annotate humann2.xml @ 1:bcd414bb721b draft default tip

planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/humann2/ commit 79571d981d7d56657699be8aa24a40a36a8d0ab5-dirty

<tool id="humann2" name="HUMAnN2" version="0.6.1">
    <description>to profile presence/absence and abundance of microbial pathways and gene families</description>

    <macros>
        <import>humann2_macros.xml</import>
    </macros>

    <expand macro="requirements"/>
    <expand macro="stdio"/>

    <version_command>
<![CDATA[
    humann2 --version
]]>
    </version_command>

    <command><![CDATA[
        `mkdir nucleotide_db`

        &&

        #if $nucleotide_db.nucleotide_db_selector == "history"
            #for $file in $nucleotide_db.history_nucleotide_db:
                `cp $file nucleotide_db/$file.name`
            #end for

            &&
        #end if

        `mkdir protein_db`

        &&

        #if $protein_db.protein_db_selector == "history"
            diamond makedb
                --in $protein_db.history_protein_db
                --db protein_db/protein_db
             &&
        #end if

        #if $taxonomic_profile.taxonomic_profile_test == "false"
          #if $taxonomic_profile.metaphlan2_db_choice.metaphlan2_db_selector == "history"
              `mkdir ref_db`
              &&
              bowtie2-build $taxonomic_profile.metaphlan2_db_choice.metaphlan2_db_sequences ref_db/ref_db
              &&
              python $__tool_directory__/transform_json_to_pkl.py
                  --json_input $metaphlan2_db_metadata
                  --pkl_output ref_db/metadata.pkl
              &&
          #end if
        #end if

        humann2
            -i "$input_file"

            #set $metaphlan_option = "-t rel_ab"
            #if $taxonomic_profile.taxonomic_profile_test == "true":
                --taxonomic-profile $taxonomic_profile.taxonomic_profile_file
            #else
                #if $taxonomic_profile.metaphlan2_db_choice.metaphlan2_db_selector == "cached"
                    #set $table = dict([(_[0], _[2]) for _ in $taxonomic_profile.metaphlan2_db_choice.cached_metaphlan2_db.input.options.tool_data_table.data])
                    #set $db_choice = $taxonomic_profile.metaphlan2_db_choice.cached_metaphlan2_db.value
                    #set $metaphlan_option += " --bowtie2db " + $table[$db_choice]
                    #set $metaphlan_option += " --mpa_pkl " + $table[$db_choice] + ".pkl"
                #else
                    #set $metaphlan_option += " --bowtie2db " + ref_db/ref_db
                    #set $metaphlan_option += " --mpa_pkl " + ref_db/metadata.pkl
                #end if
            #end if
            --metaphlan-options="$metaphlan_option"

            --evalue $e_value
            --identity-threshold $identity
            --prescreen-threshold $prescreen

            --pathways $pathways

            #if $nucleotide_db.nucleotide_db_selector == "cached"
                --nucleotide-database \${HUMANN2_DIR}/databases/chocophlan
            #else
                --nucleotide-database nucleotide_db
            #end if

            #if $protein_db.protein_db_selector == "cached"
                --protein-database \${HUMANN2_DIR}/databases/uniref
            #else
                --protein-database protein_db
            #end if

            --threads \${GALAXY_SLOTS:-4}

            --xipe $xipe
            --minpath $minpath
            --pick-frames $pick_frames

            -o "output"
            --output-format $output_format
            --output-max-decimals $output_max_dec
            --output-basename "humann2"
            $remove_statified_output
    ]]></command>

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

        <conditional name="taxonomic_profile">
            <param name='taxonomic_profile_test' type='select' label="Use a custom taxonomic profile?" help="The file must have been created by MetaPhlan2">
                <option value="true">Yes</option>
                <option value="false" selected="true">No</option>
            </param>
            <when value="true">
                <param name="taxonomic_profile_file" type="data" format="tabular,txt" label="Taxonomic profile file" help=""/>
            </when>
            <when value="false">
                <conditional name="metaphlan2_db_choice">
                    <param name="metaphlan2_db_selector" type="select" label="Database with clade-specific marker genes" help="">
                        <option value="cached" selected="true">Locally cached</option>
                        <option value="history">From history</option>
                    </param>

