# HG changeset patch
# User yhoogstrate
# Date 1391764446 18000
# Node ID ea9a28803468bdb5dfd69ee4b135d570757e91b3
# Parent  dc091c635cf0fcf2cc751368f03a1d7cb6d996e3
Uploaded

diff -r dc091c635cf0 -r ea9a28803468 varscan2_snp_from_bam.xml
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/varscan2_snp_from_bam.xml	Fri Feb 07 04:14:06 2014 -0500
@@ -0,0 +1,218 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<tool id="varscan_mpileup2snp_from_bam" name="VarScan2 Call SNPs from BAM">
+	<description>VarScan2 SNP/SNV detection (1: directly reading *.bam file(s), 2: using parallel mpileup generation, to avoid unncessairy I/O overhead and increase performance.</description>
+	<requirements>
+		<requirement type="package" version="1.0.19">samtools-mpileup-parallel</requirement>
+		<requirement type="package" version="2.3.6">VarScan</requirement>
+	</requirements>
+	<command>
+		#if $reference_genome_source.source_select == "attribute" and len({ alignment.metadata.dbkey:True for alignment in $alignments }.keys()) != 1
+			echo "Invalid number of dbkeys are found: ${ len({ alignment.metadata.dbkey:True for alignment in $alignments }.keys()) }, while only one should be used. Make sure that the alignments are done on the same reference genome and that 'tool-data/all_fasta.loc' is configured properly!" >&amp;2
+		#else
+			samtools-mpileup-parallel mpileup
+				-t $samtools_threads
+				-f 
+					#if $reference_genome_source.source_select == "indexed"
+						"$reference_genome_source.reference_genome"
+					#else if $reference_genome_source.source_select == "history"
+						"$reference_genome_source.reference_genome"
+					#else
+						<!--
+							This is a workaround to obtain the "genome.fa" file that
+							corresponds to the dbkey of the alignments.
+							Because this file is "calculated" during run-time, it can
+							be used in a workflow.
+						-->
+						"${ filter( lambda x: str( x[0] ) == str( { alignment.metadata.dbkey:True for alignment in $alignments }.keys()[0] ), $__app__.tool_data_tables[ 'all_fasta' ].get_fields() )[0][-1] }"
+					#end if
+			
+			#if $extended_parameters_regions.samtools_regions == "region"
+				-r $extended_parameters_regions.$samtools_r
+			#elif $extended_parameters_regions.samtools_regions == "regions_file_pos" or $extended_parameters_regions.samtools_regions == "regions_file_bed"
+				-l $extended_parameters_regions.$samtools_l
+			#end if
+			
+			#if $extended_parameters.parameters == "extended"
+				$extended_parameters.samtools_6
+				$extended_parameters.samtools_A
+				$extended_parameters.samtools_B
+				 -C $extended_parameters.samtools_C
+				 -d $extended_parameters.samtools_d
+				$extended_parameters.samtools_E
+				 -M $extended_parameters.samtools_M
+				$extended_parameters.samtools_R
+				 -q $extended_parameters.samtools_q
+				 -Q $extended_parameters.samtools_Q
+				
+				 -e $extended_parameters.samtools_e
+				 -F $extended_parameters.samtools_F
+				 -h $extended_parameters.samtools_h
+				$extended_parameters.samtools_I
+				 -L $extended_parameters.samtools_L
+				 -m $extended_parameters.samtools_m
+				 -o $extended_parameters.samtools_o
+				$extended_parameters.samtools_p
+				 -P $extended_parameters.samtools_P
+			#end if
+			
+			#for $alignment in $alignments
+				 ${alignment}
+			#end for
+			
+			 | java
+					 -Xmx64G
+					 -jar VarScan.v2.3.6.jar
+						 mpileup2snp
+			 
+			#if $extended_parameters.parameters == "extended"
+					 --min-coverage	 $varscan_min_coverage
+					 --min-reads2	   $varscan_min_reads2
+					 --min-avg-qual	 $varscan_min_avg_qual
+					 --min-var-freq	 $varscan_min_var_freq
+					 --min-freq-for-hom $varscan_min_freq_for_hom
+					 --p-value		  $varscan_p_value
+					$varscan_strand_filter
+					$varscan_output_vcf
+					$varscan_variants
+			#end if
+			
+			$varscan_output_vcf
+			 
+			 > $output_table
+		#end if
+	</command>
+	
+	<inputs>
