comparison gmap.xml @ 5:14561eb803a5 draft

Uploaded v3.0.1b (still working on this prior to main Tool Shed release)

4:a88571642c6e

  <description>Genomic Mapping and Alignment Program for mRNA and EST sequences</description>
  <requirements>
    <requirement type="package" version="2013-05-09">gmap</requirement>
  </requirements>
  <version_command>gmap --version</version_command>
  <command>
    #import os,os.path
    gmap
    --nthreads=4 --ordered
    #if $refGenomeSource.genomeSource == "history":
      --gseg=$refGenomeSource.ownFile
    #elif $refGenomeSource.genomeSource == "gmapdb":
      --dir=$refGenomeSource.gmapdb.extra_files_path --db=$refGenomeSource.gmapdb.metadata.db_name
      #if $refGenomeSource.kmer != None and len($refGenomeSource.kmer.__str__) == 2:
        --kmer=$refGenomeSource.kmer
      #end if
    #else:
      --dir=$os.path.dirname($refGenomeSource.gmapindex.value) --db=$os.path.basename($refGenomeSource.gmapindex.value)
      #if $refGenomeSource.kmer != None and len($refGenomeSource.kmer.__str__) == 2:
        --kmer=$refGenomeSource.kmer
      #end if
    #end if
    #if $result.format == "summary":

      --format=$result.sam_paired_read
      $result.no_sam_headers
      $result.sam_use_0M
      $result.force_xs_dir
      $result.md_lowercase_snp
      #* Removed in gmap version 2011-11-30
      #if len($result.noncanonical_splices.__str__) > 0
         --noncanonical-splices=$result.noncanonical_splices
      #end if
      *#
      #if len($result.read_group_id.__str__) > 0
         --read-group-id=$result.read_group_id
      #end if
      #if len($result.read_group_name.__str__) > 0
         --read-group-name=$result.read_group_name

      #end if
      #if len($advanced.wraplength.__str__) > 0:
        --wraplength=$advanced.wraplength
      #end if
    #end if
    #if $split_output == True
      $split_output
    #end if
    #if len($quality_protocol.__str__) > 0:
      --quality-protocol=$quality_protocol
    #end if
    $input
    #for $i in $inputs:
      ${i.added_input}
    #end for
    #if $split_output == True
      2> $gmap_stderr
    #else
      2> $gmap_stderr > $output
    #end if
  </command>
  <inputs>
    <!-- Input data -->
    <param name="input" type="data" format="fasta,fastqsanger,fastqillumina" label="&lt;H2&gt;Input Sequences&lt;/H2&gt;Select an mRNA or EST dataset to map" />
    <repeat name="inputs" title="addtional mRNA or EST dataset to map">
      <param name="added_input" type="data" format="fasta,fastqsanger,fastqillumina" label=""/>
    </repeat>
    <param name="quality_protocol" type="select" label="Protocol for input quality scores">
      <option value="">No quality scores</option>

      <option value="illumina">Illumina quality scores</option>
    </param>

    <!-- GMAPDB for mapping -->
    <conditional name="refGenomeSource">
     <param name="genomeSource" type="select" label="&lt;HR&gt;&lt;H2&gt;Map To&lt;/H2&gt;Will you map to a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options">
        <option value="indexed">Use a built-in index</option>
        <option value="gmapdb">Use gmapdb from the history</option>
        <option value="history">Use a fasta reference sequence from the history</option>
      </param>
      <when value="indexed">
        <param name="gmapindex" type="select" label="Select a reference genome" help="if your genome of interest is not listed - contact Galaxy team">
          <options from_file="gmap_indices.loc">
            <column name="uid" index="0" />
            <column name="dbkey" index="1" />
            <column name="name" index="2" />
            <column name="kmers" index="3" />
            <column name="maps" index="4" />
            <column name="snps" index="5" />
            <column name="value" index="6" />
          </options>
        </param>
        <param name="kmer" type="select" data_ref="gmapindex" label="kmer size" help="Defaults to highest available kmer size">
          <options from_file="gmap_indices.loc">
            <column name="name" index="3"/>
            <column name="value" index="3"/>
            <filter type="param_value" ref="gmapindex" column="6"/>
            <filter type="multiple_splitter" column="3" separator=","/>
            <filter type="add_value" name="" value=""/>

         sampling=INT                 Sampling to use in genome database.  If not specified, the program
                                   will find the smallest available sampling value in the genome database
                                   within selected basesize and k-mer size

