Mercurial > repos > bgruening > upload_testing
changeset 49:e343dca92ee7
Deleted selected files
| author | bgruening |
|---|---|
| date | Fri, 02 Aug 2013 12:54:08 -0400 |
| parents | 1463dc12d1a3 |
| children | f9390e176b8f |
| files | bigwigCompare.xml computeMatrix.xml correctGCBias.xml tool_data_table_conf.xml.sample |
| diffstat | 4 files changed, 0 insertions(+), 426 deletions(-) [+] |
line wrap: on
line diff
--- a/bigwigCompare.xml Fri Aug 02 12:53:58 2013 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,120 +0,0 @@ -<tool id="bigwigCompare" name="bigwigCompare" version="1.0"> - <description>compares two bigwig files based on the number of mapped reads</description> - - <command> - 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 - - - </command> - - <inputs> - <param name="bigwigFile1" format="bigwig" type="data" label="Treatment bigwig file" /> - - <param name="bigwigFile2" format="bigwig" type="data" label="Input bigwig file" /> - - <param name="comparison_type" type="select" - label="How to compare the two files" - help="The reciprocal ratio returns the negative of the inverse of the ratio if the ratio is less than 0. The resulting values are interpreted as negative fold changes." > - <option value="log2" selected="true">log2 ratio</option> - <option value="ratio">simple ratio</option> - <option value="subtract">difference (subtract input from treatment)</option> - <option value="add">sum</option> - <option value="reciprocal_ratio">reciprocal ratio</option> - </param> - - - - <param name="outFileFormat" type="select" label="Coverage file format"> - <option value="bigwig" selected="true">bigwig</option> - <option value="bedgraph">bedgraph</option> - </param> - - <conditional name="advancedOpt"> - <param name="showAdvancedOpt" type="select" label="Show advanced options" > - <option value="no" selected="true">no</option> - <option value="yes">yes</option> - </param> - <when value="no" /> - <when value="yes"> - - <param name="binSize" type="integer" value="50" min="1" - label="Bin size in bp" - help="Size of the bins in bp for the ouput of the bigwig/bedgraph file "/> - - <param name="region" type="text" value="" - label="Region of the genome to limit the operation to" - help="This is useful when testing parameters to reduce the computing time. The format is chr:start:end, for example "chr10" or "chr10:456700:891000"" /> - - <param name="missingDataAsZero" type="boolean" truevalue="yes" falsevalue="no" checked="True" - label ="Treat missing data as zero" - help ="This parameter determines if missing data should be replaced with a zero. If set to "no", missing data will be ignored and will not be included in the output file at all. Missing data is defined as those regions for which no value exists in *any* of the bigwig files. The decision to include or exclude missing data depends on the interpretation of the data. Missing data in a bigwig file may mean that there is no information available for certain regions, for example a repetitive region that is not being considered. In the same file regions with low coverage may get zero read counts. If missing data is replaced by zero, this would convert the excluded repetitive regions into regions of low coverage." /> - - <param name="scaleFactor1" type="float" value="1" label="Scale factor for treatment"/> - <param name="scaleFactor2" type="float" value="1" label="Scale factor for input"/> - <param name="pseudocount" type="float" value="1" label="Pseudocount" help="Small number to avoid dividing by zero."/> - - </when> - </conditional> - - </inputs> - <outputs> - <data format="bigwig" name="outFileName"> - <change_format> - <when input="outFileFormat" value="bigwig" format="bigwig" /> - <when input="outFileFormat" value="bedgraph" format="bedgraph" /> - </change_format> - </data> - </outputs> - - <requirements> - <requirement type="python-module">argsparse</requirement> - <requirement type="python-module">pysam</requirement> - <requirement type="python-module">numpy</requirement> - </requirements> - - <help> - -**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 - - </help> - -</tool>
--- a/computeMatrix.xml Fri Aug 02 12:53:58 2013 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,191 +0,0 @@ -<tool id="computeMatrix" name="computeMatrix" version="1.0"> - <description>summarizes and prepares an intermediary file containing scores associated with genomic regions that can be used afterwards to plot a heatmap or a profile</description> - <command> - 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 - </command> - <inputs> - <param name="regionsFile" format="bed,gff" type="data" label="Regions to plot" help="File, in BED or GFF format, containing the regions to plot."/> - <param name="scoreFile" format="bigwig,bam" type="data" label="Score file" help="Either a bigWig file (containing a score, usually covering the whole genome) or a BAM file. For this last case, coverage counts will be used for the heatmap."/> - - <conditional name="mode" > - <param name="mode_select" type="select" label="computeMatrix has two main output options" help="In the scale-regions mode, all regions in the BED/GFF file are stretched or shrunk to the same length (bp) that is indicated by the user. Reference-point refers to a position within the BED/GFF regions (e.g start of region). In the reference-point mode only those genomic positions before (downstream) and/or after (upstream) the reference point will be plotted."