comparison bwa.xml @ 26:2477830927ec draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/bwa commit 6e9628b1d92fdb358b79959ad54a456cfa46fa33

25:e188dc7a68e6

<?xml version="1.0"?>
<tool id="bwa" name="Map with BWA" version="@VERSION@.5">
    <description>- map short reads (&lt; 100 bp) against reference genome</description>
    <xrefs>
        <xref type="bio.tools">bwa</xref>
    </xrefs>
    <macros>
        <import>read_group_macros.xml</import>
        <import>bwa_macros.xml</import>
        <token name="@command_options@">
#if str( $analysis_type.analysis_type_selector ) == "full":

            <when value="do_not_set">
                <!-- do nothing -->
            </when>
        </xml>
    </macros>
    <expand macro="requirements"/>
    <expand macro="stdio"/>
    <command>
        <![CDATA[
@pipefail@

        <data format="bam" name="bam_output" label="${tool.name} on ${on_string} (mapped reads in BAM format)">
            <expand macro="dbKeyActionsBwaMem"/>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="reference_source_selector" value="history"/>
            <param name="ref_file" ftype="fasta" value="bwa-mem-mt-genome.fa"/>
            <param name="input_type_selector" value="single"/>
            <param name="fastq_input1" ftype="fasta" value="bwa-mem-fasta1.fa"/>
            <param name="analysis_type_selector" value="illumina"/>
            <output name="bam_output" ftype="bam" file="bwa-aln-test1-fasta.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="input_type_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"/>
            <output name="bam_output" ftype="bam" file="bwa-aln-test1.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="input_type_selector" value="paired"/>
            <param name="fastq_input1" ftype="fastqsanger.gz" value="bwa-mem-fastq1.fq.gz"/>
            <param name="fastq_input2" ftype="fastqsanger" value="bwa-mem-fastq2.fq"/>
            <param name="analysis_type_selector" value="illumina"/>
            <output name="bam_output" ftype="bam" file="bwa-aln-test1.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="input_type_selector" value="paired_bam"/>
            <param name="bam_input" ftype="bam" value="bwa-aln-bam-input.bam"/>
            <param name="analysis_type_selector" value="illumina"/>
            <output name="bam_output" ftype="bam" file="bwa-aln-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="input_type_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="rg_selector" value="set"/>
            <param name="ID" value="rg1"/>
            <param name="PL" value="CAPILLARY"/>
            <param name="analysis_type_selector" value="illumina"/>
            <output name="bam_output" ftype="bam" file="bwa-aln-test3.bam" lines_diff="2"/>
        </test>
    </tests>
    <help><![CDATA[
**What is does**

BWA is a software package for mapping low-divergent sequences against a large reference genome, such as the
human genome. The bwa-aln algorithm is designed for Illumina sequence reads up to 100bp. For longer reads use
the separate BWA-MEM Galaxy tool.

This Galaxy tool wraps bwa-aln, bwa-samse and -sampe modules of bwa read mapping tool:

- **bwa aln** - actual mapper placing reads onto the reference sequence
- **bwa samse** - post-processor converting suffix array coordinates into genome coordinates in SAM format for
  single reads
- **bam sampe** - post-processor for paired reads


The Galaxy implementation takes fastq or BAM (unaligned BAM) datasets as input and produces output in BAM format,
which can be further processed using various BAM utilities exiting in Galaxy (BAMTools, SAMTools, Picard).

-----

**Indices: Selecting reference genomes for BWA**

The Galaxy wrapper for BWA allows you to select between precomputed and user-defined indices for reference genomes
using the **Will you select a reference genome from your history or use a built-in index?** select box.

This select box has two options:

  1. **Use a built-in genome index** - when selected (this is default), Galaxy provides the user with **Select
     reference genome index** dropdown. Genomes listed in this dropdown have been pre-indexed with bwa index utility
     and are ready to be mapped against.
  2. **Use a genome from the history and build index** - when selected, Galaxy provides the user with **Select
     reference genome sequence** dropdown. This dropdown is populated by all FASTA formatted files listed in your
     current history. If your genome of interest is uploaded into history it will be shown there. Selecting a genome
     from this dropdown will cause Galaxy to first transparently index it using `bwa index` command, and then run
     mapping with `bwa aln`.


If your genome of interest is not listed here you have two choices:

  1. Contact galaxy team using **Help->Support** link at the top of the interface and let us know that an index
     needs to be added
  2. Upload your genome of interest as a FASTA file to Galaxy history and selected **Use a genome from the history
     and build index** option.


