comparison varscan_mpileup2indel_from_bam.xml @ 1:2c56a59a112f draft default tip

planemo upload for repository https://github.com/ErasmusMC-Bioinformatics/galaxytools-emc/tree/master/tools/galaxy-tool-shed-tools commit bd543e68c1af82bcd6a04f0ae3d1180e8887e122

0:10e2ea79ec55

<?xml version="1.0" encoding="UTF-8"?>
<tool id="varscan_mpileup2indel_from_bam" name="VarScan2 Call INDELs from BAM" version="2.3.6.a">
    <description>VarScan2 INDEL detection; directly reading *.bam file(s) &amp; using parallel mpileup generation, to avoid unnecessairy I/O overhead and increase performance.</description>
    
    <requirements>
        <requirement type="package" version="0.1.19a">samtools_parallel_mpileup_0_1_19a</requirement>
        <requirement type="package" version="0.1.19">samtools</requirement>
        <requirement type="package" version="2.3.6">varscan</requirement>
    </requirements>
    
    <version_command>java -jar $JAVA_JAR_PATH/VarScan.v2.3.6.jar 2>&amp;1 | head -n 1</version_command>
    
    <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
            #import os.path
            #for $alignment in $alignments
                <!-- @todo use the existence of $alignment.metadata.bam_index or $alignment.metadata['bam_index'] -->
                #if not os.path.isfile(str($alignment)+".bai")
                 echo "- Indexing alignment file: $alignment.name " ; 
                 samtools index $alignment 2>&amp;1 ; 
                #else
                 echo "- Skiping indexing: $alignment.name " ; 
                #end if
            #end for
            
            #if $mpileup_parallelization.mpileup_parallelization_select == "true"
                samtools-parallel-mpileup mpileup
                -t $mpileup_parallelization.samtools_threads
            #else
                samtools mpileup
            #end if
                -f 
                    #if $reference_genome_source.source_select == "indexed_filtered"
                        "$reference_genome_source.reference_genome"
                    #else if $reference_genome_source.source_select == "indexed_all"
                        "$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
             2>stderr_1.txt
            
            #if $mpileup_parallelization.mpileup_parallelization_select == "true"
                #if $mpileup_parallelization.sort_mpileup
                 | sort -k1,1V -k2,2g 
                #end if
            #end if
            
             | java
                     -Xmx64G
                     -jar \$JAVA_JAR_PATH/VarScan.v2.3.6.jar
                         mpileup2indel
             
            #if $extended_parameters.parameters == "extended"
                     --min-coverage     $extended_parameters.varscan_min_coverage
                     --min-reads2       $extended_parameters.varscan_min_reads2
                     --min-avg-qual     $extended_parameters.varscan_min_avg_qual
                     --min-var-freq     $extended_parameters.varscan_min_var_freq
                     --min-freq-for-hom $extended_parameters.varscan_min_freq_for_hom
                     --p-value          $extended_parameters.varscan_p_value
                                        $extended_parameters.varscan_strand_filter 
                                        $extended_parameters.varscan_variants 
            #end if
            
            #if $varscan_output == "vcf" or $varscan_output.value == "vcf"
             --output-vcf 1 
            #end if
            
             2>stderr_2.txt 
             > $snv_output ;
             
             
             echo "---------------[ mpileup generation ]---------------" ;
             cat stderr_1.txt ;
             echo "" ;
             echo "---------------[ VarScan INDEL detect ]-------------" ;
             cat stderr_2.txt ;
             echo "" ;
             echo "----------------------------------------------------" ;
        #end if
    </command>
    
    <inputs>
        <param format="bam,sam" multiple="true" name="alignments" type="data" label="Alignment file(s)" help="Mapped reads in BAM or SAM format."/>
        
        <!-- Find out how to access the reference genome from the BAM file(s) -->

            <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>
        
        <conditional name="mpileup_parallelization">
            <param name="mpileup_parallelization_select" type="select" label="Use parallelization for the mpileup generation (experimental)" help="Especially if larger numbers of bam/sam files are processed, or the file infrastructure is optimized for IO-paralellization, this feature might improve performance.">
                <option value="false" >False - uses classical samtools</option>
                <option value="true">True - uses (experimental) samtools mpileup-parallel</option>
            </param>
            <when value="false" />
            <when value="true">
                <param type="integer" name="samtools_threads" value="2" min="1" label="Samtools: mpileup threads" />
                <param type="boolean" name="sort_mpileup" truevalue="true" falsevalue="false" label="Sort mpileup file (SLOW)" help="Because parallelization may disrupt the outputs order, sorting can be conveniet for e.g. testing. Notice that this function has only use in a limited number of situations but consumes (much) resources. Only use it if it's really neccesairy." />
            </when>
        </conditional>
        
