<tool id="metaphlan_2" name="MetaPhlAn2" version="0.1.0">

    <description>to profile the composition of microbial communities</description>

    <requirements>
        <requirement type="package" version="2.2.5">bowtie2</requirement>
        <requirement type="package" version="2.0">metaphlan2</requirement>
    </requirements>

    <stdio>
        <exit_code range="1:" level="fatal"   description="" />
        <regex match="ERROR"
               source="stderr"
               level="fatal"
               description="" />
        <regex match="WARNING"
               source="stderr"
               level="warning"
               description="" />
    </stdio>

    <version_command>
<![CDATA[
python \${METAPHLAN2_DIR}/metaphlan2.py -v
]]>
    </version_command>

    <command>
<![CDATA[        
        (which bowtie2 || exit 200)

        &&

        python \${METAPHLAN2_DIR}/metaphlan2.py
            $input_file
            -o $output_file

            --input_type ${input_file.datatype.file_ext}
            --mpa_pkl \${METAPHLAN2_DIR}/db_v20/mpa_v20_m200.pkl 

            --bowtie2_exe `which bowtie2`
            --bowtie2db \${METAPHLAN2_DIR}/db_v20/mpa_v20_m200

            --no_map

            -t $analysis_type.analysis_type_select
            #if $analysis_type.analysis_type_select == "rel_ab"
                --tax_lev $analysis_type.taxonomic_level 
            #else if $analysis_type.analysis_type_select == "marker_ab_table"
                --nreads $analysis_type.nreads
            #else if $analysis_type.analysis_type_select == "marker_pres_table"
                --pres_th $analysis_type.pres_th 
            #end if

            --min_cu_len $min_cu_len
            --min_alignment_len $min_alignment_len

            $ignore_viruses
            $ignore_eukaryotes
            $ignore_bacteria
            $ignore_archaea

            --stat_q $stat_q

            #if $sam_output
                -s $sam_output_file
            #end if

            #if $biom_output
                --biom $biom_output_file
            #end if
]]>
    </command>

    <inputs>
        <param name="input_file" type="data" format="fastq,fasta,sam,bowtie2out" label="Input file" help=""/>

        <conditional name="analysis_type">
            <param name="analysis_type_select" type="select" label="Type of analysis to perform">
              <option value="rel_ab" selected="true">Profiling a metagenomes in terms of relative abundances</option>
              <option value="rel_ab_w_read_stats">Profiling a metagenomes in terms of relative abundances and estimate the number of reads comming from each clade</option>
              <option value="reads_map">Mapping from reads to clades (only reads hitting a marker)</option>
              <option value="clade_profiles">Normalized marker counts for clades with at least a non-null marker</option>
              <option value="marker_ab_table">Normalized marker counts (only when > 0.0 and normalized by metagenome size if --nreads is specified)</option>
              <option value="marker_pres_table">List of markers present in the sample (threshold at 1.0 if not differently specified with --pres_th</option>
            </param>
            <when value="rel_ab">
              <param name="taxonomic_level" type="select" label="Taxonomic level for the relative abundance output">
                <option value="a" selected="true">All taxonomic levels</option>
                <option value="k">Kingdoms (Bacteria and Archaea) only</option>
                <option value="p">Phyla only</option>
                <option value="c">Classes only</option>
                <option value="o">Orders only</option>
                <option value="f">Families only</option>
                <option value="g">Genera only</option>
                <option value="s">Species only</option>
              </param>
            </when>
            <when value="rel_ab_w_read_stats"/>
            <when value="reads_map"/>
            <when value="clade_profiles"/>
            <when value="marker_ab_table">
                <param name="nreads" type="integer" value="0" label="Total number of reads in the original metagenome" help="It is used for normalizing the length-normalized counts with the metagenome size as well. No normalization applied if the value is not specified"/>
            </when>
            <when value="marker_pres_table">
                <param name="pres_th" type="integer" value="0" label=" Threshold for calling a marker present" help=""/>
            </when>
        </conditional>

        <param name="min_cu_len" type="integer" value="2000" label="Minimum total nucleotide length for the markers in a clade for estimating the abundance without considering sub-clade abundances" help=""/>

