comparison bwa-mem.xml @ 5:86c73f0eb389 draft default tip

Uploaded

4:d04dfa7de2dc

<?xml version="1.0"?>
<tool id="bwa_mem_0_7_10" name="BWA-MEM" version="bwa-0.7.10-r837-dirty_galaxy_0.1">
  <requirements>
    <requirement type="package" version="0.7.10.039ea20639">bwa</requirement>
    <requirement type="package" version="1.1">samtools</requirement>
  </requirements>
  <description>- map medium and long reads (&gt; 100 bp) against reference genome</description>

    -t "\${GALAXY_SLOTS:-1}"
    -v 1                                                                                      ## Verbosity is set to 1 (errors only)   
    
    #if str( $fastq_input.fastq_input_selector ) == "paired_iv":                              ## For interleaved fastq files set -p option
      -p
      #if str( $fastq_input.iv_stats.iv_stats_selector ) == "True":                           ## check that insert statistics is used
        -I "${fastq_input.iv_stats.iset_stats}"
      #end if
    #end if
    
    #if str( $analysis_type.analysis_type_selector ) == "pacbio":
      -x

      -R "@RG\tID:$rg.ID\tSM:$rg.SM"
    #end if 
    
    #if str( $fastq_input.fastq_input_selector ) == "paired":
      
      #if str( $fastq_input.paired_stats.paired_stats_selector ) == "True":                   ## check that insert statistics is used
        -I "${fastq_input.paired_stats.iset_stats}"
      #end if
      
      "${reference_fasta_filename}"
      
      "${fastq_input.fastq_input1}" "${fastq_input.fastq_input2}"
      
    #else:
    
      "${reference_fasta_filename}"
    
      "${fastq_input.fastq_input1}"
    
    #end if
    
    | samtools view -Sb - > $bam_output
      
  </command>
  
  <inputs>

          </options>
          <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
        </param>
      </when>
      <when value="history"> 
        <param name="ref_file" type="data" format="fasta" label="Use the folloing dataset as the reference sequence" help="You can upload a FASTA sequence to the history and use it as reference" />
      </when>
    </conditional>
    <conditional name="fastq_input">
      <param name="fastq_input_selector" type="select" label="Single or Paired-end reads" help="Select between paired and single end data">
        <option value="paired">Paired</option>
        <option value="single">Single</option>
        <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"/>
        
        <!-- PE stat selection block 1: If you make any changes in this conditional block, copy them to PE stat selection block 2 below as well -->
        
        <conditional name="paired_stats">
          <param name="paired_stats_selector" type="boolean" truevalue="set" falsevalue="do_not_set" label="Specify insert size statistics?" help="-I; if you choose to not specify, it will be inferred from the data"/>
          <when value="set">
            
            <param name="iset_stats" type="text" value="250" size="10" label="Enter mean, standerd deviation, max, and min for insert lengths in the form mean,sd,min,max" help="-I; 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="do_not_set">
          <!-- do nothing -->
          </when>
        </conditional>
        
        <!-- end of PE stat selection block 1 -->
        
      </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_iv">
        <param name="fastq_input1" type="data" format="fastqsanger" label="Select fastq dataset" help="Specify dataset with interleaved reads"/>
        
        <!-- PE stat selection block 2: If you make any changes in this conditional block, copy them to PE stat selection block 1 above as well -->
        
        <conditional name="iv_stats">
          <param name="iv_stats_selector" type="boolean" truevalue="set" falsevalue="do_not_set" label="Specify insert size statistics?" help="-I; if you choose to not specify, it will be inferred from the data"/>
          <when value="set">
            
            <param name="iset_stats" type="text" value="250" size="10" label="Enter mean, standerd deviation, max, and min for insert lengths in the form mean,sd,min,max" help="-I; 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="do_not_set">
          <!-- do nothing -->
          </when>
        </conditional>
        
        <!-- end of PE stat selection block 2 -->
        
      </when>
    </conditional>
    
    <conditional name="rg">
      <param name="rg_selector" type="boolean" truevalue="set" falsevalue="do_not_set" label="Specify readgroup information?" help="Specifying readgroup information can greatly simplify your downstream analyses by allowing combining multiple datasets. See help below for more details"/>
      <when value="set">
        <param name="ID" type="text" value="readgroup1" size="20" label="Specify readgroup ID" help="This value must be unique among multiple samples in your experiment">
          <sanitizer invalid_char="">
            <valid initial="string.printable"/>
          </sanitizer>

      <when value="pacbio">
        <!-- do nothing. all magic happens within <command> tag -->
      </when>
      <when value="full">
        <conditional name="algorithmic_options">
          <param name="algorithmic_options_selector" type="boolean" truevalue="set" falsevalue="do_not_set" label="Set algorithmic options?" help="Sets -k, -w, -d, -r, -y, -c, -D, -W, -m, -S, -P, and -e options." />
          <when value="set">
            <param name="k" type="integer" value="19" label="minimum seed length" help="-k; default=19"/>
            <param name="w" type="integer" value="100" label="band width for banded alignment" help="-w; default=100"/>
            <param name="d" type="integer" value="100" label="off-diagonal X-dropoff" help="-d; default=100"/>
            <param name="r" type="float" value="1.5" label="look for internal seeds inside a seed longer than -k * THIS VALUE" help="-r; default=1.5"/>