        -->
        <param name="map" type="select" data_ref="gmapindex" label="Look for splicing involving known sites or known introns" help="">
          <options from_file="gmap_indices.loc">
            <column name="name" index="4"/>
            <column name="value" index="4"/>
            <filter type="param_value" ref="gmapindex" column="6"/>
            <filter type="multiple_splitter" column="4" separator=","/>
            <filter type="add_value" name="" value=""/>
            <filter type="sort_by" column="4"/>
          </options>
        </param>
      </when>
      <when value="gmapdb">
        <param name="gmapdb" type="data" format="gmapdb" label="Select a gmapdb"
              help="A GMAP database built with GMAP Build"/>
        <param name="kmer" type="select" data_ref="gmapdb" label="kmer size" help="Defaults to highest available kmer size">
          <options>
            <filter type="data_meta" ref="gmapdb" key="kmers" multiple="True" separator=","/>
          </options>
        </param>
        <param name="map" type="select"  data_ref="gmapdb" label="Use map for splicing involving known sites or known introns" help="">
          <options>
            <filter type="data_meta" ref="gmapdb" key="maps" multiple="True"/>
          </options>
        </param>
      </when>
      <when value="history">
        <param name="ownFile" type="data" format="fasta" label="Select the reference genome"
              help="Fasta containing genomic DNA sequence"/>
      </when>
    </conditional>


    <!-- Computation options -->
    <conditional name="computation">
      <param name="options" type="select" label="&lt;HR&gt;Computational Settings" help="">
        <option value="default">Use default settings</option>
        <option value="advanced">Set Computation Options</option>
      </param>
      <when value="default"/>
      <when value="advanced">

         <option value="antisense_filter">antisense_filter</option>
       </param>
       <param name="trimendexons"  type="integer" value="" optional="true" label="Trim end exons with fewer than given number of matches (in nt, default 12)" >
         <validator type="in_range" message="trimendexons must be positive" min="1" />
       </param>
       <param name="find_shifted_canonical" type="boolean" truevalue="--find-shifted-canonical-species" falsevalue="" checked="false" label="find-shifted-canonical Use a more sensitive search for canonical splicing" help=""/>
       <param name="cross_species" type="boolean" truevalue="--cross-species" falsevalue="" checked="false" label="Cross-species alignment" help="For cross-species alignments, use a more sensitive search for canonical splicing"/>

       <param name="canonical"  type="select" label="Reward for canonical and semi-canonical introns">
         <option value="1">high reward (default)</option>
         <option value="0">low reward</option>

      </when>
    </conditional>

    <!-- Advanced Settings -->
    <conditional name="advanced">
      <param name="options" type="select" label="&lt;HR&gt;Advanced Settings" help="">
        <option value="default">Use default settings</option>
        <option value="used">Set Options</option>
      </param>
      <when value="default"/>
      <when value="used">
       <param name="nolengths" type="boolean" checked="false" truevalue="--nolengths=true" falsevalue="" label="No intron lengths in alignment"/>
       <param name="invertmode" type="select" label=" Mode for alignments to genomic (-) strand" help="">
        <option value="">Don't invert the cDNA (default)</option>
        <option value="--invertmode=1">Invert cDNA and print genomic (-) strand</option>
        <option value="--invertmode=2">Invert cDNA and print genomic (+) strand</option>
       </param>
       <param name="introngap" type="integer" value="" optional="true" label="Nucleotides to show on each end of intron (default=3)">

