comparison bwa-mem.xml @ 4:ac30bfd3e2a8 draft

planemo upload commit a50a3947aebc8a1d11bac39599f4efd8ed9a3bd5

3:607ca4b95837

<?xml version="1.0"?>
<tool id="bwa_mem" name="Map with BWA-MEM" version="0.2.1">
  <description>- map medium and long reads (&gt; 100 bp) against reference genome</description>
  <macros>
    <import>bwa_macros.xml</import>
  </macros>
  <requirements>

  </command>

  <inputs>

    <conditional name="reference_source">
      <param name="reference_source_selector" type="select" label="Load reference genome from">
        <option value="cached">Local cache</option>
        <option value="history">History</option>
      </param>
      <when value="cached">
        <param name="ref_file" type="select" label="Using reference genome" help="Select genome from the list">
          <options from_data_table="bwa_mem_indexes">
            <filter type="sort_by" column="2" />

        <option value="paired_iv">Paired Interleaved</option>
      </param>
      <when value="paired">
        <param name="fastq_input1" type="data" format="fastqsanger" label="Select first set of reads" help="Specify dataset with forward reads"/>
        <param name="fastq_input2" type="data" format="fastqsanger" label="Select second set of reads" help="Specify dataset with reverse reads"/>
        <param name="iset_stats" type="text" optional="True" size="10" label="Enter mean, standerd deviation, max, and min for insert lengths." help="-I; This parameter is only used for paired reads. Only mean is required while sd, max, and min will be inferred. Examples: both &quot;250&quot; and &quot;250,25&quot; will work while &quot;250,,10&quot; will not. See below for details.">
          <sanitizer invalid_char="">
            <valid initial="string.digits"><add value=","/> </valid>
          </sanitizer>
        </param>
      </when>
      <when value="single">
        <param name="fastq_input1" type="data" format="fastqsanger" label="Select fastq dataset" help="Specify dataset with single reads"/>
      </when>
      <when value="paired_collection">
        <param name="fastq_input1" format="fastqsanger" type="data_collection" collection_type="paired" label="Select a paired collection" help="See help section for an explanation of dataset collections"/>
        <param name="iset_stats" type="text" optional="True" size="10" label="Enter mean, standerd deviation, max, and min for insert lengths." help="-I; This parameter is only used for paired reads. Only mean is required while sd, max, and min will be inferred. Examples: both &quot;250&quot; and &quot;250,25&quot; will work while &quot;250,,10&quot; will not. See below for details.">
          <sanitizer invalid_char="">
            <valid initial="string.digits"><add value=","/> </valid>
          </sanitizer>
        </param>
      </when>
      <when value="paired_iv">
        <param name="fastq_input1" type="data" format="fastqsanger" label="Select fastq dataset" help="Specify dataset with interleaved reads"/>
        <param name="iset_stats" type="text" optional="True" size="10" label="Enter mean, standerd deviation, max, and min for insert lengths." help="-I; This parameter is only used for paired reads. Only mean is required while sd, max, and min will be inferred. Examples: both &quot;250&quot; and &quot;250,25&quot; will work while &quot;250,,10&quot; will not. See below for details.">
          <sanitizer invalid_char="">
            <valid initial="string.digits"><add value=","/> </valid>
          </sanitizer>
        </param>
      </when>

    <expand macro="readgroup_params" />

    <conditional name="analysis_type">
      <param name="analysis_type_selector" type="select" label="Select analysis mode">
        <option value="illumina">Simple Illumina mode</option>
        <option value="pacbio">PacBio mode (-x pacbio)</option>
        <option value="full">Full list of options</option>
      </param>
      <when value="illumina">
        <!-- do nothing -->
      </when>
      <when value="pacbio">

      <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="rg_selector" value="set"/>
      <param name="ID" value="rg1"/>
      <param name="analysis_type_selector" value="illumina"/>
      <output name="bam_output" ftype="bam" file="bwa-mem-test2.bam" lines_diff="2" />
    </test>
  </tests>
  <help>

For mapping 100bp sequences, BWA-MEM shows better performance than several state-of-art read aligners to date.

It is best suited for mapping long (>70 nt) reads against large reference genomes.

This Galaxy tool wraps bwa-mem module of bwa read mapping tool. Galaxy implementation takes fastq files as input and produces output in BAM (not SAM) format, which can be further processed using various BAM utilities exiting in Galaxy (BAMTools, SAMTools, Picard).

