comparison gsnap.xml @ 2:f6ba0f12cca2 draft

Untested work-in-progress GMAP wrappers v3.0.0, from JJ back in June 2013

1:74391fc6e3f2

<tool id="gsnap" name="GSNAP" version="2.0.1">
  <description>Genomic Short-read Nucleotide Alignment Program</description>
  <requirements>
      <requirement type="package" version="2011-11-30">gmap</requirement>
  </requirements>
  <version_string>gsnap --version</version_string>
  <command>
    #import os.path, re
    gsnap
    --nthreads="4" --ordered
    #if $refGenomeSource.genomeSource == "gmapdb":
      #set $gmapdb = $os.listdir($refGenomeSource.gmapdb.extra_files_path)[0]
      --dir=$refGenomeSource.gmapdb.extra_files_path --db=$refGenomeSource.gmapdb.metadata.db_name
    #else:
      --dir=$os.path.dirname($refGenomeSource.gmapindex.value) --db=$os.path.basename($refGenomeSource.gmapindex.value)
    #end if
    #if $refGenomeSource.kmer != None and len($refGenomeSource.kmer.__str__) == 2:

      #end if
    #end if
    #if $output.options == "advanced":
      #if $output.npath.__str__ != '':
        --npath=$output.npath
      #end if
      $output.quiet_if_excessive
      $output.show_refdiff
      $output.clip_overlap
    #end if

      </param>
      <when value="fastq">
        <param name="fastq" type="data" format="fastq" label="Select a fastq dataset" />
        <conditional name="paired">
          <param name="ispaired" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Use Paired Reads?"/>
          <when value="no"/>
          <when value="yes">
            <param name="fastq" type="data" format="fastq" label="Select the paired reads reverse dataset" />
            <param name="orientation" type="select" label="Orientation of paired-end reads" help="">
              <option value="FR">fwd-rev, typical Illumina default</option>
              <option value="RF">rev-fwd, for circularized inserts</option>

        <option value="advanced">Set Computation Options</option>
      </param>
      <when value="default"/>
      <when value="advanced">
         <param name="max_mismatches" type="float" value="" optional="true" label="Maximum number of mismatches allowed (uses default when negative)" 
              help="Defaults to the ultrafast level of ((readlength+2)/12 - 2)).
                    If specified between 0.0 and 1.0, then treated as a fraction
                    of each read length.  Otherwise, treated as an integral number
                    of mismatches (including indel and splicing penalties)
                    For RNA-Seq, you may need to increase this value slightly
                    to align reads extending past the ends of an exon.">
            <validator type="in_range" message="The mismatches must >= 0." min="0."/>
         </param>
         <param name="query_unk_mismatch" type="boolean" checked="false" truevalue="--query-unk-mismatch=1" falsevalue="" label="Count unknown (N) characters in the query as a mismatch"/>
         <param name="genome_unk_mismatch" type="boolean" checked="true" truevalue="" falsevalue="--genome-unk-mismatch=0" label="Count unknown (N) characters in the genome as a mismatch"/>
         <param name="terminal_threshold"  type="integer" value="" optional="true" label="Threshold for searching for a terminal alignment (default 2)" 
                help="(from one end of the read to the best possible position at the other end).   For example, if this value is 2, then if GSNAP finds an exact or
                                   1-mismatch alignment, it will not try to find a terminal alignment.
                                   Note that this default value may not be low enough if you want to
                                   obtain terminal alignments for very short reads, although such reads
                                   probably don't have enough specificity for terminal alignments anyway." />
         <param name="indel_penalty"  type="integer" value="" optional="true" label="Penalty for an indel (default 2)" 
                help="Counts against mismatches allowed.  To find indels, make indel-penalty less than or equal to max-mismatches.  A value &lt; 2 can lead to false positives at read ends" />
         <param name="indel_endlength"  type="integer" value="" optional="true" label="Minimum length at end required for indel alignments (default 4)" />
         <param name="max_middle_insertions"  type="integer" value="" optional="true" label="Maximum number of middle insertions allowed (default 9)" />
         <param name="max_middle_deletions"  type="integer" value="" optional="true" label="Maximum number of middle deletions allowed (default 30)" />
         <param name="max_end_insertions"  type="integer" value="" optional="true" label="Maximum number of end insertions allowed (default 3)" />
         <param name="max_end_deletions"  type="integer" value="" optional="true" label="Maximum number of end deletions allowed (default 6)" />
         <param name="suboptimal_levels"  type="integer" value="" optional="true" label="Report suboptimal hits beyond best hit (default 0)"
                help="All hits with best score plus suboptimal-levels are reported" />
         <param name="adapter_strip"  type="select" label="Method for removing adapters from reads" 
                help="paired removes adapters from paired-end reads if a concordant or paired alignment cannot be found from the original read">
           <option value="paired" selected="true">paired</option>
           <option value="off">off</option>
         </param>
         <param name="trim_mismatch_score" type="integer" value="" optional="true" label="Score to use for mismatches when trimming at ends (default is -3)" 
                help="to turn off trimming, specify 0 (Warning: turning trimming off will give false positive mismatches at the ends of reads)"/>
         <param name="trim_indel_score" type="integer" value="" optional="true" label="Score to use for indels when trimming at ends (default is -4)" 
                help="to turn off trimming, specify 0 (Warning: turning trimming off will give false positive indels at the ends of reads)"/>

