Mercurial > repos > devteam > bwa
diff bwa-mem.xml @ 24:64f11cf59c6e draft
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/bwa commit 055c6c3de6c9e0f219f5792f6580244815c1cd31"
author | iuc |
---|---|
date | Wed, 05 May 2021 18:22:08 +0000 |
parents | 3fe632431b68 |
children | e188dc7a68e6 |
line wrap: on
line diff
--- a/bwa-mem.xml Tue May 19 11:29:11 2020 -0400 +++ b/bwa-mem.xml Wed May 05 18:22:08 2021 +0000 @@ -1,5 +1,5 @@ <?xml version="1.0"?> -<tool id="bwa_mem" name="Map with BWA-MEM" version="@VERSION@.1"> +<tool id="bwa_mem" name="Map with BWA-MEM" version="@VERSION@.2"> <description>- map medium and long reads (> 100 bp) against reference genome</description> <macros> <import>read_group_macros.xml</import> @@ -14,7 +14,12 @@ ## Begin BWA-MEM command line bwa mem --t "\${GALAXY_SLOTS:-1}" + +#if str( $output_sort ) == "unsorted": + -t 1 +#else + -t "\${GALAXY_SLOTS:-1}" +#end if ## Verbosity is set to 1 (errors only) -v 1 @@ -106,7 +111,15 @@ '${fastq_input.fastq_input1}' #end if -| samtools sort -@\${GALAXY_SLOTS:-2} -T "\${TMPDIR:-.}" -O bam -o '$bam_output' +#if str( $output_sort ) == "coordinate": + | samtools sort -@\${GALAXY_SLOTS:-2} -T "\${TMPDIR:-.}" -O bam -o '$bam_output' +#elif str( $output_sort ) == "name": + | samtools sort -n -@\${GALAXY_SLOTS:-2} -T "\${TMPDIR:-.}" -O bam -o '$bam_output' +#else + | samtools view -@ \${GALAXY_SLOTS:-2} -bS - -o '$bam_output' +#end if + + ]]></command> <inputs> @@ -247,11 +260,20 @@ </conditional> </when> </conditional> + <param name="output_sort" type="select" label="BAM sorting mode" help="The 'Not sorted' option can extend the run time of the tool significantly (cause it requires running on only a single thread)."> + <option value="coordinate" selected="True">Sort by chromosomal coordinates</option> + <option value="name">Sort by read names (i.e., the QNAME field) </option> + <option value="unsorted">Not sorted (sorted as input)</option> + </param> </inputs> <outputs> <data format="bam" name="bam_output" label="${tool.name} on ${on_string} (mapped reads in BAM format)"> <expand macro="dbKeyActionsBwaMem" /> + <change_format> + <when input="output_sort" value="name" format="qname_sorted.bam" /> + <when input="output_sort" value="unsorted" format="qname_input_sorted.bam" /> + </change_format> </data> </outputs> @@ -296,6 +318,26 @@ <param name="analysis_type_selector" value="illumina"/> <output name="bam_output" ftype="bam" file="bwa-mem-test2.bam" lines_diff="2" /> </test> + <test> + <param name="reference_source_selector" value="history" /> + <param name="ref_file" ftype="fasta" value="bwa-mem-mt-genome.fa"/> + <param name="fastq_input_selector" value="paired"/> + <param name="fastq_input1" ftype="fastqsanger" value="bwa-mem-fastq1.fq"/> + <param name="fastq_input2" ftype="fastqsanger" value="bwa-mem-fastq2.fq"/> + <param name="analysis_type_selector" value="illumina"/> + <param name="output_sort" value="unsorted"/> + <output name="bam_output" ftype="qname_input_sorted.bam" file="bwa-mem-test3.bam" lines_diff="2" /> + </test> + <test> + <param name="reference_source_selector" value="history" /> + <param name="ref_file" ftype="fasta" value="bwa-mem-mt-genome.fa"/> + <param name="fastq_input_selector" value="paired"/> + <param name="fastq_input1" ftype="fastqsanger" value="bwa-mem-fastq1.fq"/> + <param name="fastq_input2" ftype="fastqsanger" value="bwa-mem-fastq2.fq"/> + <param name="analysis_type_selector" value="illumina"/> + <param name="output_sort" value="name"/> + <output name="bam_output" ftype="qname_sorted.bam" file="bwa-mem-test4.bam" lines_diff="2" /> + </test> </tests> <help><![CDATA[ **What is does** @@ -332,6 +374,19 @@ 2. *PacBio mode*: The mode adjusted specifically for mapping of long PacBio subreads. Equivalent to the following command: bwa mem -k17 -W40 -r10 -A1 -B1 -O1 -E1 -L0 <reference index> <PacBio dataset in fastq format> 3. *Full list of options*: Allows access to all options through Galaxy interface. + ----- + +**Bam sorting mode** + +The generated bam files can be sorted according to three criteria: coordinates, names and input order. + +In coordinate sorted mode the reads are sorted by coordinates. It means that the reads from the beginning of the first chromosome are first in the file. + +When sorted by read name, the file is sorted by the reference ID (i.e., the QNAME field). + +Finally, the *No sorted (sorted as input)* option yield a BAM file in which the records are sorted in an order corresponding to the order of the reads in the original input file. This option requires using a single thread to perform the conversion from SAM to BAM format, so the runtime is extended. + + @RG@ @info@