<?xml version="1.0"?>
<tool id="shorah_amplicon" version="@VERSION@+galaxy0" name="Reconstruct haplotypes">
    <description>with ShoRAH in amplicon mode</description>
    <macros>
        <token name="@VERSION@">1.1.3</token>
    </macros>
    <requirements>
        <requirement type="package" version="@VERSION@">shorah</requirement>
    </requirements>
    <command detect_errors="exit_code">
    <![CDATA[
    ln -s '$bam' input.bam &&
    ln -s '$fasta' input.fa &&
    amplian.py
        --bam input.bam
        --fasta input.fa
        #if str($region):
            --region '$region'
        #end if
        $diversity
        --min_overlap $min_overlap
        --alpha $alpha
        --maxcov $maxcov
        --sigma $sigma &&
    sed -i.bak 's/,/\t/g' SNVs_0.010000_final.csv

    ]]>
    </command>
    <inputs>
        <param argument="--bam" type="data" format="bam" label="Aligned reads in .bam format" />
        <param argument="--fasta" type="data" format="fasta" label="Reference genome in fasta format" />
        <param argument="--region" type="text" value="" optional="true" label="Limit to a specific region" help="e.g. 'ch3:1000-1300'" />
        <param argument="--diversity" type="boolean" truevalue="--diversity" falsevalue="" label="Run on the highest entropy region" />
        <param argument="--min_overlap" type="float" value="0.95" min="0" max="1" optional="true" label="Fraction of read overlap to be included" />
        <param argument="--alpha" type="float" value="0.5" optional="true" label="Alpha in dpm sampling" />
        <param argument="--maxcov" type="integer" value="50000" optional="true" label="Approximate max coverage allowed" />
        <param argument="--sigma" type="float" value="0.01" optional="true" label="Sigma value to use when calling SNVs" />
        <param name="log_output" type="boolean" truevalue="log" falsevalue="" label="Include the log in the history" />
    </inputs>
    <outputs>
        <data name="haplotypes" format="tabular" from_work_dir="SNVs_0.010000_final.csv" label="${tool.name} on ${on_string}: Haplotypes" />
        <data name="log" format="txt" from_work_dir="SNV.txt" label="${tool.name} on ${on_string}: Log">
            <filter>log_output</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="bam" ftype="bam" value="shorah-amplicon-in1.bam" />
            <param name="fasta" ftype="fasta" value="shorah-amplicon-in1.fa" />
            <param name="min_overlap" value="0.95" />
            <param name="log_output" value="log" />
            <output name="haplotypes" file="shorah-amplicon-out1.tsv" compare="re_match" />
            <output name="log" file="shorah-amplicon-out1.txt" compare="re_match" />
        </test>
    </tests>
    <help>
<![CDATA[
ShoRAH is an open source project for the analysis of next generation sequencing data. It is designed to analyse genetically heterogeneous samples. Its tools are written in different programming languages and provide error correction, haplotype reconstruction and estimation of the frequency of the different genetic variants present in a mixed sample.
]]>
    </help>
    <citations>
        <citation type="doi">10.1186/1471-2105-12-119</citation>
    </citations>
</tool>