                    <when value="cached">
                        <param name="cached_metaphlan2_db" label="Cached database with clade-specific marker genes" type="select" >
                          <options from_data_table="metaphlan2_db" />
                        </param>
                    </when>
                    <when value="history">
                        <param name="metaphlan2_db_sequences" type="data" format="fasta" label="Database with clade-specific marker genes from history" help="(--bowtie2db)"/>
                        <param name="metaphlan2_db_metadata" type="data" format="json" label="Metadata associate to the database with clade-specific marker genes from history" help="(--mpa_pkl)"/>
                    </when>
                </conditional>
            </when>
        </conditional>

        <conditional name="nucleotide_db">
            <param name="nucleotide_db_selector" type="select" label="Nucleotide database" help="For locally cached databases, you need first to execute the tool to download HUMAnN2 databases">
                <option value="cached" selected="true">Locally cached</option>
                <option value="history">From history (as collection)</option>
            </param>

            <when value="cached"/>
            <when value="history">
                <param format="fasta" name="history_nucleotide_db" type="data_collection" collection_type="list" label="Nucleotide database from history" help="Each file must be named: ^[g__].[s__]"/>
            </when>
        </conditional>

        <conditional name="protein_db">
            <param name="protein_db_selector" type="select" label="Protein database" help="For locally cached databases, you need first to execute the tool to download HUMAnN2 databases">
                <option value="cached" selected="true">Locally cached</option>
                <option value="history">From history</option>
            </param>

            <when value="cached"/>
            <when value="history">
                <param name="history_protein_db" type="data" format="fasta" label="Protein database from history" help=""/>
            </when>
        </conditional>

        <param name="e_value" type="float" min="0" max="10" value="1" label="E-value threshold to use with the translated search" help="(--evalue)"/>
        <param name="identity" type="integer" min="0" max="100" value="40" label="Identity threshold for alignments" help="(--identity-threshold)"/>
        <param name="prescreen" type="float" min="0" max="1" value="0.01" label="Minimum percentage of reads matching a species" help="(--prescreen-threshold)"/>

        <param name='pathways' type="select" label="Database to use for pathway computations" help="(--pathways)">
            <option value="metacyc" selected="true">MetaCyc</option>
            <option value="unipathway">UniPathway</option>
        </param>

        <param name='xipe' type='boolean' checked="false" truevalue='on' falsevalue='off' label="Use xipe computation?" help="(--xipe)"/>
        <param name='minpath' type='boolean' checked="true" truevalue='on' falsevalue='off' label="Use minpath computation?" help="(--minpath)"/>
        <param name='pick_frames' type='boolean' checked="true" truevalue='on' falsevalue='off' label="Use pick frames computation?" help="(--pick-frames)"/>

        <param name='output_format' type="select" label="Format of the output files" help="(--output-format)">
            <option value="tsv" selected="true">TSV</option>
            <option value="biom">BIOM</option>
        </param>

        <param name="output_max_dec" type="integer" min="0" max="100" value="10" label="Number of decimals to output" help="(--output-max-decimals)"/>
        <param name='remove_statified_output' type='boolean' checked="false" truevalue='--remove-stratified-output' falsevalue='' label="Remove stratification from output?" help="(--remove-stratified-output)"/>
    </inputs>

    <outputs>
        <data format="tsv" name="gene_families_tsv" from_work_dir="output/humann2_genefamilies.tsv" label="${tool.name} on ${on_string}: Gene families and their abundance" >
            <filter>output_format == "tsv"</filter>
        </data>
        <data format="biom" name="gene_families_biom" from_work_dir="output/humann2_genefamilies.biom" label="${tool.name} on ${on_string}: Gene families and their abundance" >
            <filter>output_format == "biom"</filter>
        </data>

        <data format="tsv" name="pathcoverage_tsv" from_work_dir="output/humann2_pathcoverage.tsv" label="${tool.name} on ${on_string}: Pathways and their coverage" >
            <filter>output_format == "tsv"</filter>
        </data>
        <data format="biom" name="pathcoverage_biom" from_work_dir="output/humann2_pathcoverage.biom" label="${tool.name} on ${on_string}: Pathways and their coverage" >
            <filter>output_format == "biom"</filter>
        </data>

