annotate macros.xml @ 2:cb2fc9f60381 draft

"planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/drep commit eaae9983f0339c4624431f4f843e319f83814490"

<macros>
    <token name="@VERSION@">2.3.2</token>
    <xml name="requirements">
        <requirements>
            <requirement type="package" version="@VERSION@">drep</requirement>
            <yield/>
        </requirements>
    </xml>
    <xml name="citations">
        <citations>
            <citation type="doi">10.1038/ismej.2017.126</citation>
            <yield />
        </citations>
    </xml>


    <xml name="genomes">
        <param argument="--genomes" type="data" format="fasta" label="genomes fasta files" multiple="true"/>
    </xml>
    <token name="@PREPARE_GENOMES@"><![CDATA[
    #import re 
    #set $genomefiles = [] 
    #for $genome in $genomes
        #set $input_name = $re.sub('[^\w\-_.]', '_',str($genome.element_identifier.split('/')[-1]))
        ln -s '${genome}' '${input_name}' &&
        $genomefiles.append($input_name)
    #end for
]]></token>
    <token name="@GENOMES@"><![CDATA[
    -g 
    #for $genomefile in $genomefiles
    '${genomefile}' 
    #end for
]]></token>


    <xml name="checkm_method">
        <param argument="--checkM_method" type="select" label="checkm method" optional="true">
           <option value="lineage_wf">lineage_wf (more accurate)</option>
           <option value="taxonomy_wf">taxonomy_wf (faster)</option>
        </param>
    </xml>
    <token name="@CHECKM_METHOD@"><![CDATA[
    #if $checkM_method:
    --checkM_method $checkM_method 
    #end if
]]></token>

    <xml name="filtering_options">
        <conditional name="filter">
            <param name="set_options" type="select" label="set filtering options">
                <option value="yes">Yes</option>
                <option value="no" selected="true">No</option>
            </param>
            <when value="yes">
                <param argument="--length" type="integer" value="50000" label="Minimum genome length"/>
                <param argument="--completeness" type="integer" value="75" min="0" max="100" label="Minimum genome completeness percent"/>
                <param argument="--contamination" type="integer" value="25" min="0" max="100" label="Maximum genome contamination percent"/>
                 
                <conditional name="quality">
                    <param argument="source" type="select" label="genome quality">
                        <help>
                            --ignoreGenomeQuality is useful with
                            bacteriophages or eukaryotes or things where checkM
                            scoring does not work. Will only choose genomes based
                            on length and N50. 
                        </help>
                        <option value="checkm" selected="true">Run checkM</option>
                        <option value="genomeInfo">User supplied genomeInfo csv file</option>
                        <option value="ignoreGenomeQuality">--ignoreGenomeQuality (NOT RECOMMENDED!)</option>
                    </param>
                    <when value="checkm">
                        <param argument="--checkM_method" type="select" label="checkm method" optional="true">
                            <option value="lineage_wf">lineage_wf (more accurate)</option>
                            <option value="taxonomy_wf">taxonomy_wf (faster)</option>
                        </param>
                    </when>
                    <when value="genomeInfo">
                        <param argument="--genomeInfo" type="data" format="csv" label="genomes fasta files">
                            <help><![CDATA[
                            A CSV dataset that must contain: [
                            "genome"(history dataset name of .fasta dataset of that genome), 
                            "completeness"(0-100 value for completeness of the genome), 
                            "contamination"(0-100 value of the contamination of the genome)] 
                            ]]></help>
                        </param>
                    </when>
                    <when value="ignoreGenomeQuality"/>
                </conditional>

            </when>
            <when value="no"/>
        </conditional>
    </xml>
    <token name="@FILTER_OPTIONS@"><![CDATA[
        #if $filter.set_options == 'yes':
            --length $filter.length
            --completeness $filter.completeness
            --contamination $filter.contamination
            #if $filter.quality.source == 'checkm'
                --checkM_method $filter.quality.checkM_method
            #elif $filter.quality.source == 'genomeInfo'
                --genomeInfo $filter.quality.genomeInfo 
            #elif $filter.quality.source == 'ignoreGenomeQuality'
                --ignoreGenomeQuality
            #end if
        #end if
]]></token>

