Mercurial > repos > bgruening > deeptools_bam_correlate
changeset 3:a38ae1dfd4b2 draft
planemo upload for repository https://github.com/fidelram/deepTools/tree/master/galaxy/wrapper/ commit 4e5124484b42d4ffef76af4bd82a6feb67a5b829
| author | bgruening |
|---|---|
| date | Fri, 18 Dec 2015 12:22:07 -0500 |
| parents | b282224c8494 |
| children | 7cf2eae394bb |
| files | bamCorrelate.xml deepTools_macros.xml static/images/bamFP_galaxy_output.png |
| diffstat | 3 files changed, 22 insertions(+), 44 deletions(-) [+] |
line wrap: on
line diff
--- a/bamCorrelate.xml Fri Dec 18 07:58:53 2015 -0500 +++ b/bamCorrelate.xml Fri Dec 18 12:22:07 2015 -0500 @@ -1,5 +1,5 @@ <tool id="deeptools_bam_correlate" name="bamCorrelate" version="@WRAPPER_VERSION@.0"> - <description>correlates pairs of BAM files</description> + <description>calculates average read coverages for a list of two or more BAM files</description> <macros> <token name="@BINARY@">bamCorrelate</token> <import>deepTools_macros.xml</import> @@ -101,28 +101,19 @@ </tests> <help> <![CDATA[ + **What it does** -This tool is useful to assess the overall similarity of different BAM files. A typical application -is to check the correlation between replicates or published data sets. - -The tool splits the genomes into bins of given length. For each bin, the number of reads -found in each BAM file is counted and a correlation (either Pearson or Spearman) is computed for all -pairs of BAM files. Finally, a heatmap is drawn based on the similarity of the samples. - - -.. image:: $PATH_TO_IMAGES/QC_bamCorrelate_humanSamples.png - :alt: Heatmap of RNA Polymerase II ChIP-seq - - -You can find more details on the bamCorrelate wiki page: https://github.com/fidelram/deepTools/wiki/QC#wiki-bamCorrelate - +This tool generates a matrix of read-coverages for a list of genomic regions and a number of two or more samples (BAM files) +The tool splits the genome into bins of given length. For each bin, the number of reads found in each BAM file is counted. +Alternatively, a bed file with pre-defined genomic regions can be provided. In each case the calculation can further be limited to +a given genomic interval (e.g. a given chromosome). This option is mostly used for testing and efficiency. +A typical follow-up application is to check and visuzalize the similarity between replicates or published data sets (see: plotPCA and plotCorrelation). **Output files**: -- **diagnostic plot**: clustered heatmap displaying the values for each pair-wise correlation, see below for an example -- data matrix (optional): if you want to plot the correlation values using a different program, e.g. R, this matrix can be used - +- **score matrix**: a compressed matrix where every row correponds to a genome region (or bin) and each column corresponds to a sample (BAM file) +- optional: uncompressed **score matrix** for -----
--- a/deepTools_macros.xml Fri Dec 18 07:58:53 2015 -0500 +++ b/deepTools_macros.xml Fri Dec 18 12:22:07 2015 -0500 @@ -42,24 +42,11 @@ #if $zMax: --zMax $zMax #end if - --colorMap '$colorMap' + --colorMap '$colorMap' $plotNumbers + --plotTitle $plotTitle </token> - <expand macro="plotTitle" /> - <expand macro="plotNumbers" /> - <conditional name="output"> - <param name="showOutputSettings" type="select" label="Show advanced output settings" > - <option value="no" selected="true">no</option> - <option value="yes">yes</option> - </param> - <when value="no" /> - <when value="yes"> - <expand macro="input_image_file_format"/> - <param name="saveRawCounts" type="boolean" label="Save the bin counts"/> - <param name="saveCorMatrix" type="boolean" label="Save the correlation matrix"/> - </when> - </conditional> <xml name="includeZeros"> <param argument="--includeZeros" type="boolean" truevalue="--includeZeros" falsevalue="" @@ -102,7 +89,7 @@ <xml name="kmeans_clustering"> <conditional name="used_multiple_regions"> - <param name="used_multiple_regions_options" type="select" + <param name="used_multiple_regions_options" type="select" label="Did you compute the matrix with more than one groups of regions?" help="Would you like to cluster the regions according to the similarity of the signal distribution? This is only possible if you used computeMatrix on only one group of regions."