> - <option value="scale-regions" selected="true">scale-regions</option> - <option value="reference-point">reference-point</option> - </param> - - <when value="scale-regions" > - <param name="regionBodyLength" type="integer" value="500" label="Distance in bp to which all regions are going to be fitted"/> - <param name="startLabel" type="text" value="TSS" size="10" label="Label for the region start" help ="Label shown in the plot for the start of the region. Default is TSS (transcription start site), but could be changed to anything, e.g. "peak start"." /> - <param name="endLabel" type="text" value="TES" size="10" label="Label for the region end" help="Label shown in the plot for the region end. Default is TES (transcription end site)."/> - <conditional name="regionStartLength"> - <param name="regionStartLength_select" type="select" label="Set distance up- and downstream of the given regions"> - <option value="no" selected="true">no</option> - <option value="yes">yes</option> - </param> - <when value="no" /> - <when value="yes"> - <param name="beforeRegionStartLength" type="integer" value="1000" min="1" optional="true" label="Distance upstream of the start site of the regions defined in the region file" help="If the regions are genes, this would be the distance upstream of the transcription start site."/> - - <param name="afterRegionStartLength" type="integer" value="1000" min="1" optional="true" label="Distance downstream of the end site of the given regions" help="If the regions are genes, this would be the distance downstream of the transcription end site."/> - </when> - </conditional> - </when> - - <when value="reference-point"> - <param name="referencePoint" type="select" label="The reference point for the plotting"> - <option value="TSS" selected="true">region start (TSS)</option> - <option value="TES" selected="true">region end (TES)</option> - <option value="center" selected="true">center of the region</option> - </param> - <param name="nanAfterEnd" type="boolean" truevalue="--nanAfterEnd" falsevalue="" label="Discard any values after the region end" help="This is useful to visualize the region end when not using the scale-regions mode and when the reference-point is set to the TSS."/> - <param name="beforeRegionStartLength" type="integer" value="1000" min="1" label="Distance upstream of the start site of the regions defined in the region file" help="If the regions are genes, this would be the distance upstream of the transcription start site."/> - - <param name="afterRegionStartLength" type="integer" value="1000" min="1" label="Distance downstream of the end site of the given regions" help="If the regions are genes, this would be the distance downstream of the transcription end site."/> - </when> - </conditional> - - <conditional name="output" > - <param name="showOutputSettings" type="select" label="Show additional output options" > - <option value="no" selected="true">no</option> - <option value="yes">yes</option> - </param> - <when value="no" /> - <when value="yes"> - <param name="saveData" type="boolean" label="Save the averages per matrix column into a text file" help="This corresponds to the underlying data used to plot a summary profile."/> - <param name="saveMatrix" type="boolean" label="Save the matrix of values underlying the heatmap" help="This matrix can easily be loaded into R or other programs."/> - <param name="saveSortedRegions" type="boolean" label="Save the regions after skiping zeros or min/max threshold values" help="The order of the regions in the file follows the sorting order selected. This is useful, for example, to generate other heatmaps keeping the sorting of the first heatmap."/> - </when> - </conditional> - - - <conditional name="advancedOpt" > - <param name="showAdvancedOpt" type="select" label="Show advanced options" > - <option value="no" selected="true">no</option> - <option value="yes">yes</option> - </param> - <when value="no" /> - <when value="yes"> - - <param name="binSize" type="integer" value="100" min="1" optional="true" label="Length, in base pairs, of the non-overlapping bin for averaging the score over the regions length" /> - - <param name="sortRegions" type="select" label="Sort regions" - help="Whether the output file should present the regions sorted."> - <option value="no" selected="true">no ordering</option> - <option value="descend">descending order</option> - <option value="ascend">ascending order</option> - </param> - - <param name="sortUsing" type="select" label="Method used for sorting." help="The value is computed for each row." > - <option value="mean" selected="true">mean</option> - <option value="median">median</option> - <option value="min">min</option> - <option value="max">max</option> - <option value="sum">sum</option> - <option value="region_length">region length</option> - </param> - - <param name="averageTypeBins" type="select" label="Define the type of statistic that should be used over the bin size range"> - <option value="mean" selected="true">mean</option> - <option value="median">median</option> - <option value="min">min</option> - <option value="max">max</option> - <option value="sum">sum</option> - <option value="std">std</option> - </param> - - <param name="missingDataAsZero" type="boolean" truevalue="--missingDataAsZero" falsevalue="" label="Indicate missing data as zero" help="Only for bigwig input! Set to "yes", if missing data should be indicated as zeros. Default is to ignore such cases which will be depicted as black areas in the heatmap. (see "Missing data color" options of the heatmapper for additional options)."/> - - <param name="skipZeros" type="boolean" truevalue="--skipZeros" falsevalue="" label="Skip zeros" help="Whether regions with only scores of zero should be included or not. Default is to include them."