view tools/meme/meme.xml @ 2:c2a356708570

Uploaded
author xuebing
date Fri, 09 Mar 2012 19:45:42 -0500
parents 9071e359b9a3
children
line wrap: on
line source

<tool id="meme_meme" name="MEME" version="1.0.0">
  <requirements><requirement type='package'>meme</requirement></requirements>
  <description>- Multiple Em for Motif Elicitation</description>
  <command>meme "$input1" -o "${html_outfile.files_path}" 
  -nostatus
  
  ##-p 8 ##number of processors
  
  #if str( $options_type.options_type_selector ) == 'advanced':
  -sf "${ str( $options_type.sf ).replace( ' ', '_' ) }"
  -${options_type.alphabet_type.alphabet_type_selector} 
  -mod "${options_type.mod_type.mod_type_selector}" 
  -nmotifs "${options_type.nmotifs}" 
  -wnsites "${options_type.wnsites}"
  -maxsize "${options_type.maxsize}"
  
  #if $options_type.evt &lt; float('inf'):
    -evt "${options_type.evt}" 
  #end if
  
  #if str( $options_type.mod_type.mod_type_selector ) != 'oops':
    #if str( $options_type.mod_type.motif_occurrence_type.motif_occurrence_type_selector ) == 'nsites':
      -nsites "${options_type.mod_type.motif_occurrence_type.nsites}"
    #elif str( $options_type.mod_type.motif_occurrence_type.motif_occurrence_type_selector ) == 'min_max_sites':
      -minsites "${options_type.mod_type.motif_occurrence_type.minsites}" -maxsites "${options_type.mod_type.motif_occurrence_type.maxsites}"
    #end if
  #end if
  
  #if str( $options_type.motif_width_type.motif_width_type_selector ) == 'exact':
    -w "${options_type.motif_width_type.width}"
  #else
    -minw "${options_type.motif_width_type.minw}" -maxw "${options_type.motif_width_type.maxw}"
  #end if
  
  #if str( $options_type.motif_trim_type.motif_trim_type_selector ) == 'nomatrim':
    -nomatrim
  #else
    -wg "${options_type.motif_trim_type.wg}" -ws "${options_type.motif_trim_type.ws}" ${options_type.motif_trim_type.noendgaps}
  #end if
  
  #if str( $options_type.bfile ) != 'None':
    -bfile "${options_type.bfile}"
  #end if
  
  #if str( $options_type.pspfile ) != 'None':
    -psp "${options_type.pspfile}"
  #end if
  
  #if str( $options_type.alphabet_type.alphabet_type_selector ) == "dna":
    ${options_type.alphabet_type.revcomp} ${options_type.alphabet_type.pal}
  #end if
  
  -maxiter "${options_type.maxiter}" -distance "${options_type.distance}"
  
  -prior "${options_type.alphabet_type.prior_type.prior_type_selector}"
  #if str( $options_type.alphabet_type.prior_type.prior_type_selector ) != 'addone':
    -b "${options_type.alphabet_type.prior_type.prior_b}" 
    #if str( $options_type.alphabet_type.prior_type.plib ) != 'None':
      -plib "${options_type.alphabet_type.prior_type.plib}"
    #end if
  #end if
  
  #if str( $options_type.alphabet_type.spmap_type.spmap_type_selector ) == 'cons':
    -cons "${options_type.alphabet_type.spmap_type.cons}" 
  #else
    -spmap "${options_type.alphabet_type.spmap_type.spmap_type_selector}"
    -spfuzz "${options_type.alphabet_type.spmap_type.spfuzz}" 
  #end if
  
  #if str( $options_type.branching_type.branching_type_selector ) == 'x_branch':
    -x_branch -bfactor "${options_type.branching_type.bfactor}" -heapsize "${options_type.branching_type.heapsize}"
  #end if
  
  ##-maxsize "1000000" ##remove hardcoded maxsize? should increase number of processors instead
  
  #end if
  
  2&gt;&amp;1 || echo "Error running MEME."
  