          </when>
          <when value="do_not_set">
            <!-- do nothing -->
          </when>
        </conditional>
        <conditional name="scoring_options">
          <param name="scoring_options_selector" type="boolean" truevalue="set" falsevalue="do_not_set" label="Set scoring options?" help="Sets -A, -B, -O, -E, -L, and -U options." />
          <when value="set">
            <param name="A" type="integer" value="1" label="score for a sequence match" help="-A; scales options -T, -d, -B, -O, -E, -L, and -U; default=1"/>
            <param name="B" type="integer" value="4" label="penalty for mismatch" help="-B; default=4"/>
            <param name="O" type="text" value="6,6" label="gap open penalty for deletions and insertions" help="-O; default=6,6">
              <sanitizer invalid_char="">

          </when>
          <when value="do_not_set">
            <!-- do nothing -->
          </when>
        </conditional>
        <conditional name="io_options">
          <param name="io_options_selector" type="boolean" truevalue="set" falsevalue="do_not_set" label="Set input/output options" help="Sets -T, -h, -a, -C, -V, -Y, and -M options." />
          <when value="set">
            <param name="T" type="integer" value="30" label="minimum score to output" help="-T; default=30"/>
            <param name="h" type="integer" value="5" label="if there are this many hits with score >80% of the max score, output all in XA tag" help="-h; default=5"/>
            <param name="a" type="boolean" truevalue="-a" falsevalue="" label="output all alignments for single-ends or unpaired paired-ends" help="-a"/>
            <param name="C" type="boolean" truevalue="-C" falsevalue="" label="append FASTA/FASTQ comment to BAM output" help="-C"/>

       -I FLOAT[,FLOAT[,INT[,INT]]]
                     specify the mean, standard deviation (10% of the mean if absent), max
                     (4 sigma from the mean if absent) and min of the insert size distribution.
                     FR orientation only. [inferred]
                     
------

.. class:: warningmark

**An important note on Read Groups**

One of the recommended best practices in NGS analysis is adding read group information to BAM files. You can do thid directly in BWA MEM interface using the
**Specify readgroup information?** widget. If you are not familiar with readgroups you shold know that this is effectively a way to tag reads with an additional ID.
This allows you to combine BAM files from, for example, multiple BWA MEM runs into a single dataset. This significantly simplifies downstream processing as
instead of dealing with multiple datasets you only have to handle only one. This is possible because the readgroup information allows you to identify
data from different experiments even if they are combined in one file. Many downstream analysis tools such as varinat callers (e.g., FreeBayes or Naive Varinat Caller
present in Galaxy) are aware of readgtroups and will automatically generate calls for each individual sample even if they are combined within a single file.

-----

.. class:: infomark

**More info**

To obtain more information about BWA MEM and ask questions use these resources:

  1. https://biostar.usegalaxy.org/
  2. https://www.biostars.org/
  3. https://github.com/lh3/bwa
  4. http://bio-bwa.sourceforge.net/
  
    
  </help>
  <citations>
    <citation type="doi">10.1093/bioinformatics/btp324</citation>

5:86c73f0eb389

<?xml version="1.0"?>
<tool id="bwa_mem_0_7_10" name="BWA-MEM" version="bwa-0.7.10-r837-dirty_galaxy_0.2">
  
  <macros>
    <import>bwa_macros.xml</import>
  </macros>
  
  <requirements>
    <requirement type="package" version="0.7.10.039ea20639">bwa</requirement>
    <requirement type="package" version="1.1">samtools</requirement>
  </requirements>
  <description>- map medium and long reads (&gt; 100 bp) against reference genome</description>

    -t "\${GALAXY_SLOTS:-1}"
    -v 1                                                                                      ## Verbosity is set to 1 (errors only)   
    
    #if str( $fastq_input.fastq_input_selector ) == "paired_iv":                              ## For interleaved fastq files set -p option
      -p
      #if str( $fastq_input.iset_stats ):                                                     ## check that insert statistics is used
        -I "${fastq_input.iset_stats}"
      #end if
    #end if
    
    #if str( $analysis_type.analysis_type_selector ) == "pacbio":
      -x

      -R "@RG\tID:$rg.ID\tSM:$rg.SM"
    #end if 
    
    #if str( $fastq_input.fastq_input_selector ) == "paired":
      
      #if str( $fastq_input.iset_stats ):                   ## check that insert statistics is used
        -I "${fastq_input.iset_stats}"
      #end if
      
      "${reference_fasta_filename}"
      
      "${fastq_input.fastq_input1}" "${fastq_input.fastq_input2}"
      
