Mercurial > repos > yhoogstrate > varscan_mpileup2indel_from_bam

comparison varscan_mpileup2indel.xml @ 1:2c56a59a112f draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/ErasmusMC-Bioinformatics/galaxytools-emc/tree/master/tools/galaxy-tool-shed-tools commit bd543e68c1af82bcd6a04f0ae3d1180e8887e122
author erasmus-medical-center
date Wed, 15 Feb 2017 16:15:21 -0500
parents 10e2ea79ec55
children
comparison
equal deleted inserted replaced
0:10e2ea79ec55 1:2c56a59a112f
1 <?xml version="1.0" encoding="UTF-8"?> 1 <?xml version="1.0" encoding="UTF-8"?>
2 <tool id="varscan_mpileup2indel" name="VarScan2 Call INDELs from a mpileup file" version="2.3.6.a"> 2 <tool id="varscan_mpileup2indel" name="VarScan2 Call INDELs from a mpileup file" version="2.4.2.a">
3 <description>VarScan2 INDEL detection; directly from a *.mpileup file.</description> 3 <description>VarScan2 INDEL detection (on mpileup data)</description>
4 4
5 <requirements> 5 <requirements>
6 <requirement type="package" version="2.3.6">varscan</requirement> 6 <requirement type="package" version="2.4.2">varscan</requirement>
7 </requirements> 7 </requirements>
8 8
9 <version_command>java -jar $JAVA_JAR_PATH/VarScan.v2.3.6.jar 2>&amp;1 | head -n 1</version_command> 9 <version_command>varscan 2&gt;&amp;1 | head -n 1</version_command>
10 10
11 <command> 11 <command detect_errors="exit_code"><![CDATA[
12 cat $mpileup_input | java 12 varscan mpileup2indel
13 -Xmx64G 13
14 -jar \$JAVA_JAR_PATH/VarScan.v2.3.6.jar 14 '${mpileup_input}'
15 mpileup2indel 15
16 16 #if $extended_parameters.parameters == "extended"
17 #if $extended_parameters.parameters == "extended" 17 --min-coverage $extended_parameters.varscan_min_coverage
18 --min-coverage $extended_parameters.varscan_min_coverage 18 --min-reads2 $extended_parameters.varscan_min_reads2
19 --min-reads2 $extended_parameters.varscan_min_reads2 19 --min-avg-qual $extended_parameters.varscan_min_avg_qual
20 --min-avg-qual $extended_parameters.varscan_min_avg_qual 20 --min-var-freq $extended_parameters.varscan_min_var_freq
21 --min-var-freq $extended_parameters.varscan_min_var_freq 21 --min-freq-for-hom $extended_parameters.varscan_min_freq_for_hom
22 --min-freq-for-hom $extended_parameters.varscan_min_freq_for_hom 22 --p-value $extended_parameters.varscan_p_value
23 --p-value $extended_parameters.varscan_p_value 23 $extended_parameters.varscan_strand_filter
24 $extended_parameters.varscan_strand_filter 24 $extended_parameters.varscan_variants
25 $extended_parameters.varscan_variants 25 #end if
26 #end if 26
27 27 #if $varscan_output == "vcf" or $varscan_output.value == "vcf"
28 #if $varscan_output == "vcf" or $varscan_output.value == "vcf" 28 --output-vcf 1
29 --output-vcf 1 29 #end if
30 #end if 30
31 31 > '${snv_output}'
32 2> stderr.txt 32 ]]></command>
33 > $snv_output ;
34 cat stderr.txt
35 </command>
36 33
37 <inputs> 34 <inputs>
38 <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 <param name="mpileup_input" format="pileup" type="data" label="Alignment file"
36 help="Mapped reads in mpileup format."/>
39 37
40 <conditional name="extended_parameters"> 38 <conditional name="extended_parameters">
41 <param name="parameters" type="select" label="VarScan parameters" help="For more advanced VarScan settings."> 39 <param name="parameters" type="select" label="VarScan parameters" help="For more advanced VarScan settings.">
42 <option value="default">Default settings</option> 40 <option value="default">Default settings</option>
43 <option value="extended">Extended settings</option> 41 <option value="extended">Extended settings</option>
44 </param> 42 </param>
45 <when value="default"> 43 <when value="default">
46 </when> 44 </when>
47 <when value="extended"> 45 <when value="extended">
48 <param type="integer" name="varscan_min_coverage" value="8" label="VarScan: Minimum read depth at a position to make a call [8]" /> 46 <param type="integer" name="varscan_min_coverage" value="8" label="Minimum read depth at a position to make a call [8]" />
