<?xml version="1.0"?>
<tool id="hivclustering" name="Make inferences" version="@VERSION@.0">
    <description>on HIV-1 transmission networks using HIVClustering</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <command detect_errors="exit_code">
    <![CDATA[
    hivnetworkcsv --input $input $cluster $multiple_edges $singletons $centralities
        --threshold $threshold --exclude $exclude --triangles $triangles --format $format
        #if $contamination.contaminants != 'ignore':
            --contaminants $contamination.contaminants
            --contaminant-file $contamination.contaminant_file
        #end if
        #if $edges.edge_filtering != 'ignore':
            --edge-filtering $edges.edge_filtering
            --sequences $sequences
        #end if
        #if $uds:
            --uds $uds
        #end if
        #if $edi:
            --edi $edi
        #end if
        #if $old_edi:
            --old_edi $old_edi
        #end if
        #if $resistance:
            --resistance $resistance
        #end if
        #if $attributes:
            --attributes $attributes
        #end if
        #if $filter:
            --filter $filter
        #end if
        --json > hivcluster.json
    ]]>
    </command>
    <inputs>
        <param argument="--input" type="data" format="csv" multiple="True" label="Input file with inferred links" />
        <conditional name="contamination">
            <param argument="--contaminants" type="select" label="How to treat contamination">
                <option value="ignore" selected="True">Do nothing</option>
                <option value="report">Report</option>
                <option value="remove">Remove</option>
            </param>
            <when value="ignore" />
            <when value="report">
                <param name="contaminant_file" argument="--contaminant-file" type="data" format="tabular" label="Input file with contaminant IDs" />
            </when>
            <when value="remove">
                <param name="contaminant_file" argument="--contaminant-file" type="data" format="tabular" label="Input file with contaminant IDs" />
            </when>
        </conditional>
        <conditional name="edges">
            <param name="edge_filtering" argument="--edge-filtering" type="select" label="Compute edge support and mark edges">
                <option value="ignore" selected="True">Do not mark</option>
                <option value="report">For display</option>
                <option value="remove">For removal</option>
            </param>
            <when value="ignore" />
            <when value="report">
                <param argument="--sequences" type="data" format="hmmer3" multiple="True" label="Input multi-sequence alignment" />
            </when>
            <when value="remove">
                <param argument="--sequences" type="data" format="hmmer3" multiple="True" label="Input multi-sequence alignment" />
            </when>
        </conditional>
        <param argument="--uds" type="data" format="csv" optional="True" label="Input file with UDS data" />
        <param argument="--edi" type="data" format="json" optional="True" label="Input JSON with clinical information" />
        <param argument="--old_edi" type="data" format="csv" optional="True" label="Legacy EDI dates in CSV format" />
        <param argument="--resistance" type="data" format="csv" optional="True" label="Resistance annotation in JSON format" />
        <param argument="--attributes" type="data" format="csv" optional="True" label="Input CSV with node attributes" />
        <param argument="--filter" type="data" format="text" optional="True" label="File with IDs to cluster, one per line" />
        <param argument="--format" type="select" label="Sequence ID format">
            <option value="AEH">AEH</option>
            <option value="LANL">LANL</option>
            <option value="plain">plain</option>
        </param>
        <param argument="--cluster" type="boolean" truevalue="--cluster hivcluster.csv" falsevalue="" label="Output a CSV file with cluster assignments for each sequence" />
        <param name="multiple_edges" argument="--multiple-edges" type="boolean" truevalue="--multiple-edges" falsevalue="" label="Permit multiple edges to link the same pair of nodes in the network" />
        <param argument="--singletons" type="boolean" truevalue="--singletons" falsevalue="" label="Include singletons in output" />
        <param argument="--centralities" type="boolean" truevalue="--centralities" falsevalue="" label="Output a CSV file with node centralities" />
        <param argument="--threshold" type="float" value="0.015" label="Only count edges where the distance is less than this threshold" />
        <param argument="--exclude" type="integer" value="1959" label="Only consider sequences isolated after this year" />
        <param argument="--triangles" type="integer" value="65536" label="Maximum number of triangles to consider in each filtering pass" />
    </inputs>
    <outputs>
        <data name="graph" from_work_dir="hivcluster.json" format="json" />
    </outputs>
    <tests>
        <test>
            <param name="input" value="hivclustering-in1.csv" ftype="csv" />
            <param name="format" value="plain" />
            <param name="threshold" value="0.8" />
            <param name="json" value="True" />
            <output name="output" ftype="json" file="hivclustering-out1.json" />
        </test>
        <test>
            <param name="input" value="hivclustering-in2.csv" ftype="csv" />
            <param name="format" value="plain" />
            <param name="threshold" value="0.8" />
            <param name="json" value="True" />
            <output name="output" ftype="json" file="hivclustering-out2.json" />
        </test>
    </tests>
    <help>A Python 3 library that makes inferences on HIV-1 transmission networks.</help>
</tool>