  
  &amp;&amp; mv ${html_outfile.files_path}/meme.html ${html_outfile}
  
  &amp;&amp; mv ${html_outfile.files_path}/meme.txt ${txt_outfile}
  
  &amp;&amp; mv ${html_outfile.files_path}/meme.xml ${xml_outfile}
  
  </command>
  <inputs>
    <param format="fasta" name="input1" type="data" label="Sequences"/>
      
      <conditional name="options_type">
        <param name="options_type_selector" type="select" label="Options Configuration">
          <option value="basic" selected="true">Basic</option>
          <option value="advanced">Advanced</option>
        </param>
        <when value="basic">
          <!-- do nothing here -->
        </when>
        <when value="advanced">
      
      <param name="sf" type="text" value="Galaxy FASTA Input" label="Name of sequence set" />
      
      <conditional name="alphabet_type">
        <param name="alphabet_type_selector" type="select" label="Sequence Alphabet">
          <option value="protein">Protein</option>
          <option value="dna" selected="true">DNA</option>
        </param>
        <when value="protein">
          <conditional name="prior_type">
            <param name="prior_type_selector" type="select" label="Choice of prior">
              <option value="dirichlet">simple Dirichlet prior</option>
              <option value="dmix" selected="true">mixture of Dirichlets prior</option>
              <option value="mega">extremely low variance dmix</option>
              <option value="megap">mega for all but last iteration of EM; dmix on last iteration</option>
              <option value="addone">add +1 to each observed count</option>
            </param>
            <when value="dirichlet">
              <param name="prior_b" type="float" value="0.01" label="strength of prior on model parameters" />
              <param name="plib" type="data" format="txt" optional="True" label="Dirichlet prior file" />
            </when>
            <when value="dmix">
              <param name="prior_b" type="float" value="0" label="strength of prior on model parameters" />
              <param name="plib" type="data" format="txt" optional="True" label="Dirichlet prior file" />
            </when>
            <when value="mega">
              <param name="prior_b" type="float" value="0" label="strength of prior on model parameters" />
              <param name="plib" type="data" format="txt" optional="True" label="Dirichlet prior file" />
            </when>
            <when value="megap">
              <param name="prior_b" type="float" value="0" label="strength of prior on model parameters" />
              <param name="plib" type="data" format="txt" optional="True" label="Dirichlet prior file" />
            </when>
            <when value="addone">
              <!-- no values here? -->
            </when>
          </conditional>
          <conditional name="spmap_type">
            <param name="spmap_type_selector" type="select" label="EM starting points">
              <option value="uni">uni</option>
              <option value="pam" selected="true">pam</option>
              <option value="cons">Use starting point from string</option>
            </param>
            <when value="uni">
              <param name="spfuzz" type="float" value="0.5" label="Fuzziness of the mapping" />
            </when>
            <when value="pam">
              <param name="spfuzz" type="integer" value="120" label="Fuzziness of the mapping" />
            </when>
            <when value="cons">
              <param name="cons" type="text" value="" label="Starting point from string" />
            </when>
          </conditional>
        </when>
        <when value="dna">
          <param name="revcomp" label="Check reverse complement" type="boolean" truevalue="-revcomp" falsevalue="" checked="False"/>
          <param name="pal" label="Check for palindromes" type="boolean" truevalue="-pal" falsevalue="" checked="False"/>
          <conditional name="prior_type">
            <param name="prior_type_selector" type="select" label="Sequence Alphabet">
              <option value="dirichlet" selected="true">simple Dirichlet prior</option>
              <option value="dmix">mixture of Dirichlets prior</option>
              <option value="mega">extremely low variance dmix</option>
              <option value="megap">mega for all but last iteration of EM; dmix on last iteration</option>
              <option value="addone">add +1 to each observed count</option>
            </param>
            <when value="dirichlet">
              <param name="prior_b" type="float" value="0.01" label="strength of prior on model parameters" />
              <param name="plib" type="data" format="txt" optional="True" label="Dirichlet prior file" />
            </when>
            <when value="dmix">
              <param name="prior_b" type="float" value="0" label="strength of prior on model parameters" />
              <param name="plib" type="data" format="txt" optional="True" label="Dirichlet prior file" />
            </when>
            <when value="mega">
              <param name="prior_b" type="float" value="0" label="strength of prior on model parameters" />
              <param name="plib" type="data" format="txt" optional="True" label="Dirichlet prior file" />
            </when>
            <when value="megap">
              <param name="prior_b" type="float" value="0" label="strength of prior on model parameters" />
              <param name="plib" type="data" format="txt" optional="True" label="Dirichlet prior file" />
            </when>
            <when value="addone">
              <!-- no values here? -->
            </when>
          </conditional>
          <conditional name="spmap_type">
            <param name="spmap_type_selector" type="select" label="EM starting points">
              <option value="uni" selected="true">uni</option>
              <option value="pam">pam</option>
              <option value="cons">Use starting point from string</option>
            </param>
            <when value="uni">
              <param name="spfuzz" type="float" value="0.5" label="Fuzziness of the mapping" />
            </when>
            <when value="pam">
              <param name="spfuzz" type="integer" value="120" label="Fuzziness of the mapping" />
            </when>
            <when value="cons">
              <param name="cons" type="text" value="" label="Starting point from string" />
            </when>
          </conditional>
        </when>
      </conditional>
      
