comparison varscan_mpileup2snp.xml @ 4:796653c6376b draft

Uploaded
author jason-ellul
date Wed, 01 Jun 2016 02:36:11 -0400
parents
children
comparison
equal deleted inserted replaced
3:8c9b1fa6c456 4:796653c6376b
1 <?xml version="1.0" encoding="UTF-8"?>
2 <tool id="varscan_mpileup2snp" name="VarScan2 Call SNPs from a mpileup file">
3 <description>VarScan2 SNP/SNV detection; directly from a *.mpileup file.</description>
4 <requirements>
5 <requirement type="package" version="2.3.6">VarScan</requirement>
6 </requirements>
7 <command>
8 cat $mpileup_input | java
9 -Xmx64G
10 -jar \$JAVA_JAR_PATH/VarScan.v2.3.6.jar
11 mpileup2snp
12
13 #if $extended_parameters.parameters == "extended"
14 --min-coverage $varscan_min_coverage
15 --min-reads2 $varscan_min_reads2
16 --min-avg-qual $varscan_min_avg_qual
17 --min-var-freq $varscan_min_var_freq
18 --min-freq-for-hom $varscan_min_freq_for_hom
19 --p-value $varscan_p_value
20 $varscan_strand_filter
21 $varscan_variants
22 #end if
23
24 #if $varscan_output_vcf
25 --output-vcf 1
26 #end if
27
28 2> stderr.txt
29 > $snv_output ;
30 cat stderr.txt
31 </command>
32
33 <inputs>
34 <param format="pileup" name="mpileup_input" type="data" label="Alignment file" help="Mapped reads in mpileup format."/><!-- datatype "mpileup" does not exist.. it seems to be common to use pileup instead? -->
35
36 <conditional name="extended_parameters">
37 <param name="parameters" type="select" label="VarScan parameters" help="For more advanced VarScan settings.">
38 <option value="default">Default settings</option>
39 <option value="extended">Extended settings</option>
40 </param>
41 <when value="default">
42 </when>
43 <when value="extended">
44 <param type="integer" name="varscan_min_coverage" value="8" label="VarScan: Minimum read depth at a position to make a call [8]" />
45 <param type="integer" name="varscan_min_reads2" value="2" label="VarScan: PMinimum supporting reads at a position to call variants [2]" />
46 <param type="integer" name="varscan_min_avg_qual" value="15" label="VarScan: Minimum base quality at a position to count a read [15]" />
47 <param type="float" name="varscan_min_var_freq" value="0.01" label="VarScan: minimum fraction of gapped reads for candidates [0.002]" help="Alias: -F" />
48 <param type="float" name="varscan_min_freq_for_hom" value="0.75" label="VarScan: Minimum frequency to call homozygote [0.75]" />
49 <param type="float" name="varscan_p_value" value="0.99" label="VarScan: Default p-value threshold for calling variants [99e-02]" />
50 <param type="boolean" name="varscan_strand_filter" falsevalue=" --strand_filter 0" truevalue=" --strand_filter 1" checked="true" label="VarScan: Ignore variants with >90% support on one strand [1]" />
51 <param type="boolean" name="varscan_variants" falsevalue=" --variants 0" truevalue=" --variants 1" checked="false" label="VarScan: Report only variant (SNP/indel) positions [0]" />
52 </when>
53 </conditional>
54
55 <param type="boolean" name="varscan_output_vcf" falsevalue="0" truevalue="1" label="VarScan: If set to 1, outputs in VCF format" />
56 </inputs>
57
58 <outputs>
59 <data format="tabular" name="snv_output" label="${tool.name} on ${mpileup_input.hid}: ${mpileup_input.name}">
60 <change_format>
61 <when input="varscan_output_vcf" value="1" format="vcf" />
62 </change_format>
63 </data>
64 </outputs>
65
66 <tests>
67 <test>
68 <param name="mpileup_input" value="hg19_mutant.mpileup" dbkey="hg19" ftype="pileup" />
69 <param name="parameters" value="default" />
70 <param name="varscan_output_vcf" value="1" />
71
72
73 <output name="snv_output" file="hg19_mutant.vcf" />
74 </test>
75 </tests>
76
77 <help>
78 **VarScan 2.3.6**
79
80 VarScan is a platform-independent mutation caller for targeted, exome, and whole-genome resequencing data generated on Illumina, SOLiD, Life/PGM, Roche/454, and similar instruments. The newest version, VarScan 2, is written in Java, so it runs on most operating systems.
81 http://dx.doi.org/10.1101/gr.129684.111
82 http://www.ncbi.nlm.nih.gov/pubmed/19542151
83
84 *VarScan* requires mpileup formatted input files, which are generally derived from BAM files. Since mpileup files can become humongous, the interim step of storing it is bypassed. Thus, in this wrapper one or multiple BAM/SAM files go in, get processed into a mpileup file and get directly linked to VarScan.
85 The samtools package is not able to parallelize the mpileup generation which make it a very slow process.
86 Other people were aware of this and have written a version that can do parallelization:
87 https://github.com/mydatascience/parallel-mpileup
88
89 Consequently, when a BAM files gets processed by this wrapper, it's processed by *parallel-mpileup* before its send to VarScan.
90
91 .. _VarScan: http://varscan.sourceforge.net/
92
93 **Input formats**
94
95 VarScan2 accepts sequencing alignments in the same, either SAM or BAM format (http://samtools.sourceforge.net/). The alignment files have to be linked to a reference genome by galaxy. This is indicated under every history item with e.g.: *"database: hg19"* for a link to hg19, or *"database: ?"* if the link is missing.
96
97 **Installation**
98
99 Make sure your reference genomes are properly annotated in "tool-data/all_fasta.loc", and linked to the names of the reference used for alignment.
100
101 **License**
102
103 * VarScan2.3.6: Non-Profit Open Software License 3.0 (Non-Profit OSL 3.0)
104 * parallel-mpileup: MIT License (https://github.com/mydatascience/parallel-mpileup/blob/master/samtools-0.1.19/COPYING)
105
106
107 **Contact**
108
109 The tool wrapper has been written by Youri Hoogstrate from the Erasmus Medical Center (Rotterdam, Netherlands) on behalf of the Translational Research IT (TraIT) project:
110 http://www.ctmm.nl/en/programmas/infrastructuren/traitprojecttranslationeleresearch
111
112 More tools by the Translational Research IT (TraIT) project can be found in the following repository:
113 http://toolshed.dtls.nl/
114 </help>
115 </tool>