       <param name="chimera_overlap" type="integer" value="" optional="true" label="Overlap to show, if any, at chimera breakpoint (default 0)" >
                <validator type="in_range" message="chimera_overlap must be positive" min="0" />
       </param>
       <param name="tolerant" type="boolean" checked="false" truevalue="--tolerant=true" falsevalue=""
              label="Translates cDNA with corrections for frameshifts"/>
       <param name="protein" type="select" label="Protein alignment" help="">
        <option value="">default</option>
        <option value="--fulllength=true">Assume full-length protein, starting with Met</option>
        <option value="--truncate=true">Truncate alignment around full-length protein, Met to Stop</option>
       </param>
      </when>
    </conditional>

    <!-- Output data -->
    <conditional name="result">
    <param name="format" type="select" label="&lt;HR&gt;&lt;H2&gt;Output&lt;/H2&gt;Select the output format" help="">
      <option value="gmap">GMAP default output</option>
      <option value="summary">Summary of alignments</option>
      <option value="align">Alignment</option>
      <option value="continuous">Alignment in three continuous lines</option>
      <option value="continuous-by-exon">Alignment in three lines per exon</option>

      <option value="map_exons">IIT FASTA exon map format</option>
      <option value="map_ranges">IIT FASTA map format</option>
      <option value="coords">coords in table format</option>
      <option value="sam" selected="true">SAM format</option>
    </param>
      <when value="gmap">
      </when>
      <when value="summary"/>
      <when value="align">
      </when>
      <when value="continuous">
      </when>
      <when value="continuous-by-exon">
      </when>
      <when value="compress"/>
      <when value="exons_dna"/>
      <when value="exons_gen"/>
      <when value="protein_dna"/>
      <when value="protein_gen"/>

      <when value="introns"/>
      <when value="map_exons"/>
      <when value="map_ranges"/>
      <when value="coords"/>
      <when value="sam">
        <param name="sam_paired_read" type="boolean" truevalue="sampe" falsevalue="samse" checked="false" label="SAM paired reads"/>
        <param name="no_sam_headers" type="boolean" truevalue="--no-sam-headers" falsevalue="" checked="false" label="Do not print headers beginning with '@'"/>
        <!--  Removed in gmap version 2011-11-30
        <param name="noncanonical_splices" type="select" label="Print non-canonical genomic gaps greater than 20 nt in CIGAR string as STRING.">
          <option value="">Use default</option>
          <option value="N">N</option>
          <option value="D">D</option>
        </param>
        -->
        <param name="read_group_id" type="text" value="" label="Value to put into read-group id (RG-ID) field"/>
        <param name="read_group_name" type="text" value="" label="Value to put into read-group name (RG-SM) field"/>
        <param name="read_group_library" type="text" value="" label="Value to put into read-group library (RG-LB) field"/>
        <param name="read_group_platform" type="text" value="" label="Value to put into read-group library platform (RG-PL) field"/>
        <param name="sam_use_0M" type="boolean" truevalue="--sam-use-0M" falsevalue="" checked="false" label="Insert 0M in CIGAR between adjacent insertions and deletions" help="Required by Picard, but can cause errors in other tools"/>

        <when input="result['format']" value="map_exons" format="gmap_annotation"/>
      </change_format>
    </data>
  </outputs>
  <tests>
  </tests>

  <help>

**What it does**

GMAP_ (Genomic Mapping and Alignment Program)  The functionality provided by gmap allows a user to: (1) map and align a single cDNA interactively against a large genome in about a second, without the startup time of several minutes typically needed by existing mapping programs; (2) switch arbitrarily among different genomes, without the need for a preloaded server dedicated to each genome; (3) run the program on computers with as little as 128 MB of RAM (random access memory); (4) perform high-throughput batch processing of cDNAs by using memory mapping and multithreading when appropriate memory and hardware are available; (5) generate accurate gene models, even in the presence of substantial polymorphisms and sequence errors; (6) locate splice sites accurately without the use of probabilistic splice site models, allowing generalized use of the program across species; (7) detect statistically significant microexons and incorporate them into the alignment; and (8) handle mapping and alignment tasks on genomes having alternate assemblies, linkage groups or strains.  It is developed by Thomas D. Wu of Genentech, Inc.