    <xml name="genome_comparison_options">
        <conditional name="genome_comparison">
            <param name="set_options" type="select" label="set genome comparison options">
                <option value="yes">Yes</option>
                <option value="no" selected="true">No</option>
            </param>
            <when value="yes">
                <param argument="--MASH_sketch" type="integer" value="1000" label="MASH sketch size"/>
                <param argument="--S_algorithm" type="select" label="Algorithm for secondary clustering comaprisons">
                    <option value="ANImf" selected="true">ANImf = (RECOMMENDED) Align whole genomes with nucmer; filter alignment; compare aligned regions</option>
                    <option value="ANIn">ANIn  = Align whole genomes with nucmer; compare aligned regions</option>
                    <option value="gANI">gANI  = Identify and align ORFs; compare aligned ORFS</option>
                </param>
                <param argument="-n_PRESET" type="select" label="Presets to pass to nucmer">
                    <option value="normal" selected="true">normal  = default ANIn parameters (default: normal)</option>
                    <option value="tight">tight   = only align highly conserved regions</option>
                </param>
            </when>
            <when value="no"/>
        </conditional>
    </xml>
    <token name="@GENOME_COMPARISON_OPTIONS@"><![CDATA[
        #if $genome_comparison.set_options == 'yes':
            --MASH_sketch $genome_comparison.MASH_sketch
            --S_algorithm $genome_comparison.S_algorithm
            -n_PRESET $genome_comparison.n_PRESET
        #end if
]]></token>

    <xml name="clustering_options">
        <conditional name="clustering">
            <param name="set_options" type="select" label="set clustering options">
                <option value="yes">Yes</option>
                <option value="no" selected="true">No</option>
            </param>
            <when value="yes">
                <param argument="--P_ani" type="float" value="0.9" min="0." max="1." label="ANI threshold to form primary (MASH) clusters"/>
                <param argument="--S_ani" type="float" value="0.99" min="0." max="1." label="ANI threshold to form secondary clusters"/>

                <param argument="--SkipMash" type="boolean" truevalue="--SkipMash" falsevalue="" checked="false" label="Skip MASH clustering, just do secondary clustering on all genomes"/>
                <param argument="--SkipSecondary" type="boolean" truevalue="--SkipSecondary" falsevalue="" checked="false" label="Skip secondary clustering, just perform MASH clustering"/>
                <param argument="--cov_thresh" type="float" value="0.1" min="0." max="1." label="Minmum level of overlap between genomes when doing secondary comparisons"/>
                <param argument="--coverage_method" type="select" label="Method to calculate coverage of an alignment">
                    <help>(for ANIn/ANImf only; gANI can only do larger method)</help>
                    <option value="larger" selected="true">arger  = max((aligned length / genome 1), (aligned_length / genome2))</option>
                    <option value="total">total   = 2*(aligned length) / (sum of total genome lengths)</option>
                </param>
                <param argument="--clusterAlg" type="select" label="Algorithm used to cluster genomes">
                    <help>(passed to  scipy.cluster.hierarchy.linkage)</help>
                    <option value="average" selected="true">average</option>
                </param>
            </when>
            <when value="no"/>
        </conditional>
    </xml>
    <token name="@CLUSTERING_OPTIONS@"><![CDATA[
        #if $clustering.set_options == 'yes':
            --P_ani $clustering.P_ani
            --S_ani $clustering.S_ani
            $clustering.SkipMash
            $clustering.SkipSecondary
            --cov_thresh $clustering.cov_thresh
            --coverage_method $clustering.coverage_method
            --clusterAlg $clustering.clusterAlg
        #end if
]]></token>

