Mercurial > repos > nilesh > rseqc
diff RPKM_saturation.xml @ 32:580ee0c4bc4e
Fixes from Bjorn Gruning: create symlinks under $TMP and clean them up afterwards, replace R dependency with the Tool Shed R3 package, add --install-scripts, prepend tool-ids with rseqc
author | lparsons |
---|---|
date | Mon, 07 Oct 2013 15:01:13 -0400 |
parents | cc5eaa9376d8 |
children |
line wrap: on
line diff
--- a/RPKM_saturation.xml Wed Oct 02 02:20:04 2013 -0400 +++ b/RPKM_saturation.xml Mon Oct 07 15:01:13 2013 -0400 @@ -1,72 +1,72 @@ -<tool id="RPKM_saturation" name="RPKM Saturation" version="1.1"> - <description>calculates raw count and RPKM values for transcript at exon, intron, and mRNA level</description> - <requirements> - <requirement type="package" version="2.11.0">R</requirement> - <requirement type="package" version="1.7.1">numpy</requirement> - <requirement type="package" version="2.3.7">rseqc</requirement> - </requirements> - <command> RPKM_saturation.py -i $input -o output -r $refgene - - #if str($strand_type.strand_specific) == "pair" - -d - #if str($strand_type.pair_type) == "sd" - '1++,1--,2+-,2-+' - #else - '1+-,1-+,2++,2--' - #end if - #end if - - #if str($strand_type.strand_specific) == "single" - -d - #if str($strand_type.single_type) == "s" - '++,--' - #else - '+-,-+' - #end if - #end if - - -l $percentileFloor -u $percentileCeiling -s $percentileStep -c $rpkmCutoff +<tool id="rseqc_RPKM_saturation" name="RPKM Saturation" version="1.1"> + <description>calculates raw count and RPKM values for transcript at exon, intron, and mRNA level</description> + <requirements> + <requirement type="package" version="3.0.1">R</requirement> + <requirement type="package" version="1.7.1">numpy</requirement> + <requirement type="package" version="2.3.7">rseqc</requirement> + </requirements> + <command> RPKM_saturation.py -i $input -o output -r $refgene - </command> - <inputs> - <param name="input" type="data" format="bam" label="input bam/sam file" /> - <param name="refgene" type="data" format="bed" label="Reference gene model" /> - <conditional name="strand_type"> - <param name="strand_specific" type="select" label="Strand-specific?" value="None"> - <option value="none">None</option> - <option value="pair">Pair-End RNA-seq</option> - <option value="single">Single-End RNA-seq</option> - </param> - <when value="pair"> - <param name="pair_type" type="select" display="radio" label="Pair-End Read Type (format: mapped --> parent)" value="sd"> - <option value="sd"> read1 (positive --> positive; negative --> negative), read2 (positive --> negative; negative --> positive)</option> - <option value="ds">read1 (positive --> negative; negative --> positive), read2 (positive --> positive; negative --> negative)</option> - </param> - </when> - <when value="single"> - <param name="single_type" type="select" display="radio" label="Single-End Read Type (format: mapped --> parent)" value="s"> - <option value="s">positive --> positive; negative --> negative</option> - <option value="d">positive --> negative; negative --> positive</option> - </param> - </when> - <when value="none"></when> - </conditional> - <param name="percentileFloor" type="integer" value="5" label="Begin sampling from this percentile (default=5)" /> - <param name="percentileCeiling" type="integer" value="100" label="End sampling at this percentile (default=100)" /> - <param name="percentileStep" type="integer" value="5" label="Sampling step size (default=5)" /> - <param name="rpkmCutoff" type="text" value="0.01" label="Ignore transcripts with RPKM smaller than this number (default=0.01)" /> - </inputs> - <outputs> - <data format="xls" name="outputxls" from_work_dir="output.eRPKM.xls" label="${tool.name} on ${on_string} (RPKM XLS)"/> - <data format="xls" name="outputrawxls" from_work_dir="output.rawCount.xls" label="${tool.name} on ${on_string} (Raw Count XLS)"/> - <data format="r" name="outputr" from_work_dir="output.saturation.r" label="${tool.name} on ${on_string} (R Script)"/> - <data format="pdf" name="outputpdf" from_work_dir="output.saturation.pdf" label="${tool.name} on ${on_string} (PDF)"/> - </outputs> + #if str($strand_type.strand_specific) == "pair" + -d + #if str($strand_type.pair_type) == "sd" + '1++,1--,2+-,2-+' + #else + '1+-,1-+,2++,2--' + #end if + #end if + + #if str($strand_type.strand_specific) == "single" + -d + #if str($strand_type.single_type) == "s" + '++,--' + #else + '+-,-+' + #end if + #end if + + -l $percentileFloor -u $percentileCeiling -s $percentileStep -c $rpkmCutoff + + </command> <stdio> <exit_code range="1:" level="fatal" description="An error occured during execution, see stderr and stdout for more information" /> <regex match="[Ee]rror" source="both" description="An error occured during execution, see stderr and stdout for more information" /> </stdio> - <help> + <inputs> + <param name="input" type="data" format="bam" label="input bam/sam file" /> + <param name="refgene" type="data" format="bed" label="Reference gene model" /> + <conditional name="strand_type"> + <param name="strand_specific" type="select" label="Strand-specific?" value="None"> + <option value="none">None</option> + <option value="pair">Pair-End RNA-seq</option> + <option value="single">Single-End RNA-seq</option> + </param> + <when value="pair"> + <param name="pair_type" type="select" display="radio" label="Pair-End Read Type (format: mapped --> parent)" value="sd"> + <option value="sd"> read1 (positive --> positive; negative --> negative), read2 (positive --> negative; negative --> positive)</option> + <option value="ds">read1 (positive --> negative; negative --> positive), read2 (positive --> positive; negative --> negative)</option> + </param> + </when> + <when value="single"> + <param name="single_type" type="select" display="radio" label="Single-End Read Type (format: mapped --> parent)" value="s"> + <option value="s">positive --> positive; negative --> negative</option> + <option value="d">positive --> negative; negative --> positive</option> + </param> + </when> + <when value="none"></when> + </conditional> + <param name="percentileFloor" type="integer" value="5" label="Begin sampling from this percentile (default=5)" /> + <param name="percentileCeiling" type="integer" value="100" label="End sampling at this percentile (default=100)" /> + <param name="percentileStep" type="integer" value="5" label="Sampling step size (default=5)" /> + <param name="rpkmCutoff" type="text" value="0.01" label="Ignore transcripts with RPKM smaller than this number (default=0.01)" /> + </inputs> + <outputs> + <data format="xls" name="outputxls" from_work_dir="output.eRPKM.xls" label="${tool.name} on ${on_string} (RPKM XLS)"/> + <data format="xls" name="outputrawxls" from_work_dir="output.rawCount.xls" label="${tool.name} on ${on_string} (Raw Count XLS)"/> + <data format="txt" name="outputr" from_work_dir="output.saturation.r" label="${tool.name} on ${on_string} (R Script)"/> + <data format="pdf" name="outputpdf" from_work_dir="output.saturation.pdf" label="${tool.name} on ${on_string} (PDF)"/> + </outputs> + <help> RPKM_saturation.py ++++++++++++++++++ @@ -93,22 +93,22 @@ ++++++++++++++ Input BAM/SAM file - Alignment file in BAM/SAM format. + Alignment file in BAM/SAM format. Reference gene model - Gene model in BED format. + Gene model in BED format. Strand sequencing type (default=none) - See Infer Experiment tool if uncertain. + See Infer Experiment tool if uncertain. Options ++++++++++++++ Skip Multiple Hit Reads - Use Multiple hit reads or use only uniquely mapped reads. + Use Multiple hit reads or use only uniquely mapped reads. Only use exonic reads - Renders program only used exonic (UTR exons and CDS exons) reads, otherwise use all reads. + Renders program only used exonic (UTR exons and CDS exons) reads, otherwise use all reads. Output ++++++++++++++ @@ -124,10 +124,10 @@ :scale: 80 % - All transcripts were sorted in ascending order according to expression level (RPKM). Then they are divided into 4 groups: - 1. Q1 (0-25%): Transcripts with expression level ranked below 25 percentile. - 2. Q2 (25-50%): Transcripts with expression level ranked between 25 percentile and 50 percentile. - 3. Q3 (50-75%): Transcripts with expression level ranked between 50 percentile and 75 percentile. - 4. Q4 (75-100%): Transcripts with expression level ranked above 75 percentile. + 1. Q1 (0-25%): Transcripts with expression level ranked below 25 percentile. + 2. Q2 (25-50%): Transcripts with expression level ranked between 25 percentile and 50 percentile. + 3. Q3 (50-75%): Transcripts with expression level ranked between 50 percentile and 75 percentile. + 4. Q4 (75-100%): Transcripts with expression level ranked above 75 percentile. - BAM/SAM file containing more than 100 million alignments will make module very slow. - Follow example below to visualize a particular transcript (using R console):: @@ -156,5 +156,5 @@ .. _RSeQC: http://rseqc.sourceforge.net/ - </help> + </help> </tool>