Publication_ citation: Thomas D. Wu, Colin K. Watanabe  Bioinformatics 2005 21(9):1859-1875; doi:10.1093/bioinformatics/bti310

.. _GMAP: http://research-pub.gene.com/gmap/
.. _Publication: http://bioinformatics.oxfordjournals.org/cgi/content/full/21/9/1859

------

**Know what you are doing**

5:14561eb803a5

  <description>Genomic Mapping and Alignment Program for mRNA and EST sequences</description>
  <requirements>
    <requirement type="package" version="2013-05-09">gmap</requirement>
  </requirements>
  <version_command>gmap --version</version_command>
  <command detect_errors="exit_code"><![CDATA[
    #import os,os.path
    gmap
    --nthreads=\${GALAXY_SLOTS:-4} --ordered
    #if $refGenomeSource.genomeSource == "history":
      --gseg=$refGenomeSource.ownFile
    #elif $refGenomeSource.genomeSource == "gmapdb":
      --dir='$refGenomeSource.gmapdb.extra_files_path' --db='$refGenomeSource.gmapdb.metadata.db_name'
      #if $refGenomeSource.kmer != None and len($refGenomeSource.kmer.__str__) == 2:
        --kmer=$refGenomeSource.kmer
      #end if
    #else:
      --dir='$os.path.dirname($refGenomeSource.gmapindex.value)' --db='$os.path.basename($refGenomeSource.gmapindex.value)'
      #if $refGenomeSource.kmer != None and len($refGenomeSource.kmer.__str__) == 2:
        --kmer=$refGenomeSource.kmer
      #end if
    #end if
    #if $result.format == "summary":

      --format=$result.sam_paired_read
      $result.no_sam_headers
      $result.sam_use_0M
      $result.force_xs_dir
      $result.md_lowercase_snp
      #if len($result.read_group_id.__str__) > 0
         --read-group-id=$result.read_group_id
      #end if
      #if len($result.read_group_name.__str__) > 0
         --read-group-name=$result.read_group_name

      #end if
      #if len($advanced.wraplength.__str__) > 0:
        --wraplength=$advanced.wraplength
      #end if
    #end if
    $split_output
    #if len($quality_protocol.__str__) > 0:
      --quality-protocol=$quality_protocol
    #end if
    $input
    #for $i in $inputs:
      ${i.added_input}
    #end for
    #if $split_output
      2> $gmap_stderr
    #else
      2> $gmap_stderr > $output
    #end if
  ]]></command>
  <inputs>
    <!-- Input data -->
    <param name="input" type="data" format="fasta,fastqsanger,fastqillumina" label="Input Sequences" help="Select an mRNA or EST dataset to map" />
    <repeat name="inputs" title="addtional mRNA or EST dataset to map">
      <param name="added_input" type="data" format="fasta,fastqsanger,fastqillumina" label=""/>
    </repeat>
    <param name="quality_protocol" type="select" label="Protocol for input quality scores">
      <option value="">No quality scores</option>

      <option value="illumina">Illumina quality scores</option>
    </param>

    <!-- GMAPDB for mapping -->
    <conditional name="refGenomeSource">
     <param name="genomeSource" type="select" label="Map to a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options">
        <option value="indexed">Use a built-in index</option>
        <option value="gmapdb">Use gmapdb from the history</option>
        <option value="history">Use a fasta reference sequence from the history</option>
      </param>
      <when value="indexed">
        <param name="gmapindex" type="select" label="Select a reference genome" help="if your genome of interest is not listed - contact Galaxy team">
          <options from_data_table="gmap_indices">
            <column name="uid" index="0" />
            <column name="dbkey" index="1" />
            <column name="name" index="2" />
            <column name="kmers" index="3" />
            <column name="maps" index="4" />
            <column name="snps" index="5" />
            <column name="value" index="6" />
          </options>
        </param>
        <param name="kmer" type="select" data_ref="gmapindex" label="kmer size" help="Defaults to highest available kmer size">
          <options from_data_table="gmap_indices">
            <column name="name" index="3"/>
            <column name="value" index="3"/>
            <filter type="param_value" ref="gmapindex" column="6"/>
            <filter type="multiple_splitter" column="3" separator=","/>
            <filter type="add_value" name="" value=""/>

         sampling=INT                 Sampling to use in genome database.  If not specified, the program
                                   will find the smallest available sampling value in the genome database
                                   within selected basesize and k-mer size

