<?xml version="1.0"?>
<tool id="hyphy_bgm" name="HyPhy-BGM" version="@VERSION@+galaxy0">
    <description>- Detecting coevolving sites via Bayesian graphical models</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <command detect_errors="exit_code"><![CDATA[
        ln -s '$input_file' bgm_input.fa &&
        ln -s '$input_nhx' bgm_input.nhx &&
        @HYPHY_INVOCATION@ bgm
            --alignment ./bgm_input.fa
            --tree ./bgm_input.nhx
            --run_type $datatype.value
            #if $datatype.value == "codon":
                --code '$datatype.gencodeid'
            #end if
            #if $datatype.value == "protein":
                --baseline_model '$datatype.model'
            #end if
            --branches '$branches'
            --chain '$chain_length'
            --burn_in '$burn_in'
            --samples '$samples'
            --parents '$parents'
            --min_subs '$min_subs'
            > '$bgm_log'
    ]]></command>
    <inputs>
        <param name="input_file" type="data" format="fasta" label="Input FASTA file"/>
        <param name="input_nhx" type="data" format="nhx" label="Input newick file"/>
        <conditional name="datatype">
            <param name="value" type="select" label="Type of data">
                <option value="nucleotide">Nucleotide</option>
                <option value="amino-acid">Amino acid</option>
                <option value="codon">Codon</option>
            </param>
            <when value="nucleotide"/>
            <when value="amino-acid">
                <expand macro="substitution" />
            </when>
            <when value="codon">
                <expand macro="gencode" />
            </when>
        </conditional>
        <expand macro="branches"/>
        <param name="chain_length" type="integer" value="100000" min="0" max="1000000000" label="Length of MCMC chain"/>
        <param name="burn_in" type="integer" value="10000" min="0" max="1000000000" label="Number of samples to discard for burn-in"/>
        <param name="samples" type="integer" value="100" min="0" max="100" label="Number of steps to extract from chain sample"/>
        <param name="parents" type="integer" value="1" min="1" max="3" label="Maximum number of parents allowed per node"/>
        <param name="min_subs" type="integer" value="1" min="1" max="100000" label="Minimum number of ubstitutions per site to be included in the analysis"/>
    </inputs>
    <outputs>
        <data name="bgm_log" format="txt"/>
        <data name="bgm_output" format="hyphy_results.json" from_work_dir="bgm_input.fa.BGM.json"/>
    </outputs>
    <tests>
        <test>
            <param name="input_file" ftype="fasta" value="bgm-in1.fa"/>
            <param name="input_nhx" ftype="nhx" value="bgm-in1.nhx"/>
            <output name="bgm_output" file="bgm-out1.json" compare="sim_size"/>
        </test>
    </tests>
    <help><![CDATA[
The Bayesian Graphical Model (BGM) method is a tool for detecting coevolutionary interactions between amino acid positions in a protein.
    ]]></help>
    <expand macro="citations">
        <citation type="doi">10.1371/journal.pcbi.0030231</citation>
    </expand>
</tool>