Mercurial > repos > nilesh > rseqc
diff RPKM_saturation.xml @ 49:6b33e31bda10 draft
Uploaded tar based on https://github.com/lparsons/galaxy_tools/tree/master/tools/rseqc 1a3c419bc0ded7c40cb2bc3e7c87bfb01ddfeba2
author | lparsons |
---|---|
date | Thu, 16 Jul 2015 17:43:43 -0400 |
parents | eb339c5849bb |
children | f242ee103277 |
line wrap: on
line diff
--- a/RPKM_saturation.xml Tue Apr 21 10:27:06 2015 -0400 +++ b/RPKM_saturation.xml Thu Jul 16 17:43:43 2015 -0400 @@ -1,11 +1,22 @@ -<tool id="rseqc_RPKM_saturation" name="RPKM Saturation" version="2.4"> +<tool id="rseqc_RPKM_saturation" name="RPKM Saturation" version="2.4galaxy1"> <description>calculates raw count and RPKM values for transcript at exon, intron, and mRNA level</description> + + <macros> + <import>rseqc_macros.xml</import> + </macros> + <requirements> - <requirement type="package" version="3.0.3">R</requirement> - <requirement type="package" version="1.7.1">numpy</requirement> - <requirement type="package" version="2.4">rseqc</requirement> + <expand macro="requirement_package_r" /> + <expand macro="requirement_package_numpy" /> + <expand macro="requirement_package_rseqc" /> </requirements> - <command> RPKM_saturation.py -i $input -o output -r $refgene + + <expand macro="stdio" /> + + <version_command><![CDATA[RPKM_saturation.py --version]]></version_command> + + <command><![CDATA[ + RPKM_saturation.py -i $input -o output -r $refgene #if str($strand_type.strand_specific) == "pair" -d @@ -26,15 +37,12 @@ #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> + <inputs> - <param name="input" type="data" format="bam" label="input bam/sam file" /> - <param name="refgene" type="data" format="bed" label="Reference gene model" /> + <param name="input" type="data" label="Input .bam File" format="bam" help="(--input-file)"/> + <param name="refgene" type="data" format="bed" label="reference gene model" help="(--refgene)"/> <conditional name="strand_type"> <param name="strand_specific" type="select" label="Strand-specific?" value="None"> <option value="none">None</option> @@ -42,31 +50,46 @@ <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"> + <param name="pair_type" type="select" display="radio" label="Pair-End Read Type (format: mapped --> parent)" value="sd" help="(--strand)"> <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"> + <param name="single_type" type="select" display="radio" label="Single-End Read Type (format: mapped --> parent)" value="s" help="(--strand)"> <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)" /> + <param name="percentileFloor" type="integer" value="5" label="Begin sampling from this percentile (default=5)" help="(--percentile-floor)"/> + <param name="percentileCeiling" type="integer" value="100" label="End sampling at this percentile (default=100)" help="(--percentile-ceiling)" /> + <param name="percentileStep" type="integer" value="5" label="Sampling step size (default=5)" help="(--percentile-step)" /> + <param name="rpkmCutoff" type="text" value="0.01" label="Ignore transcripts with RPKM smaller than this number (default=0.01)" help="(--rpkm-cutoff)" /> + <param name="mapq" value="30" type="integer" label="Minimum mapping quality for an alignment to be called 'uniquly mapped'" help="(--mapq)" /> </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> + + <!-- Unable to succefully run this script with test data + <tests> + <test> + <param name="input" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam"/> + <param name="refgene" value="hg19_RefSeq_chr1_1-100000.bed"/> + <output name="outputxls" file="output.eRPKM.xls"/> + <output name="outputrawxls" file="output.rawCount.xls"/> + <output name="outputr" file="output.saturation.r"/> + </test> + </tests> + --> + + <help><![CDATA[ RPKM_saturation.py ++++++++++++++++++ @@ -77,7 +100,7 @@ the current sequencing depth was saturated or not (or if the RPKM values were stable or not) in terms of genes' expression estimation. If sequencing depth was saturated, the estimated RPKM value will be stationary or reproducible. By default, this module will calculate 20 -RPKM values (using 5%, 10%, ... , 95%,100% of total reads) for each transcripts. +RPKM values (using 5%, 10%, ... , 95%,100% of total reads) for each transcripts. In the output figure, Y axis is "Percent Relative Error" or "Percent Error" which is used to measures how the RPKM estimated from subset of reads (i.e. RPKMobs) deviates from real @@ -107,7 +130,7 @@ Skip Multiple Hit Reads Use Multiple hit reads or use only uniquely mapped reads. -Only use exonic reads +Only use exonic reads Renders program only used exonic (UTR exons and CDS exons) reads, otherwise use all reads. Output @@ -121,7 +144,7 @@ .. image:: http://rseqc.sourceforge.net/_images/saturation.png :height: 600 px :width: 600 px - :scale: 80 % + :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. @@ -140,11 +163,11 @@ .. image:: http://rseqc.sourceforge.net/_images/saturation_eg.png :height: 600 px :width: 600 px - :scale: 80 % + :scale: 80 % ----- -About RSeQC +About RSeQC +++++++++++ The RSeQC_ package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. "Basic modules" quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while "RNA-seq specific modules" investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. @@ -154,7 +177,9 @@ .. image:: http://rseqc.sourceforge.net/_static/logo.png .. _RSeQC: http://rseqc.sourceforge.net/ - +]]> + </help> - </help> + <expand macro="citations" /> + </tool>