Mercurial > repos > mvdbeek > bam_readtagger
view findcluster.xml @ 57:38ae00c376ef draft
planemo upload for repository https://github.com/bardin-lab/readtagger/tree/master/galaxy commit 8186814619b9163944e3c11cb797f02c94804ecb
author | mvdbeek |
---|---|
date | Mon, 29 Jul 2019 10:52:49 -0400 |
parents | b50e114fece9 |
children | 84f51c5d69e3 |
line wrap: on
line source
<tool id="findcluster" name="Find clusters of reads" version="0.5.4"> <description>in bam files</description> <macros> <import>macros.xml</import> </macros> <requirements> <requirement type="package" version="0.5.4">readtagger</requirement> </requirements> <version_command>findcluster --version</version_command> <command detect_errors="aggressive"><![CDATA[ #import re #set sample_name = re.sub('[^\w\-_\.\,]', '_', str( $input.element_identifier)) ln -f -s $input input.bam && ln -f -s $input.metadata.bam_index input.bam.bai && findcluster --input_path input.bam #if $transposon_source.ref_file: #if str($transposon_source.reference_source_selector) == "history": --transposon_reference_fasta '$transposon_source.ref_file' #else : --transposon_bwa_index '$transposon_source.ref_file.fields.path' #end if #end if #if $genome_source.ref_file: #if str($genome_source.reference_source_selector) == "history": --genome_reference_fasta '$genome_source.ref_file' #else : --genome_bwa_index '$genome_source.ref_file.fields.path' #end if #end if #if str($make_bam) == 'True': --output_bam '$output_bam' #end if #if str($make_vcf) == 'True' --output_vcf '$output_vcf' #end if #if str($make_gff) == 'True' --output_gff '$output_gff' #end if #if str($make_fasta) == 'True' --output_fasta '$output_fasta' #end if --sample_name '$sample_name' --threads "\${GALAXY_SLOTS:-2}" ]]></command> <inputs> <param name="input" argument="--input_path" type="data" format="bam"/> <param name="make_bam" type="boolean" truevalue="True" checked="true" label="Produce an alignment file containing evidence for insertions."/> <param name="make_vcf" type="boolean" truevalue="True" checked="true" label="Produce a VCF file describing the insertion that have been found."/> <param name="make_gff" type="boolean" truevalue="True" checked="false" label="produce a GFF file describing the insertions that have been found."/> <param name="make_fasta" type="boolean" checked="True" truevalue="True" label="Produce a fasta file containing assembled contigs."/> <expand macro="reference_source_conditional" reference_type="transposon"/> <expand macro="reference_source_conditional" reference_type="genome"/> </inputs> <outputs> <data name="output_bam" format="bam" label="findcluster BAM on $on_string"> <filter>make_bam</filter> </data> <data name="output_fasta" format="fasta" label="findcluster contigs on $on_string"> <filter>make_fasta</filter> </data> <data name="output_vcf" format="vcf" label="findcluster VCF on $on_string"> <filter>make_vcf</filter> </data> <data name="output_gff" format="gff3" label="findcluster GFF on $on_string"> <filter>make_gff</filter> </data> </outputs> <tests> <test> <param name="input" value="extended_and_annotated_roi.bam" ftype="bam"/> <param name="make_gff" value="true"/> <output name="output_bam" file="three_cluster_out.bam" ftype="bam" lines_diff="2"/> <output name="output_gff" file="three_cluster_out.gff" ftype="gff3" compare="sim_size"/> <output name="output_vcf" file="three_cluster_out.vcf" ftype="vcf" compare="sim_size"/> </test> <test> <param name="input" value="extended_and_annotated_roi.bam" ftype="bam"/> <param name="transposon_source|reference_source_selector" value="history"/> <param name="transposon_source|ref_file" value="reference.fasta" ftype="fasta"/> <param name="make_gff" value="true"/> <output name="output_bam" file="three_cluster_out.bam" ftype="bam" lines_diff="2"/> <output name="output_gff"> <assert_contents> <has_text text="FBti0019066_rover_Gypsy" /> </assert_contents> </output> </test> </tests> <help><![CDATA[ .. code-block:: Usage: findcluster [OPTIONS] Find clusters of reads that support a TE insertion. Options: --input_path PATH Find cluster in this BAM file. --region TEXT Find clusters in this Region (Format is chrX:2000-1000). --max_proper_pair_size INTEGER Maximum proper pairs size. If not given will be inferred from the data. --output_bam PATH Write out BAM file with cluster information to this path. Reads will have an additional "CD" tag to indicate the cluster number --output_gff PATH Write out GFF file with cluster information to this path. --output_fasta PATH Write out supporting evidence for clusters to this path. --sample_name TEXT Sample name to use when writing out clusters in GFF file. Default is to infer the name from the input filename. --include_duplicates / --no-include_duplicates Include reads marked as duplicates when finding clusters. --transposon_reference_fasta TEXT Transposon fasta to align clipped reads to. Not necessary if BWA index is provided. --transposon_bwa_index TEXT Transposon BWA index to align clipped reads to --genome_reference_fasta TEXT Genome fasta to align clipped reads to. Not necessary if BWA index is provided. --genome_bwa_index TEXT Genome BWA index to align clipped reads to --threads INTEGER RANGE Threads to use for cap3 assembly step --shm_dir PATH Path to shared memory folder --version Show the version and exit. --help Show this message and exit. ]]></help> </tool>