-----

**Galaxy-specific option**

4:ac30bfd3e2a8

<?xml version="1.0"?>
<tool id="bwa_mem" name="Map with BWA-MEM" version="0.2.2">
  <description>- map medium and long reads (&gt; 100 bp) against reference genome</description>
  <macros>
    <import>bwa_macros.xml</import>
  </macros>
  <requirements>

  </command>

  <inputs>

    <conditional name="reference_source">
      <param name="reference_source_selector" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options. See `Indexes` section of help below">
        <option value="cached">Use a built-in genome index</option>
        <option value="history">Use a genome from history and build index</option>
      </param>
      <when value="cached">
        <param name="ref_file" type="select" label="Using reference genome" help="Select genome from the list">
          <options from_data_table="bwa_mem_indexes">
            <filter type="sort_by" column="2" />

        <option value="paired_iv">Paired Interleaved</option>
      </param>
      <when value="paired">
        <param name="fastq_input1" type="data" format="fastqsanger" label="Select first set of reads" help="Specify dataset with forward reads"/>
        <param name="fastq_input2" type="data" format="fastqsanger" label="Select second set of reads" help="Specify dataset with reverse reads"/>
        <param name="iset_stats" type="text" optional="True" size="10" label="Enter mean, standard deviation, max, and min for insert lengths." help="-I; This parameter is only used for paired reads. Only mean is required while sd, max, and min will be inferred. Examples: both &quot;250&quot; and &quot;250,25&quot; will work while &quot;250,,10&quot; will not. See below for details.">
          <sanitizer invalid_char="">
            <valid initial="string.digits"><add value=","/> </valid>
          </sanitizer>
        </param>
      </when>
      <when value="single">
        <param name="fastq_input1" type="data" format="fastqsanger" label="Select fastq dataset" help="Specify dataset with single reads"/>
      </when>
      <when value="paired_collection">
        <param name="fastq_input1" format="fastqsanger" type="data_collection" collection_type="paired" label="Select a paired collection" help="See help section for an explanation of dataset collections"/>
        <param name="iset_stats" type="text" optional="True" size="10" label="Enter mean, standard deviation, max, and min for insert lengths." help="-I; This parameter is only used for paired reads. Only mean is required while sd, max, and min will be inferred. Examples: both &quot;250&quot; and &quot;250,25&quot; will work while &quot;250,,10&quot; will not. See below for details.">
          <sanitizer invalid_char="">
            <valid initial="string.digits"><add value=","/> </valid>
          </sanitizer>
        </param>
      </when>
      <when value="paired_iv">
        <param name="fastq_input1" type="data" format="fastqsanger" label="Select fastq dataset" help="Specify dataset with interleaved reads"/>
        <param name="iset_stats" type="text" optional="True" size="10" label="Enter mean, standard deviation, max, and min for insert lengths." help="-I; This parameter is only used for paired reads. Only mean is required while sd, max, and min will be inferred. Examples: both &quot;250&quot; and &quot;250,25&quot; will work while &quot;250,,10&quot; will not. See below for details.">
          <sanitizer invalid_char="">
            <valid initial="string.digits"><add value=","/> </valid>
          </sanitizer>
        </param>
      </when>

    <expand macro="readgroup_params" />

    <conditional name="analysis_type">
      <param name="analysis_type_selector" type="select" label="Select analysis mode">
        <option value="illumina">1.Simple Illumina mode</option>
        <option value="pacbio">2.PacBio mode (-x pacbio)</option>
        <option value="full">3.Full list of options</option>
      </param>
      <when value="illumina">
        <!-- do nothing -->
      </when>
      <when value="pacbio">

      <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="rg_selector" value="set"/>
      <param name="ID" value="rg1"/>
      <param name="PL" value="CAPILLARY"/>
      <param name="LB" value="AARDVARK-1" />
      <param name="analysis_type_selector" value="illumina"/>
      <output name="bam_output" ftype="bam" file="bwa-mem-test2.bam" lines_diff="2" />
    </test>
  </tests>
  <help>

For mapping 100bp sequences, BWA-MEM shows better performance than several state-of-art read aligners to date.

It is best suited for mapping long (>70 nt) reads against large reference genomes.

This Galaxy tool wraps bwa-mem module of bwa read mapping tool. Galaxy implementation takes fastq files as input and produces output in BAM (not SAM) format, which can be further processed using various BAM utilities exiting in Galaxy (BAMTools, SAMTools, Picard).

-----

**Indices: Selecting reference genomes for BWA**

Galaxy wrapper for BWA allows you select between precomputed and user-defined indices for reference genomes using **Will you select a reference genome from your history or use a built-in index?** flag. This flag 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 mem`.
    
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.

-----

**Galaxy-specific option**