49 <param type="integer" name="varscan_min_reads2" value="2" label="VarScan: PMinimum supporting reads at a position to call variants [2]" /> 47 <param type="integer" name="varscan_min_reads2" value="2" label="Minimum supporting reads at a position to call variants [2]" />
50 <param type="integer" name="varscan_min_avg_qual" value="15" label="VarScan: Minimum base quality at a position to count a read [15]" /> 48 <param type="integer" name="varscan_min_avg_qual" value="15" label="Minimum base quality at a position to count a read [15]" />
51 <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" /> 49 <param type="float" name="varscan_min_var_freq" value="0.01" label="minimum fraction of gapped reads for candidates [0.002]" help="Alias: -F" />
52 <param type="float" name="varscan_min_freq_for_hom" value="0.75" label="VarScan: Minimum frequency to call homozygote [0.75]" /> 50 <param type="float" name="varscan_min_freq_for_hom" value="0.75" label="Minimum frequency to call homozygote [0.75]" />
53 <param type="float" name="varscan_p_value" value="0.99" label="VarScan: Default p-value threshold for calling variants [99e-02]" /> 51 <param type="float" name="varscan_p_value" value="0.99" label="Default p-value threshold for calling variants [99e-02]" />
54 <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]" /> 52 <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]" />
55 <param type="boolean" name="varscan_variants" falsevalue=" --variants 0" truevalue=" --variants 1" checked="false" label="VarScan: Report only variant (SNP/indel) positions [0]" /> 53 <param type="boolean" name="varscan_variants" falsevalue=" --variants 0" truevalue=" --variants 1" checked="false" label="VarScan: Report only variant (SNP/indel) positions [0]" />
56 </when> 54 </when>
57 </conditional> 55 </conditional>
58 56
79 <output name="snv_output" file="example.vcf" /> 77 <output name="snv_output" file="example.vcf" />
80 </test> 78 </test>
81 </tests> 79 </tests>
82 80
83 <help> 81 <help>
84 **VarScan 2.3.6** 82 **VarScan 2.4.2**
85 83
86 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. 84 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.
87 http://dx.doi.org/10.1101/gr.129684.111 85 http://dx.doi.org/10.1101/gr.129684.111
88 http://www.ncbi.nlm.nih.gov/pubmed/19542151 86 http://www.ncbi.nlm.nih.gov/pubmed/19542151
89 87
90 *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.
91 The samtools package is not able to parallelize the mpileup generation which make it a very slow process.
92 Other people were aware of this and have written a version that can do parallelization:
93 https://github.com/mydatascience/parallel-mpileup
94
95 Consequently, when a BAM files gets processed by this wrapper, it's processed by *parallel-mpileup* before its send to VarScan.
96
97 .. _VarScan: http://varscan.sourceforge.net/
98
99 **Input formats** 88 **Input formats**
100 89
101 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. 90 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.
102 91
103 **Installation** 92 **Installation**
104 93
105 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. 94 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.
106
107 **License**
108
109 * VarScan2.3.6: Non-Profit Open Software License 3.0 (Non-Profit OSL 3.0)
110 * parallel-mpileup: MIT License (https://github.com/mydatascience/parallel-mpileup/blob/master/samtools-0.1.19/COPYING)
111
112 Contact
113 -------
114
115 The tool wrapper has been written by Youri Hoogstrate from the Erasmus
116 Medical Center (Rotterdam, Netherlands) on behalf of the Translational
117 Research IT (TraIT) project:
118
119 http://www.ctmm.nl/en/programmas/infrastructuren/traitprojecttranslationeleresearch
120
121 More tools by the Translational Research IT (TraIT) project can be found
122 in the following toolsheds:
123
124 http://toolshed.g2.bx.psu.edu/
125
126 http://testtoolshed.g2.bx.psu.edu/
127 </help> 95 </help>
128 <citations> 96 <citations>
129 <citation type="doi">10.1101/gr.129684.111</citation> 97 <citation type="doi">10.1101/gr.129684.111</citation>
130 </citations> 98 </citations>
131 </tool> 99 </tool>