         
         <!-- Options for GMAP alignment within GSNAP -->
          <param name="gmap_mode" type="select" multiple="true" optional="true" display="checkboxes" label="Cases to use GMAP for complex alignments containing multiple splices or indels" 
                 help="Default: pairsearch,terminal,improve">
            <option value="pairsearch" selected="true">pairsearch</option>
            <option value="terminal" selected="true">terminal</option>
            <option value="improve" selected="true">improve</option>
          </param>
          <param name="trigger_score_for_gmap" type="integer" value="" optional="true" label="GMAP pairsearch threshold (default 5)" 
                 help="Try GMAP pairsearch on nearby genomic regions if best score (the total of both ends if paired-end) exceeds this value (default 5)" />

2:f6ba0f12cca2

<tool id="gsnap" name="GSNAP" version="3.0.0">
  <description>Genomic Short-read Nucleotide Alignment Program</description>
  <requirements>
      <requirement type="package" version="2013-05-09">gmap</requirement>
  </requirements>
  <version_string>gsnap --version</version_string>
  <command>
    #import os.path, re
    gsnap
    --nthreads="4" --ordered
    #if $refGenomeSource.genomeSource == "gmapdb":
      --dir=$refGenomeSource.gmapdb.extra_files_path --db=$refGenomeSource.gmapdb.metadata.db_name
    #else:
      --dir=$os.path.dirname($refGenomeSource.gmapindex.value) --db=$os.path.basename($refGenomeSource.gmapindex.value)
    #end if
    #if $refGenomeSource.kmer != None and len($refGenomeSource.kmer.__str__) == 2:

      #end if
    #end if
    #if $output.options == "advanced":
      #if $output.npath.__str__ != '':
        --npath=$output.npath
      #end if
      #if $output.maxsearch.__str__ != '':
        --maxsearch=$output.maxsearch 
      #end if
      $output.quiet_if_excessive
      $output.show_refdiff
      $output.clip_overlap
    #end if

      </param>
      <when value="fastq">
        <param name="fastq" type="data" format="fastq" label="Select a fastq dataset" />
        <conditional name="paired">
          <param name="ispaired" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Use Paired Reads?"/>
          <when value="no">
          <!--
            Could allow multiple input fastq and set the force-single-end flag
            force-single-end             When multiple FASTQ files are provided on the command line, GSNAP assumes
                                    they are match paired-end files.  This flag treats each file as single-end.
          -->
          </when>
          <when value="yes">
            <param name="fastq" type="data" format="fastq" label="Select the paired reads reverse dataset" />
            <param name="orientation" type="select" label="Orientation of paired-end reads" help="">
              <option value="FR">fwd-rev, typical Illumina default</option>
              <option value="RF">rev-fwd, for circularized inserts</option>