        <param name="min_alignment_len" type="integer" value="0" label="Sam records for aligned reads with the longest subalignment length smaller than this threshold will be discarded." help=""/>

        <param name="ignore_viruses" type='boolean' checked="true" truevalue='' falsevalue='--ignore_viruses' label="Profile viral organisms?" help="" />
        <param name="ignore_eukaryotes" type='boolean' checked="true" truevalue='' falsevalue='--ignore_eukaryotes' label="Profile eukaryotic organisms?" help="" />
        <param name="ignore_bacteria" type='boolean' checked="true" truevalue='' falsevalue='--ignore_bacteria' label="Profile bacteria organisms?" help="" />
        <param name="ignore_archaea" type='boolean' checked="true" truevalue='' falsevalue='--ignore_archaea' label="Profile archea organisms?" help="" />

        <param name="stat_q" type="float" value="0.1" label="Quantile value for the robust average" help=""/>

        <param name="sam_output" type='boolean' label="Output a sam file?" help="" />
        <param name="biom_output" type='boolean' label="Output a biom file?" help="" />
    </inputs>

    <outputs>
        <data format="txt" name="output_file" 
            metadata="input_sequence_file" 
            label="Profile of communities on ${on_string} (MetaPhlAn)" />

        <data format="sam" name="sam_output_file" 
            metadata="input_sequence_file" 
            label="Sam output on ${on_string} (MetaPhlAn)">
            <filter>sam_output</filter>
        </data>
        <data format="biom" name="biom_output_file" 
            metadata="input_sequence_file" 
            label="Biom output on ${on_string} (MetaPhlAn)">
            <filter>biom_output</filter>
        </data>
    </outputs>

    <tests>
        <test>
            <param name="input_file" value="metaphlan2_input_sequences.fastq"/>
            <param name="analysis_type_select" value="rel_ab" />
            <param name="taxonomic_level" value="a" />
            <param name="min_cu_len" value="2000" />
            <param name="min_alignment_len" value="0" />
            <param name="ignore_viruses" value="" />
            <param name="ignore_eukaryotes" value="" />
            <param name="ignore_bacteria" value="" />
            <param name="ignore_archaea" value="" />
            <param name="stat_q" value="0.1" />
            <param name="sam_output" value='false' />
            <param name="biom_output" value='true' />
            <output name="output_file" file="metaphlan2_profiled_metagenome.txt"/>
            <output name="biom_output_file" file="metaphlan2_biom.biom"/>
        </test>
    </tests>

    <help><![CDATA[

**What it does**

MetaPhlAn is a computational tool for profiling the composition of microbial 
communities (Bacteria, Archaea, Eukaryotes and Viruses) from metagenomic shotgun 
sequencing data with species level resolution. For more information, check the 
`user manual <https://bitbucket.org/biobakery/metaphlan2/>`_.

-----

**Input**

Metaphlan2 takes as input a sequence file in fasta, fastq, a BowTie2 produced
SAM file or an intermediary mapping file of the metagenome generated by a 
previous MetaPhlAn

-----

**Parameters**

Several parameters can modulate the MetaPhlAn execution

    * Mapping arguments

        * Test to avoid saving the output of BowTie2

    * Post-mapping arguments

        * Taxonomic level for the relative abundance output
        * Minimum total nucleotide length for the markers in a clade for estimating the abundance without considering sub-clade abundances
        * Sam records for aligned reads with the longest subalignment length smaller than this threshold will be discarded
        * Tests to avoid profiling of virus, eukaryotes, bacteria and/or archea
        * Quantile value

    * Additional analysis types and arguments

        * Type of analyse to perform and some parameters for specific analysis type

-----

**Outputs**

The main output file is a tab-separated output file of the predicted taxon 
relative abundances.

Given the choosen parameters, other output files can be:

    * a sam output file
    * a biom output fime
    * a BowTie2 output file

    ]]></help>

    <citations>
        <citation type="doi">10.1038/nmeth.3589</citation>
    </citations>
</tool>