<?xml version="1.0"?>
<tool id="hyphy_sm19" name="HyPhy-SM2019" version="2.5.0+galaxy0">
  <description>- Partition Tree using Modified Slatkin-Maddison Test</description>
  <macros>
    <import>macros.xml</import>
  </macros>
  <expand macro="requirements"/>
  <command detect_errors="exit_code"><![CDATA[
    #set $count = len($partitions)
    ln -s '$input_file' sm19_input.nhx &&
    @HYPHY_ENVIRONMENT@ HYPHYMP LIBPATH=\$HYPHY_LIB
    \$HYPHY_LIB/TemplateBatchFiles/SM-2019.bf `pwd`/sm19_input.nhx $count
    #for $n, $partition in enumerate($partitions):
        '${partition.label}'
        '${partition.regex}'
    #end for
    $replicates
    ]]></command>
  <inputs>
    <param name="input_file" type="data" format="nhx" label="Input tree"/>
    <repeat name="partitions" min="2" max="50" title="Partitions">
      <param name="label" type="text" label="Partition label"/>
      <param name="regex" type="text" label="Regular expression">
        <sanitizer>
          <valid initial="string.printable">
            <remove value="'"/>
          </valid>
          <mapping initial="none">
            <add source="'" target="__sq__"/>
          </mapping>
        </sanitizer>
      </param>
    </repeat>
    <param name="replicates" type="integer" min="1" max="1000000" value="100"/>
  </inputs>
  <outputs>
    <data name="sm19_output" format="hyphy_json_results" from_work_dir="sm19_input.nhx.json"/>
  </outputs>
  <tests>
    <test>
      <param name="input_file" ftype="fasta" value="sm19-in1.nhx"/>
      <param name="replicates" value="1000"/>
      <repeat name="partitions">
        <param name="label" value="Blood"/>
        <param name="regex" value="B[0-9]+"/>
      </repeat>
      <repeat name="partitions">
        <param name="label" value="Semen"/>
        <param name="regex" value="S[0-9]+"/>
      </repeat>
      <output name="sm19_output" file="sm19-out1.json" compare="sim_size"/>
    </test>
    <test>
      <param name="input_file" ftype="fasta" value="sm19-in2.nhx"/>
      <param name="replicates" value="1000"/>
      <repeat name="partitions">
        <param name="label" value="Blood"/>
        <param name="regex" value="B[0-9]+"/>
      </repeat>
      <repeat name="partitions">
        <param name="label" value="Semen"/>
        <param name="regex" value="S[0-9]+"/>
      </repeat>
      <output name="sm19_output" file="sm19-out2.json" compare="sim_size"/>
    </test>
  </tests>
  <help><![CDATA[
This analysis implements canonical and modified versions of the Slatkin-Maddison
phylogeny based test for population segregation. The test estimates the minimum
number of migration events using maximum parsimony, and then evaluating whether
or not this number is lower than expected in a panmictic or unstructured
population using permutation tests.
        ]]></help>
  <expand macro="citations">
    <citation type="bibtex">
            @UNPUBLISHED{slatkin,
                author = "Slatkin M, Maddison WP",
                title = "A cladistic measure of gene flow inferred from the phylogenies of alleles",
                year = "1989",
                note = "Genetics 123(3):603-613",
                url = "https://www.ncbi.nlm.nih.gov/pubmed/2599370"}
        </citation>
  </expand>
</tool>