        <option value="advanced">Set Computation Options</option>
      </param>
      <when value="default"/>
      <when value="advanced">
         <param name="max_mismatches" type="float" value="" optional="true" label="Maximum number of mismatches allowed (uses default when negative)" 
              help="Maximum number of mismatches allowed (if not specified, then
                    defaults to the ultrafast level of ((readlength+index_interval-1)/kmer - 2))
                    (By default, the genome index interval is 3, but this can be changed
                    by providing a different value for -q to gmap_build when processing the genome.)
		    If specified between 0.0 and 1.0, then treated as a fraction
                    of each read length.  Otherwise, treated as an integral number
                    of mismatches (including indel and splicing penalties)
                    For RNA-Seq, you may need to increase this value slightly
                    to align reads extending past the ends of an exon.">
            <validator type="in_range" message="The mismatches must >= 0." min="0."/>
         </param>
         <param name="query_unk_mismatch" type="boolean" checked="false" truevalue="--query-unk-mismatch=1" falsevalue="" label="Count unknown (N) characters in the query as a mismatch"/>
         <param name="genome_unk_mismatch" type="boolean" checked="true" truevalue="" falsevalue="--genome-unk-mismatch=0" label="Count unknown (N) characters in the genome as a mismatch"/>
         <param name="maxsearch" type="integer" value="" optional="true" label="Maximum number of alignments to find (default 1000)"
                help="Must be larger than paths, which is the number to report.
                      Keeping this number large will allow for random selection among multiple alignments.
                      Reducing this number can speed up the program. "/>

         <param name="terminal_threshold"  type="integer" value="" optional="true" label="Threshold for searching for a terminal alignment" 
                help="Threshold for searching for a terminal alignment (from one end of the
                                   read to the best possible position at the other end) (default 2
                                   for standard, atoi-stranded, and atoi-nonstranded mode; default 100
                                   for cmet-stranded and cmet-nonstranded mode).
                                   For example, if this value is 2, then if GSNAP finds an exact or
                                   1-mismatch alignment, it will not try to find a terminal alignment.
                                   Note that this default value may not be low enough if you want to
                                   obtain terminal alignments for very short reads, although such reads
                                   probably don't have enough specificity for terminal alignments anyway.
                                   To turn off terminal alignments, set this to a high value, greater
                                   than the value for max-mismatches.
                                   "/>
         <param name="indel_penalty"  type="integer" value="" optional="true" label="Penalty for an indel (default 2)" 
                help="Counts against mismatches allowed.  To find indels, make indel-penalty less than or equal to max-mismatches.  A value &lt; 2 can lead to false positives at read ends" />
         <param name="indel_endlength"  type="integer" value="" optional="true" label="Minimum length at end required for indel alignments (default 4)" />
         <param name="max_middle_insertions"  type="integer" value="" optional="true" label="Maximum number of middle insertions allowed (default 9)" />
         <param name="max_middle_deletions"  type="integer" value="" optional="true" label="Maximum number of middle deletions allowed (default 30)" />
         <param name="max_end_insertions"  type="integer" value="" optional="true" label="Maximum number of end insertions allowed (default 3)" />
         <param name="max_end_deletions"  type="integer" value="" optional="true" label="Maximum number of end deletions allowed (default 6)" />
         <param name="suboptimal_levels"  type="integer" value="" optional="true" label="Report suboptimal hits beyond best hit (default 0)"
                help="All hits with best score plus suboptimal-levels are reported" />
         <param name="adapter_strip"  type="select" label="Method for removing adapters from reads" 
                help="Default is 'off'.  To turn on, specify 'paired', which removes adapters
                                   from paired-end reads if they appear to be present.">
           <option value="paired">paired</option>
           <option value="off" selected="true">off</option>
         </param>
         <param name="trim_mismatch_score" type="integer" value="" optional="true" label="Score to use for mismatches when trimming at ends (default is -3)" 
                help="to turn off trimming, specify 0 (Warning: turning trimming off will give false positive mismatches at the ends of reads)"/>
         <param name="trim_indel_score" type="integer" value="" optional="true" label="Score to use for indels when trimming at ends (default is -4)" 
                help="to turn off trimming, specify 0 (Warning: turning trimming off will give false positive indels at the ends of reads)"/>

         
         <!-- Options for GMAP alignment within GSNAP -->
          <param name="gmap_mode" type="select" multiple="true" optional="true" display="checkboxes" label="Cases to use GMAP for complex alignments containing multiple splices or indels" 
                 help="Default: pairsearch,terminal,improve">
            <option value="pairsearch" selected="true">pairsearch</option>
            <option value="indel_knownsplice" selected="true">indel_knownsplice</option>
            <option value="terminal" selected="true">terminal</option>
            <option value="improve" selected="true">improve</option>
          </param>
          <param name="trigger_score_for_gmap" type="integer" value="" optional="true" label="GMAP pairsearch threshold (default 5)" 
                 help="Try GMAP pairsearch on nearby genomic regions if best score (the total of both ends if paired-end) exceeds this value (default 5)" />