    #elif str( $fastq_input.fastq_input_selector ) == "paired_collection":
      
      #if str( $fastq_input.iset_stats ):                   ## check that insert statistics is used
        -I "${fastq_input.iset_stats}"
      #end if

      
      "${reference_fasta_filename}"
      
      "${fastq_input.fastq_input1.forward}" "${fastq_input.fastq_input1.reverse}"
      
    #else:
      
      
      "${reference_fasta_filename}"
    
      "${fastq_input.fastq_input1}"
    
    #end if
    
    | samtools view -Sb - > temporary_bam_file.bam &&
    
    samtools sort -f temporary_bam_file.bam ${bam_output}
      
  </command>
  
  <inputs>

          </options>
          <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
        </param>
      </when>
      <when value="history"> 
        <param name="ref_file" type="data" format="fasta" label="Use the following dataset as the reference sequence" help="You can upload a FASTA sequence to the history and use it as reference" />
      </when>
    </conditional>
    <conditional name="fastq_input">
      <param name="fastq_input_selector" type="select" label="Single or Paired-end reads" help="Select between paired and single end data">
        <option value="paired">Paired</option>
        <option value="single">Single</option>
        <option value="paired_collection">Paired Collection</option>
        <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>
    </conditional>
  
    
    <conditional name="rg">
      <param name="rg_selector" type="select" label="Set read groups information?" help="Specifying readgroup information can greatly simplify your downstream analyses by allowing combining multiple datasets. See help below for more details">
        <option value="set">Set</option>
        <option value="do_not_set" selected="True">Do not set</option>
      </param>
      <when value="set">
        <param name="ID" type="text" value="readgroup1" size="20" label="Specify readgroup ID" help="This value must be unique among multiple samples in your experiment">
          <sanitizer invalid_char="">
            <valid initial="string.printable"/>
          </sanitizer>

      <when value="pacbio">
        <!-- do nothing. all magic happens within <command> tag -->
      </when>
      <when value="full">
        <conditional name="algorithmic_options">
          <param name="algorithmic_options_selector" type="select" label="Set algorithmic options?" help="Sets -k, -w, -d, -r, -y, -c, -D, -W, -m, -S, -P, and -e options.">
            <option value="set">Set</option>
            <option value="do_not_set" selected="True">Do not set</option>
          </param>
          <when value="set">
            <param name="k" type="integer" value="19" label="minimum seed length" help="-k; default=19"/>
            <param name="w" type="integer" value="100" label="band width for banded alignment" help="-w; default=100"/>
            <param name="d" type="integer" value="100" label="off-diagonal X-dropoff" help="-d; default=100"/>
            <param name="r" type="float" value="1.5" label="look for internal seeds inside a seed longer than -k * THIS VALUE" help="-r; default=1.5"/>

          </when>
          <when value="do_not_set">
            <!-- do nothing -->
          </when>
        </conditional>
        
        <conditional name="scoring_options">
          <param name="scoring_options_selector" type="select" label="Set scoring options?" help="Sets -A, -B, -O, -E, -L, and -U options.">
            <option value="set">Set</option>
            <option value="do_not_set" selected="True">Do not set</option>
          </param>
          <when value="set">
            <param name="A" type="integer" value="1" label="score for a sequence match" help="-A; scales options -T, -d, -B, -O, -E, -L, and -U; default=1"/>
            <param name="B" type="integer" value="4" label="penalty for mismatch" help="-B; default=4"/>
            <param name="O" type="text" value="6,6" label="gap open penalty for deletions and insertions" help="-O; default=6,6">
              <sanitizer invalid_char="">

          </when>
          <when value="do_not_set">
            <!-- do nothing -->
          </when>
        </conditional>
        
        <conditional name="io_options">
          <param name="io_options_selector" type="select" label="Set input/output options" help="Sets -T, -h, -a, -C, -V, -Y, and -M options.">
            <option value="set">Set</option>
            <option value="do_not_set" selected="True">Do not set</option>
          </param>
          <when value="set">
            <param name="T" type="integer" value="30" label="minimum score to output" help="-T; default=30"/>
            <param name="h" type="integer" value="5" label="if there are this many hits with score >80% of the max score, output all in XA tag" help="-h; default=5"/>
            <param name="a" type="boolean" truevalue="-a" falsevalue="" label="output all alignments for single-ends or unpaired paired-ends" help="-a"/>
            <param name="C" type="boolean" truevalue="-C" falsevalue="" label="append FASTA/FASTQ comment to BAM output" help="-C"/>

       -I FLOAT[,FLOAT[,INT[,INT]]]
                     specify the mean, standard deviation (10% of the mean if absent), max
                     (4 sigma from the mean if absent) and min of the insert size distribution.
                     FR orientation only. [inferred]
                     

@dataset_collections@

@RG@

@info@

  
    
  </help>
  <citations>
    <citation type="doi">10.1093/bioinformatics/btp324</citation>