/> - - <param name="minThreshold" type="float" optional="true" label="Minimum threshold" help="Any region containing a value that is equal or less than this numeric value will be skipped. This is useful to skip, for example, genes where the read count is zero for any of the bins. This could be the result of unmappable areas and can bias the overall results."/> - <param name="maxThreshold" type="float" optional="true" label="Maximum threshold" help="Any region containing a value that is equal or higher that this numeric value will be skipped. The max threshold is useful to skip those few regions with very high read counts (e.g. major satellites) that may bias the average values."/> - <param name="scale" type="float" optional="true" label="Scale" help="If set, all values are multiplied by this number."/> - </when> - </conditional> - - </inputs> - <outputs> - <data format="bgzip" name="outFileName" label="${tool.name} on ${on_string}: matrix"> - </data> - <data format="tabular" name="outFileNameData" label="${tool.name} on ${on_string}: raw data"> - <filter>(output['showOutputSettings'] == 'yes' and output['saveData'] == True)</filter> - </data> - <data format="tabular" name="outFileNameMatrix" label="${tool.name} on ${on_string}: matrix of values"> - <filter>(output['showOutputSettings'] == 'yes' and output['saveMatrix'] == True)</filter> - </data> - <data format="bed" name="outFileSortedRegions" label="${tool.name} on ${on_string}: sorted/filtered regions"> - <filter>(output['showOutputSettings'] == 'yes' and output['saveSortedRegions'] == True)</filter> - </data> - </outputs> - <help> -**What it does** - -This tool summarizes and prepares an intermediary file containing scores associated with genomic regions that can be used afterwards to plot a heatmap or a profile. Typically, these genomic regions are genes, but any other regions defined in a BED or GFF format can be used. This tool can also be used to filter and sort regions according to their score. - ------ - -.. class:: infomark - -Please acknowledge that this tool **is still in development** and we will be very happy to receive feedback from the users. If you run into any trouble please sent an email to `Fidel Ramirez`_. - -This tool is developed by the `Bioinformatics and Deep-Sequencing Unit`_ at the `Max Planck Institute for Immunobiology and Epigenetics`_. - - -.. _Bioinformatics and Deep-Sequencing Unit: http://www3.ie-freiburg.mpg.de/facilities/research-facilities/bioinformatics-and-deep-sequencing-unit/ -.. _Max Planck Institute for Immunobiology and Epigenetics: http://www3.ie-freiburg.mpg.de -.. _Fidel Ramirez: ramirez@ie-freiburg.mpg.de - </help> - -</tool>
--- a/correctGCBias.xml Fri Aug 02 12:53:58 2013 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,108 +0,0 @@ -<tool id="correctGCBias" name="correctGCBias" version="1.0"> - <description> - </description> - <command> - correctGCBias - --bamfile '$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 - - </command> - - <inputs> - - <param name="GCbiasFrequenciesFile" type="data" format="tabular" label="Output of computeGCBias" /> - - <param name="bamInput" format="bam" type="data" label="Input BAM file" help="The BAM file must be sorted and indexed."/> - - <param name="species" type="text" value="" label="Species name abbreviation" /> - - <conditional name="source"> - <param name="ref_source" type="select" label="Reference genome"> - <option value="cached">locally cached</option> - <option value="history">in your history</option> - </param> - <when value="cached"> - <param name="input1_2bit" type="select" label="Using reference genome" help="If your genome of interest is not listed, contact your Galaxy team"> - <options from_data_table="deepTools_seqs" /> - </param> - </when> - <when value="history"> - <param name="input1" type="data" format="twobit" label="Select a reference dataset in 2bit format" /> - </when> - </conditional> - - <param name="outFileFormat" type="select" label="File format of the output"> - <option value="bam">bam</option> - <option value="bw">bigwig</option> - <option value="bg">bedgraph</option> - </param> - - <conditional name="advancedOpt"> - <param name="showAdvancedOpt" type="select" label="Show advanced options" > - <option value="no" selected="true">no</option> - <option value="yes">yes</option> - </param> - <when value="no" /> - <when value="yes"> - <param name="region" type="text" value="" - label="Region of the genome to limit the operation to" - help="This is useful when testing parameters to reduce the computing time. The format is chr:start:end, for example "chr10" or "chr10:456700:891000"" /> - - <param name="binSize" type="integer" value="50" min="1" - label="Bin size in bp" - help="Size of the bins in bp for the ouput of the bigwig/bedgraph file."/> - </when> - </conditional> - </inputs> - - <outputs> - <data format="bam" name="outFileName"> - <change_format> - <when input="outFileFormat" value="bw" format="bigwig" /> - <when input="outFileFormat" value="bam" format="bam" /> - <when input="outFileFormat" value="bg" format="bedgraph" /> - </change_format> - </data> - </outputs> - <help> - -**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 - - </help> - -</tool>
--- a/tool_data_table_conf.xml.sample Fri Aug 02 12:53:58 2013 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,7 +0,0 @@ -<tables> - <!-- Locations of 2bit sequence files for use in deepTools --> - <table name="deepTools_seqs" comment_char="#"> - <columns>value, name, path</columns> - <file path="tool-data/deepTools_seqs.loc" /> - </table> -</tables>