      <param name="nmotifs" type="integer" value="1" label="Number of different motifs to search" />
      <param name="maxsize" type="integer" value="1000000" label="Max number of characters in the sequence file"/>
      <param name="evt" type="float" value="inf" label="E-value to stop looking for motifs" />
      <conditional name="mod_type">
        <param name="mod_type_selector" type="select" label="Expected motif distribution">
          <option value="oops">One Occurrence Per Sequence</option>
          <option value="zoops" selected="true">Zero or One Occurrence Per Sequence</option>
          <option value="anr">Any Number of Repetitions</option>
        </param>
        <when value="oops">
          <!-- no values here -->
        </when>
        <when value="zoops">
          <conditional name="motif_occurrence_type">
            <param name="motif_occurrence_type_selector" type="select" label="Number of motif occurrences">
              <option value="default" selected="true">Use defaults</option>
              <option value="nsites">nsites</option>
              <option value="min_max_sites">min and max sites</option>
            </param>
            <when value="default">
              <!-- no values here -->
            </when>
            <when value="nsites">
              <param name="nsites" type="integer" value="1" label="Search nsites number of occurrences" />
            </when>
            <when value="min_max_sites">
              <param name="minsites" type="integer" value="1" label="minsites" />
              <param name="maxsites" type="integer" value="50" label="maxsites" />
            </when>
          </conditional>
        </when>
        <when value="anr">
          <conditional name="motif_occurrence_type">
            <param name="motif_occurrence_type_selector" type="select" label="Number of motif occurrences">
              <option value="default" selected="true">Use defaults</option>
              <option value="nsites">nsites</option>
              <option value="min_max_sites">min and max sites</option>
            </param>
            <when value="default">
              <!-- no values here -->
            </when>
            <when value="nsites">
              <param name="nsites" type="integer" value="1" label="Search nsites number of occurrences" />
            </when>
            <when value="min_max_sites">
              <param name="minsites" type="integer" value="1" label="minsites" />
              <param name="maxsites" type="integer" value="50" label="maxsites" />
            </when>
          </conditional>
        </when>
      </conditional>
      <param name="wnsites" type="float" value="0.8" label="Weight on the prior on nsites" />
      
