comparison macros.xml @ 2:cb2fc9f60381 draft

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

1:7e2debc267eb

        <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>

    <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

    <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)

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>

  -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)

2:cb2fc9f60381

        <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

    <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)

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>

  -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)