    <xml name="scoring_options">
        <conditional name="scoring">
            <param name="set_options" type="select" label="set scoring options">
                <option value="yes">Yes</option>
                <option value="no" selected="true">No</option>
            </param>
            <when value="yes">
                <param argument="--completeness_weight" type="float" value="1" label="completeness weight">
                    <help>
Based off of the formula:
A*Completeness - B*Contamination + C*(Contamination * (strain_heterogeneity/100)) + D*log(N50) + E*log(size)
A = completeness_weight; B = contamination_weight; C = strain_heterogeneity_weight; D = N50_weight; E = size_weight;
                    </help>
                </param>
                <param argument="--contamination_weight" type="float" value="5" label="contamination weight"/>
                <param argument="--strain_heterogeneity_weight" type="float" value="1" min="0." max="1." label="strain heterogeneity weight"/>
                <param argument="--N50_weight" type="float" value=".5" label="weight of log(genome N50)"/>
                <param argument="--size_weight" type="float" value="0" label="weight of log(genome size)"/>
            </when>
            <when value="no"/>
        </conditional>
    </xml>
    <token name="@SCORING_OPTIONS@"><![CDATA[
        #if $scoring.set_options == 'yes':
            --completeness_weight $scoring.completeness_weight
            --contamination_weight $scoring.contamination_weight
            --strain_heterogeneity_weight $scoring.strain_heterogeneity_weight
            --N50_weight $scoring.N50_weight
            --size_weight $scoring.size_weight
        #end if
]]></token>

    <xml name="taxonomy_options">
        <conditional name="taxonomy">
            <param name="set_options" type="select" label="generate taxonomy information">
                <option value="yes">Yes</option>
                <option value="no" selected="true">No</option>
            </param>
            <when value="yes">
                <param argument="--tax_method" type="select" label="Method of determining taxonomy">
                    <help>(for ANIn/ANImf only; gANI can only do larger method)</help>
                    <option value="percent" selected="true">percent = The most descriptive taxonimic level with at least (per) hits</option>
                    <option value="max">max = The centrifuge taxonomic level with the most overall hits</option>
                </param>
                <param argument="--percent" type="float" value="50" min="0" max="100" label="minimum percent for percent method"/>
                <param argument="--cent_index" type="data" format="" label="centrifuge index"/>
            </when>
            <when value="no"/>
        </conditional>
    </xml>
    <token name="@TAXONOMY_OPTIONS@"><![CDATA[
        #if $taxonomy.set_options == 'yes':
            --run_tax
            --tax_method $taxonomy.tax_method
            --percent $taxonomy.percent
            --cent_index $taxonomy.cent_index
        #end if
]]></token>

   <xml name="warning_options">
        <conditional name="warning">
            <param name="set_options" type="select" label="set warning options">
                <option value="yes">Yes</option>
                <option value="no" selected="true">No</option>
            </param>
            <when value="yes">
                <param argument="--warn_dist" type="float" value="0.25" min="0" max="1" label="How far from the threshold to throw cluster warnings"/>
                <param argument="--warn_sim" type="float" value="0.98" min="0" max="1" label="Similarity threshold for warnings between dereplicated genomes"/>
                <param argument="--warn_aln" type="float" value="0.25" min="0" max="1" label="Minimum aligned fraction for warnings between dereplicated genomes (ANIn)"/>
            </when>
            <when value="no"/>
        </conditional>
    </xml>
    <token name="@WARNING_OPTIONS@"><![CDATA[
        #if $warning.set_options == 'yes':
            --warn_dist $warning.warn_dist
            --warn_sim $warning.warn_sim
            --warn_aln $warning.warn_aln
        #end if
]]></token>

    <xml name="select_outputs">
        <param name="select_outputs" type="select" multiple="true" optional="false" label="Select outputs">
            <option value="log" selected="true">log</option>
            <option value="warnings" selected="true">Warnings</option>
            <option value="Primary_clustering_dendrogram" selected="true">Primary_clustering_dendrogram.pdf</option>
            <option value="Secondary_clustering_dendrograms">Secondary_clustering_dendrograms.pdf</option>
            <option value="Secondary_clustering_MDS">Secondary_clustering_MDS.pdf</option>
            <option value="Clustering_scatterplots" selected="true">Clustering_scatterplots.pdf</option>
            <yield/>
        </param>
    </xml>
    <xml name="select_drep_outputs">
        <expand macro="select_outputs">
            <option value="Cluster_scoring">Cluster_scoring.pdf</option>
            <option value="Winning_genomes">Winning_genomes.pdf</option>
            <option value="Widb">Widb.csv</option>
            <option value="Chdb">Chdb.tsv</option>
        </expand>
    </xml>