+		<param format="bam,sam" multiple="true" name="alignments" type="data" label="Alignment file" help="Mapped reads in BAM or SAM format."/>
+		
+		<!-- Find out how to access the reference genome from the BAM file(s) -->
+		<conditional name="reference_genome_source">
+			<param name="source_select" type="select" label="Fasta Source">
+				<option value="indexed">Use a built-in index</option>
+				<option value="history">Use reference from the history</option>
+				<option value="attribute">Use a built-in index based on the 'metadata.dbkey' attribute; use this option in workflows?</option>
+			</param>
+			<when value="indexed">
+				<param name="reference_genome" type="select" label="Reference Genome used during alignment (fasta)" >
+					<options from_file="all_fasta.loc">
+						<column name="name" index="0"/>
+						<column name="dbkey" index="1"/>
+						<column name="value" index="3"/>
+						<filter type="data_meta" ref="alignments" multiple="false" key="dbkey" column="1" />
+						<validator type="no_options" message="No indexes are available for the selected input dataset" />
+					</options>
+				</param>
+			</when>
+			<when value="history">
+				<param name="reference_genome" format="fasta" type="data" label="Reference Genome used during alignment (fasta)" help="Reference genome (genome.fa) that corresponds to the *.bam file." />
+			</when>
+			
+		</conditional>
+		
+		<conditional name="extended_parameters_regions">
+			<param name="samtools_regions" type="select" label="VarScan parameters" help="For more advanced VarScan settings.">
+				<option value="entire_genome">Entire genome</option>
+				<option value="region">Specific region</option>
+				<option value="regions_file_pos">Specific positions (file); list of positions</option>
+				<option value="regions_file_bed">Specific regions (file); list of regions in BED</option>
+			</param>
+			<when value="entire_genome">
+			</when>
+			<when value="region">
+				<param type="text" name="samtools_r" label="Samtools: region in which pileup is generated" help="chr:pos or chr:start-end" />
+			</when>
+			<when value="regions_file_pos">
+				<param type="data" name="samtools_l" format="tabular" label="Samtools: list of positions (chr pos)" />
+			</when>
+			<when value="regions_file_bed">
+				<param type="data" name="samtools_l" format="bed"	 label="Samtools: specific regions (BED)" />
+			</when>
+		</conditional>
+		
+		<param type="integer" name="samtools_threads" value="8" min="1" label="Samtools: mpileup threads" />
+		
+		<conditional name="extended_parameters">
+			<param name="parameters" type="select" label="VarScan parameters" help="For more advanced VarScan settings.">
+				<option value="default">Default settings</option>
+				<option value="extended">Extended settings</option>
+			</param>
+			<when value="default">
+			</when>
+			<when value="extended">
+				<param type="boolean" name="samtools_6" falsevalue="" truevalue=" -6" label="Samtools: assume the quality is in the Illumina-1.3+ encoding" />
+				<param type="boolean" name="samtools_A" falsevalue="" truevalue=" -A" label="Samtools: count anomalous read pairs" />
+				<param type="boolean" name="samtools_B" falsevalue="" truevalue=" -B" label="Samtools: disable BAQ computation" />
+				<param type="integer" name="samtools_C" value="0"					 label="Samtools: parameter for adjusting mapQ; 0 to disable [0]" />
+				<param type="integer" name="samtools_d" value="250"				   label="Samtools: max per-BAM depth to avoid excessive memory usage [250]" />
+				<param type="boolean" name="samtools_E" falsevalue="" truevalue=" -E" label="Samtools: recalculate extended BAQ on the fly thus ignoring existing BQs" />
+				<param type="integer" name="samtools_M" value="60"					label="cap mapping quality at INT [60]" />
+				<param type="boolean" name="samtools_R" falsevalue="" truevalue=" -R" label="Samtools: ignore RG tags" />
+				<param type="integer" name="samtools_q" value="0"					 label="Samtools: skip alignments with mapQ smaller than INT [0]" />