@RG@

@info@
    ]]></help>
    <citations>
        <citation type="doi">10.1093/bioinformatics/btp324</citation>
        <citation type="doi">10.1093/bioinformatics/btp698</citation>
    </citations>

26:2477830927ec

<?xml version="1.0"?>
<tool id="bwa" name="Map with BWA" version="@TOOL_VERSION@" profile="22.05">
    <description>- map short reads (&lt; 100 bp) against reference genome</description>
    <macros>
        <import>read_group_macros.xml</import>
        <import>bwa_macros.xml</import>
        <token name="@command_options@">
#if str( $analysis_type.analysis_type_selector ) == "full":

            <when value="do_not_set">
                <!-- do nothing -->
            </when>
        </xml>
    </macros>
    <expand macro="bio_tools"/>
    <expand macro="requirements"/>
    <expand macro="stdio"/>
    <command>
        <![CDATA[
@pipefail@

        <data format="bam" name="bam_output" label="${tool.name} on ${on_string} (mapped reads in BAM format)">
            <expand macro="dbKeyActionsBwaMem"/>
        </data>
    </outputs>
    <tests>
        <!-- `samtools sort` in the new update adds PG lines to the output so the lines_diff is changed from "2" to "4" -->
        <test expect_num_outputs="1">
            <param name="reference_source_selector" value="history"/>
            <param name="ref_file" ftype="fasta" value="bwa-mem-mt-genome.fa"/>
            <param name="input_type_selector" value="single"/>
            <param name="fastq_input1" ftype="fasta" value="bwa-mem-fasta1.fa"/>
            <param name="analysis_type_selector" value="illumina"/>
            <output name="bam_output" ftype="bam" file="bwa-aln-test1-fasta.bam" lines_diff="4"/>
        </test>
        <test expect_num_outputs="1">
            <param name="reference_source_selector" value="history"/>
            <param name="ref_file" ftype="fasta" value="bwa-mem-mt-genome.fa"/>
            <param name="input_type_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"/>
            <output name="bam_output" ftype="bam" file="bwa-aln-test1.bam" lines_diff="4"/>
        </test>
        <test expect_num_outputs="1">
            <param name="reference_source_selector" value="history"/>
            <param name="ref_file" ftype="fasta" value="bwa-mem-mt-genome.fa"/>
            <param name="input_type_selector" value="paired"/>
            <param name="fastq_input1" ftype="fastqsanger.gz" value="bwa-mem-fastq1.fq.gz"/>
            <param name="fastq_input2" ftype="fastqsanger" value="bwa-mem-fastq2.fq"/>
            <param name="analysis_type_selector" value="illumina"/>
            <output name="bam_output" ftype="bam" file="bwa-aln-test1.bam" lines_diff="4"/>
        </test>
        <test expect_num_outputs="1">
            <param name="reference_source_selector" value="history"/>
            <param name="ref_file" ftype="fasta" value="bwa-mem-mt-genome.fa"/>
            <param name="input_type_selector" value="paired_bam"/>
            <param name="bam_input" ftype="bam" value="bwa-aln-bam-input.bam"/>
            <param name="analysis_type_selector" value="illumina"/>
            <output name="bam_output" ftype="bam" file="bwa-aln-test2.bam" lines_diff="4"/>
        </test>
        <test expect_num_outputs="1">
            <param name="reference_source_selector" value="history"/>
            <param name="ref_file" ftype="fasta" value="bwa-mem-mt-genome.fa"/>
            <param name="input_type_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="rg_selector" value="set"/>
            <param name="ID" value="rg1"/>
            <param name="PL" value="CAPILLARY"/>
            <param name="analysis_type_selector" value="illumina"/>
            <output name="bam_output" ftype="bam" file="bwa-aln-test3.bam" lines_diff="5"/>
        </test>
    </tests>
    <help><![CDATA[
**What it does**

BWA_ is a software package for mapping low-divergent sequences against a large reference genome, such as the human genome.
The bwa-aln algorithm is designed for Illumina sequence reads up to 100bp. For longer reads use the separate BWA-MEM Galaxy tool.

This Galaxy tool wraps the bwa-aln, bwa-samse and -sampe modules of the BWA read mapping tool:

- **bwa aln** - actual mapper placing reads onto the reference sequence
- **bwa samse** - post-processor converting suffix array coordinates into genome coordinates in SAM format for
  single reads
- **bam sampe** - post-processor for paired reads

For more details about the different modules of the BWA package see the `BWA manual`_.

The Galaxy implementation takes fastq or BAM (unaligned BAM) datasets as input and produces output in BAM format,
which can be further processed using various BAM utilities existing in Galaxy (BAMTools, SAMTools, Picard).

-----

@ref_genomes@

@RG@

@links@
    ]]></help>
    <citations>
        <citation type="doi">10.1093/bioinformatics/btp324</citation>
        <citation type="doi">10.1093/bioinformatics/btp698</citation>
    </citations>