        -->
        <!-- Not currently used in the command tag,
        <param name="map" type="select" data_ref="gmapindex" label="Look for splicing involving known sites or known introns" >
          <options from_data_table="gmap_indices">
            <column name="name" index="4"/>
            <column name="value" index="4"/>
            <filter type="param_value" ref="gmapindex" column="6"/>
            <filter type="multiple_splitter" column="4" separator=","/>
            <filter type="add_value" name="" value=""/>
            <filter type="sort_by" column="4"/>
          </options>
        </param>
        -->
      </when>
      <when value="gmapdb">
        <param name="gmapdb" type="data" format="gmapdb" label="Select a gmapdb"
              help="A GMAP database built with GMAP Build"/>
        <param name="kmer" type="select" data_ref="gmapdb" label="kmer size" help="Defaults to highest available kmer size">
          <options>
            <filter type="data_meta" ref="gmapdb" key="kmers" multiple="True" separator=","/>
          </options>
        </param>
        <!-- Not currently used in the command tag,
        <param name="map" type="select"  data_ref="gmapdb" label="Use map for splicing involving known sites or known introns" >
          <options>
            <filter type="data_meta" ref="gmapdb" key="maps" multiple="True"/>
          </options>
        </param>
        -->
      </when>
      <when value="history">
        <param name="ownFile" type="data" format="fasta" label="Select the reference genome"
              help="Fasta containing genomic DNA sequence"/>
      </when>
    </conditional>


    <!-- Computation options -->
    <conditional name="computation">
      <param name="options" type="select" label="Computational Settings" >
        <option value="default">Use default settings</option>
        <option value="advanced">Set Computation Options</option>
      </param>
      <when value="default"/>
      <when value="advanced">

         <option value="antisense_filter">antisense_filter</option>
       </param>
       <param name="trimendexons"  type="integer" value="" optional="true" label="Trim end exons with fewer than given number of matches (in nt, default 12)" >
         <validator type="in_range" message="trimendexons must be positive" min="1" />
       </param>
       <param name="find_shifted_canonical" type="boolean" truevalue="--find-shifted-canonical-species" falsevalue="" checked="false" label="find-shifted-canonical Use a more sensitive search for canonical splicing" />
       <param name="cross_species" type="boolean" truevalue="--cross-species" falsevalue="" checked="false" label="Cross-species alignment" help="For cross-species alignments, use a more sensitive search for canonical splicing"/>

       <param name="canonical"  type="select" label="Reward for canonical and semi-canonical introns">
         <option value="1">high reward (default)</option>
         <option value="0">low reward</option>

      </when>
    </conditional>

    <!-- Advanced Settings -->
    <conditional name="advanced">
      <param name="options" type="select" label="Advanced Settings" >
        <option value="default">Use default settings</option>
        <option value="used">Set Options</option>
      </param>
      <when value="default"/>
      <when value="used">
       <param name="nolengths" type="boolean" checked="false" truevalue="--nolengths=true" falsevalue="" label="No intron lengths in alignment"/>
       <param name="invertmode" type="select" label=" Mode for alignments to genomic (-) strand" >
        <option value="">Don't invert the cDNA (default)</option>
        <option value="--invertmode=1">Invert cDNA and print genomic (-) strand</option>
        <option value="--invertmode=2">Invert cDNA and print genomic (+) strand</option>
       </param>
       <param name="introngap" type="integer" value="" optional="true" label="Nucleotides to show on each end of intron (default=3)">

       <param name="chimera_overlap" type="integer" value="" optional="true" label="Overlap to show, if any, at chimera breakpoint (default 0)" >
                <validator type="in_range" message="chimera_overlap must be positive" min="0" />
       </param>
       <param name="tolerant" type="boolean" checked="false" truevalue="--tolerant=true" falsevalue=""
              label="Translates cDNA with corrections for frameshifts"/>
       <param name="protein" type="select" label="Protein alignment" >
        <option value="">default</option>
        <option value="--fulllength=true">Assume full-length protein, starting with Met</option>
        <option value="--truncate=true">Truncate alignment around full-length protein, Met to Stop</option>
       </param>
      </when>
    </conditional>