        <conditional name="extended_parameters">
            <param name="parameters" type="select" label="Advanced parameters" help="For more advanced VarScan and samtools settings.">

            
            <param name="parameters" value="default" />
            <param name="varscan_output_vcf" value="1" />
            
            
            <output name="snv_output" file="example.vcf" />
        </test>
        <test><!-- Use parallelized samtools -->
            <param name="alignments" value="example.bam" ftype="bam" />
            
            <param name="source_select" value="history" />
            <param name="reference_genome" value="example.fa" ftype="fasta" />
            
            <param name="samtools_regions" value="entire_genome" />
            
            <param name="mpileup_parallelization_select" value="true" />
            <param name="samtools_threads" value="2" />
            <param name="sort_mpileup" value="true" />
            
            <param name="parameters" value="default" />
            <param name="varscan_output_vcf" value="1" />
            
            
            <output name="snv_output" file="example.vcf" />
        </test>
    </tests>
    
    <help>
**VarScan 2.3.6**

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

**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

More tools by the Translational Research IT (TraIT) project can be found
in the following toolsheds:

http://toolshed.g2.bx.psu.edu/

http://testtoolshed.g2.bx.psu.edu/
    </help>
    <citations>
        <citation type="doi">10.1101/gr.129684.111</citation>
    </citations>
</tool>

1:2c56a59a112f

<?xml version="1.0" encoding="UTF-8"?>
<tool id="varscan_mpileup2indel_from_bam" name="VarScan2 Call INDELs from BAM" version="2.4.2.a">
    <description>VarScan2 INDEL detection; directly reading *.bam file(s) &amp; using parallel mpileup generation, to avoid unnecessairy I/O overhead and increase performance.</description>
    
    <requirements>
        <requirement type="package" version="2.4.2">varscan</requirement>
        <requirement type="package" version="0.6.5">sambamba</requirement>
    </requirements>
    
    <version_command>varscan 2&gt;&amp;1 | head -n 1</version_command>
    
    <command detect_errors="exit_code"><![CDATA[
        #for $alignment in $alignments
            ln -f -s '${alignment.metadata.bam_index}' '${alignment}.bai' &&
        #end for

        sambamba mpileup
            -t \${GALAXY_SLOTS:-4}
            
            #for $alignment in $alignments
                 '${alignment}'
            #end for
            
            --samtools
            -f 
                #if $reference_genome_source.source_select == "indexed_filtered"
                    '$reference_genome_source.reference_genome'
                #else if $reference_genome_source.source_select == "indexed_all"
                    '$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.sambamba_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

        | varscan mpileup2indel
         
        #if $extended_parameters.parameters == "extended"
                 --min-coverage     $extended_parameters.varscan_min_coverage
                 --min-reads2       $extended_parameters.varscan_min_reads2
                 --min-avg-qual     $extended_parameters.varscan_min_avg_qual
                 --min-var-freq     $extended_parameters.varscan_min_var_freq
                 --min-freq-for-hom $extended_parameters.varscan_min_freq_for_hom
                 --p-value          $extended_parameters.varscan_p_value
                                    $extended_parameters.varscan_strand_filter 
                                    $extended_parameters.varscan_variants 
        #end if
        
        #if $varscan_output == "vcf" or $varscan_output.value == "vcf"
            --output-vcf 1 
        #end if
        
         > '${snv_output}'
         
    ]]></command>
    
    <inputs>
        <param format="bam,sam" multiple="true" name="alignments" type="data" label="Alignment file(s)" help="Mapped reads in BAM or SAM format."/>
        
        <!-- Find out how to access the reference genome from the BAM file(s) -->

            <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>
        
        <conditional name="extended_parameters">
            <param name="parameters" type="select" label="Advanced parameters" help="For more advanced VarScan and samtools settings.">

            
            <param name="parameters" value="default" />
            <param name="varscan_output_vcf" value="1" />
            
            
            <output name="snv_output" file="example.2.vcf" />
        </test>
    </tests>
    
    <help>
**VarScan 2.4.2**

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

**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.

**License**

* VarScan 2.4.2: Non-Profit Open Software License 3.0 (Non-Profit OSL 3.0)


Contact
-------

The tool wrapper has been written by Youri Hoogstrate from the Erasmus
Medical Center (Rotterdam, Netherlands).
    </help>
    <citations>
        <citation type="doi">10.1101/gr.129684.111</citation>
    </citations>
</tool>