Mercurial > repos > bgruening > deeptools
changeset 17:ef65d6b68ccc draft
Uploaded
| author | bgruening |
|---|---|
| date | Sat, 21 Dec 2013 14:26:06 -0500 |
| parents | 16310f8b24d5 |
| children | 5ea8782d650c |
| files | bamCompare.xml bamCoverage.xml deepTools_macros.xml heatmapper.xml tool_dependencies.xml |
| diffstat | 5 files changed, 86 insertions(+), 67 deletions(-) [+] |
line wrap: on
line diff
--- a/bamCompare.xml Mon Dec 16 15:13:08 2013 -0500 +++ b/bamCompare.xml Sat Dec 21 14:26:06 2013 -0500 @@ -38,30 +38,29 @@ #elif $comparison.normalization.type=='1x': --normalizeTo1x $comparison.normalization.normalizeTo1x #end if - - #if str($comparison.ignoreForNormalization).strip() != '': - --ignoreForNormalization $comparison.ignoreForNormalization - #end if - #end if #if $advancedOpt.showAdvancedOpt == "yes": - #if $advancedOpt.smoothLength: - --smoothLength '$advancedOpt.smoothLength' - #end if + #if $advancedOpt.smoothLength: + --smoothLength '$advancedOpt.smoothLength' + #end if - #if str($advancedOpt.region.value) != '': - --region '$advancedOpt.region' - #end if + #if str($advancedOpt.region.value) != '': + --region '$advancedOpt.region' + #end if - $advancedOpt.doNotExtendPairedEnds - $advancedOpt.ignoreDuplicates + $advancedOpt.doNotExtendPairedEnds + $advancedOpt.ignoreDuplicates - #if $advancedOpt.minMappingQuality: - --minMappingQuality '$advancedOpt.minMappingQuality' - #end if + #if $advancedOpt.minMappingQuality: + --minMappingQuality '$advancedOpt.minMappingQuality' + #end if - --missingDataAsZero $advancedOpt.missingDataAsZero + --missingDataAsZero $advancedOpt.missingDataAsZero + + #if str($advancedOpt.ignoreForNormalization).strip() != '': + --ignoreForNormalization $advancedOpt.ignoreForNormalization + #end if #end if @@ -128,9 +127,6 @@ help ="Sequencing depth is defined as the total number of mapped reads * fragment length / effective genome size. To use this option, the effective genome size has to be given. Common values are: mm9: 2150570000, hg19:2451960000, dm3:121400000 and ce10:93260000."/> </when> </conditional> - <param name="ignoreForNormalization" type="text" value="" size="50" - label="regions that should be excluded for calculating the scaling factor" - help="Sometimes it makes sense to exclude certain regions when calculating the scaling factor. For example, if you know some regions that you suspect to be present more often in your sample's genome than in the reference genome that will therefore accumulate reads (CNV). Another typical example is the single X chromosome in male samples that should be scaled separately from the diploid autosomes. For example chrX,chrY,chr3. or chr10:12220-128932" /> </when> </conditional> @@ -147,29 +143,34 @@ <when value="no" /> <when value="yes"> - <param name="smoothLength" type="integer" value="1" optional="true" min="1" - label="Smooth values using the following length (in bp)" - help ="The smooth length defines a window, larger than the bin size, to average the number of reads. For example, if the bin size is set to 20 bp and the smooth length is set to 60 bp, then, for each bin size the average of it and its left and right neighbors is considered. Any value smaller than the bin size will be ignored and no smoothing will be applied."/> + <param name="smoothLength" type="integer" value="1" optional="true" min="1" + label="Smooth values using the following length (in bp)" + help ="The smooth length defines a window, larger than the bin size, to average the number of reads. For example, if the bin size is set to 20 bp and the smooth length is set to 60 bp, then, for each bin size the average of it and its left and right neighbors is considered. Any value smaller than the bin size will be ignored and no smoothing will be applied."/> - <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="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="doNotExtendPairedEnds" type="boolean" truevalue="--doNotExtendPairedEnds" falsevalue="" - label="Do not extend paired ends" - help="If set, reads are not extended to match the fragment length reported in the BAM file, instead they will be extended to match the fragment length. Default is to extend the reads if paired end information is available."/> + <param name="doNotExtendPairedEnds" type="boolean" truevalue="--doNotExtendPairedEnds" falsevalue="" + label="Do not extend paired ends" + help="If set, reads are not extended to match the fragment length reported in the BAM file, instead they will be extended to match the fragment length. Default is to extend the reads if paired end information is available."/> - <param name="ignoreDuplicates" type="boolean" truevalue="--ignoreDuplicates" falsevalue="" - label="Ignore duplicates" - help="If set, reads that have the same orientation and start position will be considered only once. If reads are paired, the mate position also has to coincide to ignore a read." /> + <param name="ignoreDuplicates" type="boolean" truevalue="--ignoreDuplicates" falsevalue="" + label="Ignore duplicates" + help="If set, reads that have the same orientation and start position will be considered only once. If reads are paired, the mate position also has to coincide to ignore a read." /> + + <param name="minMappingQuality" type="integer" optional="true" value="1" min="1" + label="Minimum mapping quality (e.g. BOWTIE2 measures)" + help= "If set, only reads that have a mapping quality score higher than the given value are considered. *Note* Bowtie's Mapping quality is related to uniqueness: the higher the score, the more unique is a read. A mapping quality defined by Bowtie of 10 or less indicates that there is at least a 1 in 10 chance that the read truly originated elsewhere."