   <xml name="common_outputs">
        <data name="log" format="txt" label="${tool.name} on ${on_string}: Log" from_work_dir="outdir/log/logger.log">
            <filter>'log' in select_outputs or not select_outputs</filter>
        </data>
        <data name="warnings" format="txt" label="${tool.name} on ${on_string}: Warnings" from_work_dir="outdir/log/warnings.txt">
            <filter>'warnings' in select_outputs</filter>
        </data>
        <data name="Primary_clustering_dendrogram" format="pdf" label="${tool.name} on ${on_string}: Primary_clustering_dendrogram.pdf" from_work_dir="outdir/figures/Primary_clustering_dendrogram.pdf">
            <filter>'Primary_clustering_dendrogram' in select_outputs</filter>
        </data>
        <data name="Secondary_clustering_dendrograms" format="pdf" label="${tool.name} on ${on_string}: Secondary_clustering_dendrograms.pdf" from_work_dir="outdir/figures/Secondary_clustering_dendrograms.pdf">
            <filter>'Secondary_clustering_dendrograms' in select_outputs</filter>
        </data>
        <data name="Secondary_clustering_MDS" format="pdf" label="${tool.name} on ${on_string}: Secondary_clustering_MDS.pdf" from_work_dir="outdir/figures/Secondary_clustering_MDS.pdf">
            <filter>'Secondary_clustering_MDS' in select_outputs</filter>
        </data>
        <data name="Clustering_scatterplots" format="pdf" label="${tool.name} on ${on_string}: Clustering_scatterplots.pdf" from_work_dir="outdir/figures/Clustering_scatterplots.pdf">
            <filter>'Clustering_scatterplots' in select_outputs</filter>
        </data>
    </xml>


    <xml name="drep_outputs">
        <expand macro="common_outputs"/>
        <data name="Cluster_scoring" format="pdf" label="${tool.name} on ${on_string}: Cluster_scoring.pdf" from_work_dir="outdir/figures/Cluster_scoring.pdf">
            <filter>'Cluster_scoring' in select_outputs</filter>
        </data>
        <data name="Winning_genomes" format="pdf" label="${tool.name} on ${on_string}: Winning_genomes.pdf" from_work_dir="outdir/figures/Winning_genomes.pdf">
            <filter>'Winning_genomes' in select_outputs</filter>
        </data>
        <data name="Widb" format="csv" label="${tool.name} on ${on_string}: Widb.csv" from_work_dir="outdir/data_tables/Widb.csv">
            <filter>'Widb' in select_outputs</filter>
        </data>
        <data name="Chdb" format="tabular" label="${tool.name} on ${on_string}: Chdb.tsv" from_work_dir="outdir/data/checkM/checkM_outdir/Chdb.tsv">
            <filter>'Chdb' in select_outputs</filter>
        </data>
    </xml>

    
    <xml name="test_defaults_log">
        <test>
            <param name="genomes" ftype="fasta" value="Enterococcus_casseliflavus_EC20.fasta,Enterococcus_faecalis_T2.fna,Enterococcus_faecalis_TX0104.fa"/>
            <output name="log">
                <assert_contents>
                    <yield/>
                </assert_contents>
            </output>
        </test>
    </xml>

    <token name="@GENOMES_HELP@"><![CDATA[
I/O PARAMETERS:
  -g [GENOMES [GENOMES ...]], --genomes [GENOMES [GENOMES ...]]
                        genomes to cluster in .fasta format
                        (default: None)


]]></token>

    <token name="@FILTERING_HELP@"><![CDATA[
FILTERING OPTIONS:
  -l LENGTH, --length LENGTH
                        Minimum genome length
                        (default: 50000)


  -comp COMPLETENESS, --completeness COMPLETENESS
                        Minumum genome completeness
                        (default: 75)


  -con CONTAMINATION, --contamination CONTAMINATION
                        Maximum genome contamination
                        (default: 25)


  --ignoreGenomeQuality
                        Don't run checkM or do any quality filtering. NOT
                        RECOMMENDED! This is useful for use with
                        bacteriophages or eukaryotes or things where checkM
                        scoring does not work. Will only choose genomes based
                        on length and N50 (default: False)


]]></token>

    <token name="@GENOME_COMPARISON_HELP@"><![CDATA[
GENOME COMPARISON PARAMETERS:
  -ms MASH_SKETCH, --MASH_sketch MASH_SKETCH
                        MASH sketch size (default: 1000)