> <option value="yes">Yes, I used multiple groups of regions</option> @@ -115,7 +102,7 @@ <option value="kmeans">Kmeans clustering</option> </param> <when value="kmeans"> - <param name="k_kmeans" type="integer" value="0" label="Number of clusters to compute" + <param name="k_kmeans" type="integer" value="0" label="Number of clusters to compute" help="When this option is set, then the matrix is split into clusters using the kmeans algorithm. Only works for data that is not grouped, otherwise only the first group will be clustered. If more specific clustering methods are required it is advisable to save the underlying matrix and run the clustering using other software. The plotting of the clustering may fail (Error: Segmentation fault) if a cluster has very few members compared to the total number or regions. (default: None)."/> </when> <when value="none" /> @@ -154,7 +141,7 @@ <xml name="plotNumbers"> <param argument="--plotNumbers" type="boolean" truevalue="--plotNumbers" falsevalue="" - label="Plot the correlation value" + label="Plot the correlation value" help="If set, then the correlation number is plotted on top of the heatmap."/> </xml> @@ -274,9 +261,9 @@ 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/ +.. _Bioinformatics and Deep-Sequencing Unit: http://www.ie-freiburg.mpg.de/bioinformaticsfac .. _Max Planck Institute for Immunobiology and Epigenetics: http://www3.ie-freiburg.mpg.de -.. _help site: https://github.com/fidelram/deepTools/wiki/ +.. _help site: https://deeptools.readthedocs.org/ </token> <xml name="citations"> @@ -294,7 +281,7 @@ <xml name="multiple_input_bigwigs"> <param argument="--bigwigfiles" type="data" format="bigwig" multiple="True" - label="Bigwig file" + label="Bigwig file" help="The Bigwig file must be sorted."/> </xml> @@ -360,8 +347,8 @@ <xml name="effectiveGenomeSize"> <conditional name="effectiveGenomeSize"> <param name="effectiveGenomeSize_opt" type="select" label="Effective genome size" - help="The effective genome size is the portion of the genome that is mappable. Large fractions of the genome are stretches of NNNN that should be discarded. - Also, if repetitive regions were not included in the mapping of reads, the effective genome size needs to be adjusted accordingly. + help="The effective genome size is the portion of the genome that is mappable. Large fractions of the genome are stretches of NNNN that should be discarded. + Also, if repetitive regions were not included in the mapping of reads, the effective genome size needs to be adjusted accordingly. See Table 2 of http://www.plosone.org/article/info%3Adoi%2F10.1371%2Fjournal.pone.0030377 or http://www.nature.com/nbt/journal/v27/n1/fig_tab/nbt.1518_T1.html for several effective genome sizes."> <option value="93260000">ce10 (93260000)</option> <option value="121400000">dm3 (121400000)</option> @@ -445,7 +432,7 @@ <data format="tabular" name="outFileNameMatrix" label="${tool.name} on ${on_string}: Heatmap values"> <filter> (( - output['showOutputSettings'] == 'yes' and + output['showOutputSettings'] == 'yes' and output['saveMatrix'] is True )) </filter> @@ -456,7 +443,7 @@ <data format="tabular" name="outFileNameData" label="${tool.name} on ${on_string}: averages per matrix column"> <filter> (( - output['showOutputSettings'] == 'yes' and + output['showOutputSettings'] == 'yes' and output['saveData'] is True )) </filter> @@ -464,7 +451,7 @@ <data format="bed" name="outFileSortedRegions" label="${tool.name} on ${on_string}: sorted/filtered regions"> <filter> (( - output['showOutputSettings'] == 'yes' and + output['showOutputSettings'] == 'yes' and output['saveSortedRegions'] is True )) </filter>