        <data format="tsv" name="pathabundance_tsv" from_work_dir="output/humann2_pathabundance.tsv" label="${tool.name} on ${on_string}: Pathways and their abundance" >
            <filter>output_format == "tsv"</filter>
        </data>
        <data format="biom" name="pathabundance_biom" from_work_dir="output/humann2_pathabundance.biom" label="${tool.name} on ${on_string}: Pathways and their abundance" >
            <filter>output_format == "biom"</filter>
        </data>
    </outputs>

    <tests>
        <test>
            <param name="input_file" value="input_sequences.fasta"/>
            <param name='taxonomic_profile_test' value="true"/>
            <param name="taxonomic_profile_file" value="taxonomic_profile.tabular"/>
            <param name="nucleotide_db_selector" value="history"/>
            <param name="history_nucleotide_db">
                <collection type="list">
                    <element name="g__Bacteroides.s__Bacteroides_stercoris.centroids.v0.1.1" ftype="fasta" value="g__Bacteroides.s__Bacteroides_stercoris.centroids.v0.1.1.ffn.gz" />
                    <element name="g__Bacteroides.s__Bacteroides_thetaiotaomicron.centroids.v0.1.1" ftype="fasta" value="g__Bacteroides.s__Bacteroides_thetaiotaomicron.centroids.v0.1.1.ffn.gz" />
                </collection>
            </param>
            <param name="protein_db_selector" value="history"/>
            <param name="history_protein_db" value="reduced_uniref50.fasta"/>
            <param name="e_value" value="1"/>
            <param name="identity" value="40"/>
            <param name="prescreen" value="0.01"/>
            <param name='pathways' value="metacyc"/>
            <param name='xipe' value="false"/>
            <param name='minpath' value="true"/>
            <param name='pick_frames' value="true"/>
            <param name='output_format' value="tsv"/>
            <param name="output_max_dec" value="10"/>
            <output name="gene_families_tsv" file="expected_gene_family_abundance.tsv"/>
            <output name="pathcoverage_tsv" file="expected_pathway_coverage.tsv"/>
            <output name="pathabundance_tsv" file="expected_pathway_abundance.tsv"/>
        </test>
    </tests>

    <help><![CDATA[
**What it does**

HUMAnN is a pipeline for efficiently and accuretly profiling the presence/absence and abundance of microbial pathways in a community from metagenomic or metatranscriptomic sequencing data. `Read more about the tool <http://huttenhower.sph.harvard.edu/humann2/manual>`_.

This tool corresponds to the main tool in HUMAnN2 pipeline.

**Inputs**

The input is a single file corresponding either to filtered shotgun sequencing metagenome file (fastq, fastq.gz, fasta, or fasta.gz format), alignment file (sam, bam or blastm8 format) or gene table file (tsv or biom format).

A file with a taxonomic profile (obtained with MetaPhlan2) can also be provided to avoid first step of taxonomic profiling needed to select pangenomes in protein database. Otherwise, default MetaPhlAn2 or custom databases can be used for taxonomic profiling. For custom databases, a fasta file with marker gene sequences is required and also a json file containing metadata:

::

  {
    "taxonomy": {
            "taxonomy of genome1": genome1_length,
            "taxonomy of genome2": genome2_length,
            ...
        }
    "markers": {
            "marker1_name": {
                "clade": the clade that the marker belongs to,
                "ext": [list of external genomes where the marker appears],
                "len": length of the marker,
                "score": score of the marker,
                "taxon": the taxon of the marker
            }
            ...
        }
  }

For functional profiling, HUMAnN2 uses multiple databases. Locally cached nucleotide or protein databases have to be downloaded database before using them (using the dedicated tool). Custom databases can also be used after upload. Nucleotide database have to be provided as a dataset.

**Outputs**

HUMAnN creates three output files:

 - A file with gene families and their abundance
 - A file with pathways and their abundance
 - A file with pathways and their coverage

    ]]></help>

    <expand macro="citations"/>
</tool>