  --S_algorithm {goANI,ANIn,ANImf,gANI}
                        Algorithm for secondary clustering comaprisons:
                        ANImf = (RECOMMENDED) Align whole genomes with nucmer; filter alignment; compare aligned regions
                        ANIn  = Align whole genomes with nucmer; compare aligned regions
                        gANI  = Identify and align ORFs; compare aligned ORFS
                        (default: ANImf)

  -n_PRESET {normal,tight}
                        Presets to pass to nucmer
                        tight   = only align highly conserved regions
                        normal  = default ANIn parameters (default: normal)

]]></token>

    <token name="@CLUSTERING_HELP@"><![CDATA[
CLUSTERING PARAMETERS:
  -pa P_ANI, --P_ani P_ANI
                        ANI threshold to form primary (MASH) clusters
                        (default: 0.9)
  -sa S_ANI, --S_ani S_ANI
                        ANI threshold to form secondary clusters
                        (default: 0.99)

  --SkipMash            Skip MASH clustering, just do secondary clustering on
                        all genomes (default: False)
  --SkipSecondary       Skip secondary clustering, just perform MASH clustering
                        (default: False)

  -nc COV_THRESH, --cov_thresh COV_THRESH
                        Minmum level of overlap between genomes when doing
                        secondary comparisons (default: 0.1)
  -cm {total,larger}, --coverage_method {total,larger}
                        Method to calculate coverage of an alignment
                        (for ANIn/ANImf only; gANI can only do larger method)
                        total   = 2*(aligned length) / (sum of total genome lengths)
                        larger  = max((aligned length / genome 1), (aligned_length / genome2))
                        (default: larger)

  --clusterAlg CLUSTERALG
                        Algorithm used to cluster genomes (passed to
                        scipy.cluster.hierarchy.linkage (default: average)

]]></token>

    <token name="@SCORING_HELP@"><![CDATA[
SCORING CRITERIA
Based off of the formula: 
A*Completeness - B*Contamination + C*(Contamination * (strain_heterogeneity/100)) + D*log(N50) + E*log(size)

A = completeness_weight; B = contamination_weight; C = strain_heterogeneity_weight; D = N50_weight; E = size_weight:
  -comW COMPLETENESS_WEIGHT, --completeness_weight COMPLETENESS_WEIGHT
                        completeness weight (default: 1)
  -conW CONTAMINATION_WEIGHT, --contamination_weight CONTAMINATION_WEIGHT
                        contamination weight (default: 5)
  -strW STRAIN_HETEROGENEITY_WEIGHT, --strain_heterogeneity_weight STRAIN_HETEROGENEITY_WEIGHT
                        strain heterogeneity weight (default: 1)
  -N50W N50_WEIGHT, --N50_weight N50_WEIGHT
                        weight of log(genome N50) (default: 0.5)
  -sizeW SIZE_WEIGHT, --size_weight SIZE_WEIGHT
                        weight of log(genome size) (default: 0)


]]></token>

    <token name="@TAXONOMY_HELP@"><![CDATA[
TAXONOMY:
  --run_tax             generate taxonomy information (Tdb)
                        (default: False)

  --tax_method {percent,max}
                        Method of determining taxonomy
                        percent = The most descriptive taxonimic level with at least (per) hits
                        max     = The centrifuge taxonomic level with the most overall hits
                        (default: percent)


  -per PERCENT, --percent PERCENT
                        minimum percent for percent method
                        (default: 50)


  --cent_index CENT_INDEX
                        path to centrifuge index (for example,
                        /home/mattolm/download/centrifuge/indices/b+h+v
                        (default: None)

]]></token>

    <token name="@WARNINGS_HELP@"><![CDATA[
WARNINGS:
  --warn_dist WARN_DIST
                        How far from the threshold to throw cluster warnings
                        (default: 0.25)
  --warn_sim WARN_SIM   Similarity threshold for warnings between dereplicated
                        genomes (default: 0.98)
  --warn_aln WARN_ALN   Minimum aligned fraction for warnings between
                        dereplicated genomes (ANIn) (default: 0.25)

]]></token>


</macros>