/> - <param name="minMappingQuality" type="integer" optional="true" value="1" min="1" - label="Minimum mapping quality (e.g. BOWTIE2 measures)" - help= "If set, only reads that have a mapping quality score higher than the given value are considered. *Note* Bowtie's Mapping quality is related to uniqueness: the higher the score, the more unique is a read. A mapping quality defined by Bowtie of 10 or less indicates that there is at least a 1 in 10 chance that the read truly originated elsewhere."/> + <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 treated as zeros. If unchecked, missing data will be ignored and not included in the output file. Missing data is defined as those regions for which both BAM files have 0 reads." /> - <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 treated as zeros. If unchecked, missing data will be ignored and not included in the output file. Missing data is defined as those regions for which both BAM files have 0 reads." /> + <param name="ignoreForNormalization" type="text" value="" size="50" + label="regions that should be excluded for calculating the scaling factor" + help="Sometimes it makes sense to exclude certain regions when calculating the scaling factor. For example, if you know some regions that you suspect to be present more often in your sample's genome than in the reference genome that will therefore accumulate reads (CNV). Another typical example is the single X chromosome in male samples that should be scaled separately from the diploid autosomes. For example chrX,chrY,chr3. or chr10:12220-128932" /> + </when> </conditional>
--- a/bamCoverage.xml Mon Dec 16 15:13:08 2013 -0500 +++ b/bamCoverage.xml Sat Dec 21 14:26:06 2013 -0500 @@ -26,10 +26,6 @@ --scaleFactor $scaling.scaleFactor #end if - ##if str($ignoreForNormalization).strip() != '': - ## --ignoreForNormalization $ignoreForNormalization - ##end if - #if $advancedOpt.showAdvancedOpt == "yes": #if $advancedOpt.smoothLength: --smoothLength '$advancedOpt.smoothLength' @@ -45,6 +41,10 @@ --minMappingQuality '$advancedOpt.minMappingQuality' #end if + ##if str($advancedOpt.ignoreForNormalization).strip() != '': + ## --ignoreForNormalization $advancedOpt.ignoreForNormalization + ##end if + #end if </command> @@ -80,13 +80,6 @@ </when> </conditional> - <!-- - Not yet supported. - <param name="ignoreForNormalization" type="text" value="" size="50" - label="regions that should be excluded for calculating the scaling factor" - help="Sometimes it makes sense to exclude certain regions when calculating the scaling factor. For example, if you know some regions that you suspect to be present more often in your sample's genome than in the reference genome that will therefore accumulate reads (CNV). Another typical example is the single X chromosome in male samples that should be scaled separately from the diploid autosomes. For example chrX,chrY,chr3. or chr10:12220-128932" /> - --> - <param name="outFileFormat" type="select" label="Coverage file format"> <option value="bigwig" selected="true">bigwig</option> <option value="bedgraph">bedgraph</option> @@ -118,6 +111,11 @@ <param name="minMappingQuality" type="integer" optional="true" value="1" min="1" label="Minimum mapping quality" help= "If set, only reads that have a mapping quality score higher than the given value are considered. *Note* Bowtie's Mapping quality is related to uniqueness: the higher the score, the more unique is a read. A mapping quality defined by Bowtie of 10 or less indicates that there is at least a 1 in 10 chance that the read truly originated elsewhere."/> + + <!-- <param name="ignoreForNormalization" type="text" value="" size="50" + label="regions that should be excluded for calculating the scaling factor" + help="Sometimes it makes sense to exclude certain regions when calculating the scaling factor. For example, if you know some regions that you suspect to be present more often in your sample's genome than in the reference genome that will therefore accumulate reads (CNV). Another typical example is the single X chromosome in male samples that should be scaled separately from the diploid autosomes. For example chrX,chrY,chr3. or chr10:12220-128932" /> + --> </when> </conditional> </inputs>
--- a/deepTools_macros.xml Mon Dec 16 15:13:08 2013 -0500 +++ b/deepTools_macros.xml Sat Dec 21 14:26:06 2013 -0500 @@ -43,7 +43,7 @@ <requirement type="package" >samtools</requirement> <requirement type="package" >deepTools</requirement> <requirement type="package" >ucsc_tools</requirement> - <requirement type="package" version="1.5.4_74aac0843a956ca352e3e85087f20c8f158e2f7d">deepTools</requirement> + <requirement type="package" version="1.5.4_e5c75f3e967be0fa1d6dbcbb63a0f992e1cdcd61">deepTools</requirement> <requirement type="package" version="0.1">ucsc_tools</requirement> <requirement type="package" version="1.7.1">numpy</requirement> <requirement type="package" version="0.7.7">pysam</requirement>