+				<param type="integer" name="samtools_Q" value="13"					label="Samtools: skip bases with baseQ/BAQ smaller than INT [13]" />
+				
+				<param type="integer" name="samtools_e" value="20"					label="Samtools: Phred-scaled gap extension seq error probability [20]" />
+				<param type="float"   name="samtools_F" value="0.002"				 label="Samtools: minimum fraction of gapped reads for candidates [0.002]" help="Alias: -F" />
+				<param type="integer" name="samtools_h" value="100"				   label="Samtools: coefficient for homopolymer errors [100]" />
+				<param type="boolean" name="samtools_I" falsevalue="" truevalue=" -I" label="Samtools: do not perform indel calling" />
+				<param type="integer" name="samtools_L" value="250"				   label="Samtools: max per-sample depth for INDEL calling [250]" />
+				<param type="integer" name="samtools_m" value="1"					 label="Samtools: minimum gapped reads for indel candidates [1]" help="Alias: -m" />
+				<param type="integer" name="samtools_o" value="40"					label="Samtools: Phred-scaled gap open sequencing error probability [40]" />
+				<param type="boolean" name="samtools_p" falsevalue="" truevalue=" -p" label="Samtools: apply -m and -F per-sample to increase sensitivity" />
+				<param type="text"	name="samtools_P" value="all"				   label="Samtools: comma separated list of platforms for indels [all]" />
+				
+				<param type="integer" name="varscan_min_coverage"	 value="8"	label="VarScan: Minimum read depth at a position to make a call [8]" />
+				<param type="integer" name="varscan_min_reads2"	   value="2"	label="VarScan: PMinimum supporting reads at a position to call variants [2]" />
+				<param type="integer" name="varscan_min_avg_qual"	 value="15"   label="VarScan: Minimum base quality at a position to count a read [15]" />
+				<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" />
+				<param type="float"   name="varscan_min_freq_for_hom" value="0.75" label="VarScan: Minimum frequency to call homozygote [0.75]" />
+				<param type="float"   name="varscan_p_value"		  value="0.99" label="VarScan: Default p-value threshold for calling variants [99e-02]" />
+				<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]" />
+				<param type="boolean" name="varscan_variants"		 falsevalue=" --variants 0"	  truevalue=" --variants 1"					 label="VarScan: Report only variant (SNP/indel) positions [0]" />
+			</when>
+		</conditional>
+		
+		<param type="boolean" name="varscan_output_vcf" falsevalue=" --output-vcf 0" truevalue=" --output-vcf 1" label="VarScan: If set to 1, outputs in VCF format" />
+	</inputs>
+	
+	<outputs>
+		<data format="tabular" name="output_table" label="${tool.name} on ${', '.join([ str(a.hid)+': '+a.name for a in $alignments ])}" />
+	</outputs>
+	
+	<help>
+VarScan2.3.6:
+
+**VarScan2 Overview**
+
+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.
+http://dx.doi.org/10.1101/gr.129684.111
+http://www.ncbi.nlm.nih.gov/pubmed/19542151
+
+*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.
+The samtools package is not able to parallelize the mpileup generation which make it a very slow process.
+Other people were aware of this and have written a version that can do parallelization:
+https://github.com/mydatascience/parallel-mpileup
+
+Consequently, when a BAM files gets processed by this wrapper, it's processed by *parallel-mpileup* before its send to VarScan.
+
+.. _VarScan: http://varscan.sourceforge.net/
+
+**Input formats**
+
+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.
+
+**Installation**
+
+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.
+
+**License**
+
+* VarScan2.3.6: Non-Profit Open Software License 3.0 (Non-Profit OSL 3.0)
+* parallel-mpileup: MIT License (https://github.com/mydatascience/parallel-mpileup/blob/master/samtools-0.1.19/COPYING)
+
+
+**Contact**
+
+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:
+http://www.ctmm.nl/en/programmas/infrastructuren/traitprojecttranslationeleresearch
+</help>
+</tool>