<tool id="gd_add_fst_column" name="Add an FST column" version="1.0.0">
  <description>to a table</description>

  <command interpreter="python">
    add_fst_column.py "$input" "$p1_input" "$p2_input" "$data_source" "$min_reads" "$min_qual" "$retain" "$discard_fixed" "$biased" "$output"
    #for $individual, $individual_col in zip($input.dataset.metadata.individual_names, $input.dataset.metadata.individual_columns)
        #set $arg = '%s:%s' % ($individual_col, $individual)
        "$arg"
    #end for
  </command>

  <inputs>
    <param name="input" type="data" format="snp" label="SNP table" />
    <param name="p1_input" type="data" format="ind" label="Population 1 individuals" />
    <param name="p2_input" type="data" format="ind" label="Population 2 individuals" />

    <param name="data_source" type="select" format="integer" label="Data source">
      <option value="0" selected="true">sequence coverage</option>
      <option value="1">estimated genotype</option>
    </param>

    <param name="min_reads" type="integer" min="0" value="0" label="Minimum total read count for a population" />
    <param name="min_qual" type="integer" min="0" value="0" label="Minimum individual genotype quality" />

    <param name="retain" type="select" label="Special treatment">
      <option value="0" selected="true">Skip row</option>
      <option value="1">Set FST = -1</option>
    </param>

    <param name="discard_fixed" type="select" label="Apparently fixed SNPs">
      <option value="0">Retain SNPs that appear fixed in the two populations</option>
      <option value="1" selected="true">Delete SNPs that appear fixed in the two populations</option>
    </param>

    <param name="biased" type="select" label="FST estimator">
      <option value="0" selected="true">Wright's original definition</option>
      <option value="1">Weir's unbiased estimator</option>
    </param>

  </inputs>

  <outputs>
    <data name="output" format="snp" metadata_source="input" />
  </outputs>

  <tests>
    <test>
      <param name="input" value="test_in/sample.snp" ftype="snp" />
      <param name="p1_input" value="test_in/a.ind" ftype="ind" />
      <param name="p2_input" value="test_in/b.ind" ftype="ind" />
      <param name="data_source" value="0" />
      <param name="min_reads" value="3" />
      <param name="min_qual" value="0" />
      <param name="retain" value="0" />
      <param name="discard_fixed" value="1" />
      <param name="biased" value="0" />
      <output name="output" file="test_out/add_fst_column/add_fst_column.snp" />
    </test>
  </tests>

  <help>
**What it does**

The user specifies a SNP table and two "populations" of individuals,
both previously defined using the Galaxy tool to select individuals from
a SNP table.  No individual can be in both populations.  Other choices are
as follows.

Data source.  The allele frequencies of a SNP in the two populations can be
estimated either by the total number of reads of each allele, or by adding
the frequencies inferred from genotypes of individuals in the populations.

After specifying the data source, the user sets lower bounds on amount
of data required at a SNP.  For estimating the Fst using read counts,
the bound is the minimum count of reads of the two alleles in a population.
For estimations based on genotype, the bound is the minimum reported genotype
quality per individual.

The user specifies whether the SNPs that violate the lower bound should be
ignored or the Fst set to -1.

The user specifies whether SNPs where both populations appear to be fixed
for the same allele should be retained or discarded.

Finally, the user chooses which definition of Fst to use:  Wright's original
definition or Weir's unbiased estimator.

A column is appended to the SNP table giving the Fst for each retained SNP.
  </help>
</tool>