annotate mothur/tools/mothur/cluster.split.xml @ 2:e990ac8a0f58

Migrated tool version 1.19.0 from old tool shed archive to new tool shed repository

<tool id="mothur_cluster_split" name="Cluster.split" version="1.19.0">
 <description>Assign sequences to OTUs (Operational Taxonomic Unit) splits large matrices</description>
 <command interpreter="python">
  mothur_wrapper.py 
  --cmd='cluster.split'
  --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.sabund$:'$sabund,'^\S+\.rabund$:'$rabund,'^\S+\.list$:'$otulist,'^\S+\.dist$:'$dist_out
  --outputdir='$logfile.extra_files_path'
  #if $splitby.splitmethod == "distance":
   #if $splitby.matrix.format == "column":
    --column=$splitby.matrix.dist
    --name=$splitby.matrix.name
   #elif $splitby.matrix.format == "phylip":
    --phylip=$splitby.matrix.dist
    #if $splitby.matrix.name.__str__ != "None" and len($splitby.matrix.name.__str__) > 0:
     --name=$splitby.matrix.name
    #end if
   #end if
   --splitmethod=$splitby.splitmethod
  #elif $splitby.splitmethod == "classify":
   --column=$splitby.dist
   --name=$splitby.name
   --taxonomy=$splitby.taxonomy
   #if $splitby.taxlevel > 1:
    --taxlevel=$splitby.taxlevel
   #end if
   --splitmethod=$splitby.splitmethod
  #elif $splitby.splitmethod == "fasta":
   --fasta=$splitby.fasta
   --name=$splitby.name
   --taxonomy=$splitby.taxonomy
   #if $splitby.taxlevel > 1:
    --taxlevel=$splitby.taxlevel
   #end if
   --splitmethod=$splitby.splitmethod
  #end if
  #if len($method.__str__) > 0:
   --method=$method
  #end if
  #if float($cutoff.__str__) > 0.0:
   --cutoff=$cutoff
  #end if
  $hard
  #if len($precision.__str__) > 0:
   --precision=$precision
  #end if
  $large
  --processors=1
 </command>
 <inputs>
  <conditional name="splitby">
   <param name="splitmethod" type="select" label="Split by" help="">
    <option value="distance">Distance</option>
    <option value="classify">Classification</option>
    <option value="fasta">Classification using fasta</option>
   </param>
   <when value="distance">
    <conditional name="matrix">
     <param name="format" type="select" label="Select a Distance Matrix Format" help="">
      <option value="column">Pairwise Column Matrix</option>
      <option value="phylip">Phylip Distance Matrix</option>
     </param>
     <when value="column">
      <param name="dist" type="data" format="pair.dist" label="column - Distance Matrix"/>
      <param name="name" type="data" format="names" label="name - Sequences Name reference"/>
     </when>
     <when value="phylip">
      <param name="dist" type="data" format="lower.dist,square.dist" label="phylip - Distance Matrix"/>
      <param name="name" type="data" format="names" optional="true" label="name - Sequences Name reference"/>
     </when>
    </conditional>
   </when>
   <when value="classify">
    <param name="dist" type="data" format="pair.dist" label="column - Distance Matrix"/>
    <param name="name" type="data" format="names" label="name - Sequences Name reference"/>
    <param name="taxonomy" type="data" format="seq.taxonomy" label="taxonomy - Taxonomy (from Classify.seqs)"/>
    <param name="taxlevel" type="integer" value="1" label="taxlevel - taxonomy level for split (default=1)" 
           help="taxonomy level you want to use to split the distance file, default=1, meaning use the first taxon in each list"/>
   </when>
   <when value="fasta">
    <param name="fasta" type="data" format="fasta" label="fasta - Sequences"/>
    <param name="name" type="data" format="names" label="name - Sequences Name reference"/>
    <param name="taxonomy" type="data" format="seq.taxonomy" label="taxonomy - Taxonomy (from Classify.seqs)"/>
    <param name="taxlevel" type="integer" value="1" label="taxlevel - taxonomy level for split (default=1)" 
           help="taxonomy level you want to use to split the distance file, default=1, meaning use the first taxon in each list"/>
   </when>
  </conditional> <!-- splitby -->
  <param name="method" type="select" label="method - Select a Clustering Method" help="">
   <option value="furthest">Furthest neighbor</option>
   <option value="nearest">Nearest neighbor</option>
   <option value="average" selected="true">Average neighbor</option>
  </param>
  <param name="cutoff" type="float" value="0.0" label="cutoff - Distance Cutoff threshold - ignored if not > 0" 
                 help="Ignore pairwise distances larger than this, a common value would be 0.10"/>
  <param name="hard" type="boolean" checked="true" truevalue="--hard=true" falsevalue="--hard=true" label="hard - Use hard cutoff instead of rounding" 
                 help=""/>
  <param name="precision" type="select" optional="true" label="precision - Precision for rounding distance values"
                 help="Set higher precision for longer genome scale sequence lengths">
   <option value="10">.1</option>
   <option value="100" selected="true">.01</option>
   <option value="1000">.001</option>
   <option value="10000">.0001</option>
   <option value="100000">.00001</option>
   <option value="1000000">.000001</option>
  </param>
  <param name="large" type="boolean" checked="false" truevalue="--large=true" falsevalue="" label="large - distance matrix is too large to fit in RAM" 
                 help="If your job fails due to not enough memory error, set this to true to rerun"/>
 </inputs>
 <outputs>
  <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" />
  <data format="rabund" name="rabund" label="${tool.name} on ${on_string}: rabund (Rank Abundance)"/>
  <data format="sabund" name="sabund" label="${tool.name} on ${on_string}: sabund (Species Abundance)"/>
  <data format="list" name="otulist" label="${tool.name} on ${on_string}: list (OTU List)"/>
  <data format="pair.dist" name="dist_out" label="${tool.name} on ${on_string}: Column dist">
   <filter>splitby.splitmethod == 'fasta' </filter>
  </data>
 </outputs>
 <requirements>
  <requirement type="binary">mothur</requirement>
 </requirements>
 <tests>
 </tests>
 <help>
**Mothur Overview**

Mothur_, initiated by Dr. Patrick Schloss and his software development team
in the Department of Microbiology and Immunology at The University of Michigan,
provides bioinformatics for the microbial ecology community.

.. _Mothur: http://www.mothur.org/wiki/Main_Page

**Command Documenation**

The cluster.split_ command assign sequences to OTUs (Operational Taxonomy Unit). 

.. _cluster.split: http://www.mothur.org/wiki/Cluster.split


 </help>
</tool>