--- a/heatmapper.xml Mon Dec 16 15:13:08 2013 -0500 +++ b/heatmapper.xml Sat Dec 21 14:26:06 2013 -0500 @@ -80,9 +80,11 @@ $advancedOpt.onePlotPerGroup - #if $advancedOpt.clustering.clustering_options == 'kmeans': - #if int($advancedOpt.clustering.k_kmeans) > 0: - --kmeans $advancedOpt.clustering.k_kmeans + #if $advancedOpt.used_multiple_regions.used_multiple_regions_options == 'yes': + #if $advancedOpt.used_multiple_regions.clustering.clustering_options == 'kmeans': + #if int($advancedOpt.used_multiple_regions.clustering.k_kmeans) > 0: + --kmeans $advancedOpt.used_multiple_regions.clustering.k_kmeans + #end if #end if #end if @@ -156,23 +158,41 @@ <param name="endLabel" type="text" value="TES" size="10" label="Label for the region end" help="[only for scale-regions mode] Label shown in the plot for the region end. Default is TES (transcription end site)."/> <param name="referencePointLabel" type="text" value="TSS" size="10" label="Reference point label" help ="[only for scale-regions mode] Label shown in the plot for the reference-point. Default is the same as the reference point selected (e.g. TSS), but could be anything, e.g. "peak start" etc." /> - <param name="regionsLabel" type="text" value="genes" size="30" label="Labels for the regions plotted in the heatmap" help="If more than one region is being plotted a list of labels separated by comma and limited by quotes, is required. For example, "label1, label2"."/> + <param name="regionsLabel" type="text" value="genes" size="30" + label="Labels for the regions plotted in the heatmap" + help="If more than one region is being plotted a list of labels separated by comma and limited by quotes, is required. For example, label1, label2."> + <sanitizer> + <valid initial="string.printable"> + </valid> + </sanitizer> + </param> <param name="plotTitle" type="text" value="" size="30" label="Title of the plot" help="Title of the plot, to be printed on top of the generated image. Leave blank for no title." /> - <param name="onePlotPerGroup" type="boolean" truevalue="--onePlotPerGroup" falsevalue="" label="Do one plot per group" help="When the region file contains groups separated by "#", the default is to plot the averages for the distinct plots in one plot. If this option is set, each group will get its own plot, stacked on top of each other."/> + <param name="onePlotPerGroup" type="boolean" truevalue="--onePlotPerGroup" falsevalue="" + label="Do one plot per group" + help="When computeMatrix was used on more than one group of genes, the average plots for all the groups will be drawn in one panel by default. If this option is set, each group will get its own plot, stacked on top of each other."/> - <conditional name="clustering"> - <param name="clustering_options" type="select" label="Clustering algorithm"> - <option value="none">No clustering</option> - <option value="kmeans">Kmeans clustering</option> + <conditional name="used_multiple_regions"> + <param name="used_multiple_regions_options" type="select" + label="Did you used multiple regions in ComputeMatrix?" + help="That option is only relevant if you want to cluster the results. Clustering is only available with one selected region in ComputeMatrix."> + <option value="no">No, I used only one region.</option> + <option value="yes">Yes, I used multiple regions.</option> </param> - <when value="kmeans"> - <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 value="yes"> + <conditional name="clustering"> + <param name="clustering_options" type="select" label="Clustering algorithm"> + <option value="none">No clustering</option> + <option value="kmeans">Kmeans clustering</option> + </param> + <when value="kmeans"> + <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" /> + </conditional> </when> - <when value="none" /> + <when value="no" /> </conditional> - - </when> </conditional> </inputs>
--- a/tool_dependencies.xml Mon Dec 16 15:13:08 2013 -0500 +++ b/tool_dependencies.xml Sat Dec 21 14:26:06 2013 -0500 @@ -57,7 +57,7 @@ <readme>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.</readme> </package> - <package name="deepTools" version="1.5.4_74aac0843a956ca352e3e85087f20c8f158e2f7d"> + <package name="deepTools" version="1.5.4_e5c75f3e967be0fa1d6dbcbb63a0f992e1cdcd61"> <install version="1.0"> <actions> <action type="shell_command">git clone --recursive https://github.com/fidelram/deepTools.git</action> @@ -79,7 +79,7 @@ <package name="scipy" version="0.12.0" /> </repository> </action> - <action type="shell_command">git reset --hard 74aac0843a956ca352e3e85087f20c8f158e2f7d</action> + <action type="shell_command">git reset --hard e5c75f3e967be0fa1d6dbcbb63a0f992e1cdcd61</action> <action type="make_directory">$INSTALL_DIR/lib/python</action> <action type="shell_command"> export PYTHONPATH=$PYTHONPATH:$INSTALL_DIR/lib/python &&