<tool id="cluster-pick" name="Cluster Picker" version="1.2.3">
  <description>cluster picker</description>
<requirements>
    <requirement type="package" version="1.2.3">cluster-picker</requirement>
</requirements>
<command> <![CDATA[ln -s '$sequence_file' seq.dat &&
    ln -s '$tree_file' tree.dat &&
    cluster-picker seq.dat tree.dat $init_threshold $main_threshold $dis_threshold $size $genetic_distance
  ]]> </command>
<inputs>
  <param format="fasta" name="sequence_file" type="data" label="align"
    help="Please enter fasta format sequences file name to process"/>
  <param format="nhx" name="tree_file" type="data" label="tree"
    help="Please enter newick format tree, with branch lengths and node support"/>
  <param name="init_threshold" type="float" value="0.9" optional="true"
    help="Please enter initial support threshold for these initial subtrees" label="initial threshold">
  </param>
  <param name="main_threshold" type="float" value="0.9" optional="true"
    help="Please enter main support threshold for clusters" label="main threshold">
  </param>
  <param name="dis_threshold" type="float" value="0.045" optional="true"
    help="Please enter genetic distance threshold for clusters in %" label="distance threshold">
  </param>
  <param name="size" type="integer" value="10" optional="true"
    help="To output all cluster names for clusters of size >= X enter X" label="size">
  </param>
  <param name="genetic_distance" type="select" label="genetic distance"
    help="Please enter scoring type for genetic distance\n
          gap      	= disregard sites with -, ~, or n\n
          abs      	= count absolute character differences\n
          valid    	= only count differences for sites with nucleotides: a, c, t, g in both sequences\n
          ambiguity	= disregard sites with -, ~, or n and do not count ambiguities as differences (e.g. a vs r is not a difference)">
      <option value="gap">gap</option>
      <option value="abs">abs</option>
      <option value="valid">valid</option>
      <option value="ambiguity">ambiguity</option>
  </param>
</inputs>
<outputs>
  <data name='fig' format="figTree" from_work_dir="tree_clusterPicks.nwk.figTree"/>
  <data name='tr' format="nhx" from_work_dir="tree_clusterPicks.nwk"/>
  <data name='log' format="txt" from_work_dir="tree_clusterPicks_log.txt"/>
  <data name='seq' format="fasta" from_work_dir="seq.dat_tree_clusterPicks.fasta"/>
</outputs>

<tests>
    <test>
        <param name="sequence_file" value="dummy.fasta" />
        <param name="tree_file" value="dummy.nhx" />
        <param name="init_threshold" value="0.9" />
        <param name="main_threshold" value="0.9" />
        <param name="dis_threshold" value="0.045" />
        <param name="size" value="10" />
        <param name="genetic_distance" value="gap" />
        <param name="main_threshold" file="0.9" />
        <output name="fig" file="dummy.figTree" />
    </test>
</tests>

<help>
Cluster identification strategies differ between studies and as a consequence cluster definitions vary.
</help>
<citations>
   <citation type="bibtex">@ARTICLE{cluster-picker,
   author = {Ragonnet-Cronin, Manon, et al;},
   title = {Automated analysis of phylogenetic clusters},
   journal = {BMC bioinformatics},
   year = {2013},
   volume = {14.1},
   pages = {317}}
 </citation>
</citations>
</tool>