    <!-- Output data -->
    <conditional name="result">
    <param name="format" type="select" label="Output" help="Select the output format" >
      <option value="gmap">GMAP default output</option>
      <option value="summary">Summary of alignments</option>
      <option value="align">Alignment</option>
      <option value="continuous">Alignment in three continuous lines</option>
      <option value="continuous-by-exon">Alignment in three lines per exon</option>

      <option value="map_exons">IIT FASTA exon map format</option>
      <option value="map_ranges">IIT FASTA map format</option>
      <option value="coords">coords in table format</option>
      <option value="sam" selected="true">SAM format</option>
    </param>
      <when value="gmap"/>
      <when value="summary"/>
      <when value="align"/>
      <when value="continuous"/>
      <when value="continuous-by-exon"/>
      <when value="compress"/>
      <when value="exons_dna"/>
      <when value="exons_gen"/>
      <when value="protein_dna"/>
      <when value="protein_gen"/>

      <when value="introns"/>
      <when value="map_exons"/>
      <when value="map_ranges"/>
      <when value="coords"/>
      <when value="sam">
        <param name="sam_paired_read" type="boolean" truevalue="sampe" falsevalue="samse" checked="false" label="SAM paired reads" help="The sampe option will generate SAM flags to indicate whether the read is the first or second end of a pair"/>
        <param name="no_sam_headers" type="boolean" truevalue="--no-sam-headers" falsevalue="" checked="false" label="Do not print SAM headers (lines beginning with '@')"/>
        <param name="read_group_id" type="text" value="" label="Value to put into read-group id (RG-ID) field"/>
        <param name="read_group_name" type="text" value="" label="Value to put into read-group name (RG-SM) field"/>
        <param name="read_group_library" type="text" value="" label="Value to put into read-group library (RG-LB) field"/>
        <param name="read_group_platform" type="text" value="" label="Value to put into read-group library platform (RG-PL) field"/>
        <param name="sam_use_0M" type="boolean" truevalue="--sam-use-0M" falsevalue="" checked="false" label="Insert 0M in CIGAR between adjacent insertions and deletions" help="Required by Picard, but can cause errors in other tools"/>

        <when input="result['format']" value="map_exons" format="gmap_annotation"/>
      </change_format>
    </data>
  </outputs>
  <tests>
    <test>
      <!-- 
      mimic first test from GMAP source code, mapping Human ERBB2 onto fragment of chr17
      $ gmap -A -g ss.chr17test ss.her2
      -->
      <param name="input" value="ss.her2.fasta" ftype="fasta"/>
      <!-- <param name="quality_protocol" value=""/> -->
      <param name="genomeSource" value="history"/>
      <param name="ownFile" value="ss.chr17.fasta" ftype="fasta"/>
      <param name="format" value="align"/>
      <param name="computation" value="default"/>
      <param name="options" value="default"/>
      <output name="output" file="ss.her2.chr17.txt" ftype="txt"/>
    </test>
  </tests>

  <help>

**What it does**

GMAP (Genomic Mapping and Alignment Program)

The functionality provided by gmap allows a user to:

    1. map and align a single cDNA interactively against a large genome in
       about a second, without the startup time of several minutes typically
       needed by existing mapping programs;
    2. switch arbitrarily among different genomes, without the need for a
       preloaded server dedicated to each genome;
    3. run the program on computers with as little as 128 MB of RAM (random
       access memory)
    4. perform high-throughput batch processing of cDNAs by using memory
       mapping and multithreading when appropriate memory and hardware are
       available;
    5. generate accurate gene models, even in the presence of substantial
       polymorphisms and sequence errors;
    6. locate splice sites accurately without the use of probabilistic splice
       site models, allowing generalized use of the program across species;
    7. detect statistically significant microexons and incorporate them into
       the alignment; and
    8. handle mapping and alignment tasks on genomes having alternate
       assemblies, linkage groups or strains.

It is developed by Thomas D. Wu of Genentech, Inc.

------

**Know what you are doing**