle '$advancedOpt.plotTitle'
+ #end if
+
+ $advancedOpt.onePlotPerGroup
+
+ #if $advancedOpt.yMin:
+ --yMin $advancedOpt.yMin
+ #end if
+ #if $advancedOpt.yMax:
+ --yMax $advancedOpt.yMax
+ #end if
+
+ --xAxisLabel '$advancedOpt.xAxisLabel'
+ #if str($advancedOpt.yAxisLabel.value) != "None":
+ --yAxisLabel '$advancedOpt.yAxisLabel'
+ #end if
+ #end if
+ ; mv $newoutFileName $outFileName
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ (output['showOutputSettings'] == 'yes' and output['saveData'] == True)
+
+
+ (output['showOutputSettings'] == 'yes' and output['saveMatrix'] == True)
+
+
+ (output['showOutputSettings'] == 'yes' and output['saveSortedRegions'] == True)
+
+
+
+
+**What it does**
+
+This tool creates a profile plot for a score associated to genomic regions.
+Typically, these regions are genes, but any other regions defined in a BED or
+GFF format will work. A preprocessed matrix generated by the tool
+computeMatrix is required.
+
+-----
+
+.. class:: infomark
+
+Please acknowledge that this tool **is still in development** and we will be very happy to receive feedback from the users. If you run into any trouble please sent an email to `Fidel Ramirez`_.
+
+This tool is developed by the `Bioinformatics and Deep-Sequencing Unit`_ at the `Max Planck Institute for Immunobiology and Epigenetics`_.
+
+
+.. _Bioinformatics and Deep-Sequencing Unit: http://www3.ie-freiburg.mpg.de/facilities/research-facilities/bioinformatics-and-deep-sequencing-unit/
+.. _Max Planck Institute for Immunobiology and Epigenetics: http://www3.ie-freiburg.mpg.de
+.. _Fidel Ramirez: ramirez@ie-freiburg.mpg.de
+
+
+
+
diff -r 1a78aa9ea234 -r c6f1a059bc7d tool_dependencies.xml
--- a/tool_dependencies.xml Sun Jun 30 19:31:28 2013 -0400
+++ b/tool_dependencies.xml Fri Aug 02 12:18:55 2013 -0400
@@ -1,30 +1,66 @@
-
-
+
+
+
+
+
+
+
+
+
+
+
-
+
- http://bioconductor.org/packages/release/bioc/src/contrib/DESeq2_1.0.17.tar.gz
+
+ http://hgdownload.cse.ucsc.edu/admin/exe/linux.x86_64/bedGraphToBigWig
+ http://hgdownload.cse.ucsc.edu/admin/exe/macOSX.i386/bedGraphToBigWig
+ http://hgdownload.cse.ucsc.edu/admin/exe/macOSX.i386/bedGraphToBigWig
+ http://hgdownload.cse.ucsc.edu/admin/exe/macOSX.x86_64/bedGraphToBigWig
+
+
+ $INSTALL_DIR/bedGraphToBigWig
+
+
+ http://hgdownload.cse.ucsc.edu/admin/exe/linux.x86_64/bigWigInfo
+ http://hgdownload.cse.ucsc.edu/admin/exe/macOSX.i386/bigWigInfo
+ http://hgdownload.cse.ucsc.edu/admin/exe/macOSX.i386/bigWigInfo
+ http://hgdownload.cse.ucsc.edu/admin/exe/macOSX.x86_64/bigWigInfo
+
+
+ $INSTALL_DIR/bigWigInfo
+
+
+ $INSTALL_DIR
+
+
+
+ The tools downloaded by this dependency definition are free for academic use. TODO: UCSC tools are only available with their latest version. That is not good for reproducibility.
+
-
-
-
-
+
+
+
+
+
+ git clone --recursive https://github.com/fidelram/deepTools.git
+ git reset --hard 98e5d8a61431ea8605c0643d991a1a5d8999b4dc
+
+ export PYTHONPATH=$PYTHONPATH:$INSTALL_DIR/lib/python &&
+ python setup.py install --install-lib $INSTALL_DIR/lib/python --install-scripts $INSTALL_DIR/bin
- $INSTALL_DIR/deseq2/
-
- Rscript -e "source('http://bioconductor.org/biocLite.R'); install.packages('DESeq2', lib='$INSTALL_DIR/deseq2/', repos='http://cran.us.r-project.org')"
+
+ $INSTALL_DIR/bin
+ $INSTALL_DIR/lib/python
-
- $INSTALL_DIR/deseq2/
-
-
-
- DESeq2
-
+
+
+ Installation of deepTools from Fidel Ramirez.
+