      <conditional name="motif_width_type">
        <param name="motif_width_type_selector" type="select" label="Motif width type">
          <option value="exact">Exact width</option>
          <option value="range" selected="true">Specify a range</option>
        </param>
        <when value="exact">
          <param name="width" type="integer" value="10" label="Width of motif to search" />
        </when>
        <when value="range">
          <param name="minw" type="integer" value="8" label="Min width of motif to search" />
          <param name="maxw" type="integer" value="50" label="Max width of motif to search" />
        </when>
      </conditional>
    
      <conditional name="motif_trim_type">
        <param name="motif_trim_type_selector" type="select" label="Motif trim type">
          <option value="nomatrim">No motif trim</option>
          <option value="trim" selected="true">Trim motif</option>
        </param>
        <when value="nomatrim">
          <!-- no values here -->
        </when>
        <when value="trim">
          <param name="wg" type="integer" value="11" label="Gap cost" />
          <param name="ws" type="integer" value="1" label="Space cost" />
          <param name="noendgaps" label="Do not penalize endgaps" type="boolean" truevalue="-noendgaps" falsevalue="" checked="False"/>
        </when>
      </conditional>
    
    <param name="bfile" type="data" format="txt" optional="True" label="Background Model" />
    <param name="pspfile" type="data" format="txt" optional="True" label="Position-Specific Prior" />
    
    <param name="maxiter" type="integer" value="50" label="Number of iterations of EM to run" />
    <param name="distance" type="float" value="0.001" label="Convergence criterion" />
    
      <conditional name="branching_type">
        <param name="branching_type_selector" type="select" label="x-branching type">
          <option value="x_branch">Perform x-branching</option>
          <option value="no_x_branch" selected="true">No x-branching</option>
        </param>
        <when value="no_x_branch">
          <!-- no values here -->
        </when>
        <when value="x_branch">
          <param name="bfactor" type="integer" value="3" label="Number of iterations of branching" />
          <param name="heapsize" type="integer" value="64" label="Maximum number of heaps to use" />
        </when>
      </conditional>
  
    </when>
  </conditional>
  
  <param name="non_commercial_use" label="I certify that I am not using this tool for commercial purposes." type="boolean" truevalue="NON_COMMERCIAL_USE" falsevalue="COMMERCIAL_USE" checked="False">
    <validator type="expression" message="This tool is only available for non-commercial use.">value == True</validator>
  </param>
  
  </inputs>
  <outputs>
    <data format="html" name="html_outfile" label="${tool.name} on ${on_string} (html)"/>
    <data format="txt" name="txt_outfile" label="${tool.name} on ${on_string} (text)"/>
    <data format="memexml" name="xml_outfile" label="${tool.name} on ${on_string} (xml)"/>
  </outputs>
  <tests>
    <test>
      <param name="input1" value="meme/meme/meme_input_1.fasta" ftype="fasta" dbkey="hg19"/>
      <param name="options_type_selector" value="basic"/>
      <param name="non_commercial_use" value="True"/>
      <output name="html_outfile" file="meme/meme/meme_output_html_1.html" lines_diff="12"/>
      <output name="txt_outfile" file="meme/meme/meme_output_txt_1.txt" lines_diff="12"/>
      <output name="xml_outfile" file="meme/meme/meme_output_xml_1.xml" lines_diff="8"/>
    </test>
  </tests>
  <help>

.. class:: warningmark

**WARNING: This tool is only available for non-commercial use. Use for educational, research and non-profit purposes is permitted. Before using, be sure to review, agree, and comply with the license.**

If you want to specify sequence weights, you must include them at the top of your input FASTA file.

.. class:: infomark

**To cite MEME:**
Timothy L. Bailey and Charles Elkan, "Fitting a mixture model by expectation maximization to discover motifs in biopolymers", Proceedings of the Second International Conference on Intelligent Systems for Molecular Biology, pp. 28-36, AAAI Press, Menlo Park, California, 1994. 


For detailed information on MEME, click here_. To view the license_.

.. _here: http://meme.nbcr.net/meme/meme-intro.html
.. _license: http://meme.nbcr.net/meme/COPYRIGHT.html

  </help>
</tool>