annotate orfipy.xml @ 1:45d4d26e01b5 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/orfipy commit 472277ff42e1d7018e0d2921bd51a018572793c5

<tool id="orfipy" name="ORFipy" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.05">
    <description>a versatile ORF finder</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="xrefs"/>
    <requirements>
        <requirement type="package" version="@TOOL_VERSION@">orfipy</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[
orfipy 
--procs "\${GALAXY_SLOTS:-1}"
--outdir ./ 
#for $o in str($out_files).split(','):
    #if $o == 'BED':
        --bed '$out_bed'
    #else if $o == 'BED12':
        --bed12 '$out_bed12'
    #else if $o == 'DNA':
        --dna '$out_dna'
    #else if $o == 'RNA':
        --rna '$out_rna'
    #else if $o == 'PEP':
        --pep '$out_pep'
    #end if
#end for
--strand $strand
#if $min:
    --min $min
#end if
#if $max:
    --max $max
#end if
--table $table
#if $start:
    --start '$start'
#end if
#if $stop:
    --stop '$stop'
#end if
$ignore_case
$partial_3
$partial_5
$between_stops
$include_stop
'$input1'
    ]]></command>
    <inputs>
        <param name="input1" type="data" format="fasta,fasta.gz" label="Find ORFs in:" help="ORFs will be detected in this sequence"/>
        <param type="select" argument="--table" label="Specify genetic code">
            <option value="1" selected="true">1 Standard</option>
            <option value="2">2 Vertebrate mitochondrial</option>
            <option value="3">3 Yeast mitochondrial</option>
            <option value="4">4 Mold, Protozoan, Coelenterate, Mycoplasma, Spiroplasma mitochondrial</option>
            <option value="5">5 Invertebrate Mitochondrial</option>
            <option value="6">6 Ciliate, Dasycladacean, Hexamita Nuclear</option>
            <option value="7">7 Echinoderm and Flatworm Mitochondrial</option>
            <option value="8">8 Euplotid Nuclear</option>
            <option value="9">9 Bacterial, Archaeal and Plant Plastid</option>
            <option value="10">10 Alternative Yeast nuclear</option>
            <option value="11">11 Ascidian mitochondrial</option>
            <option value="12">12 Alternative Flatworm mitochondrial</option>
            <option value="13">13 Chlorophycean mitochondrial</option>
            <option value="14">14 Trematode mitochondrial</option>
            <option value="15">15 Scenedesmus obliquus mitochondrial</option>
            <option value="16">16 Thraustochytrium mitochondrial code</option>
            <option value="17">17 Pterobranchia mitochondrial</option>
            <option value="18">18 Candidate Division SR1 and Gracilibacteria</option>
            <option value="19">19 Pachysolen tannophilus Nuclear Code</option>
            <option value="20">20 Karyorelict nuclear</option>
            <option value="21">21 Condylostoma nuclear</option>
            <option value="22">22 Mesodinium nuclear</option>
            <option value="23">23 Peritrich nuclear</option>
        </param>
        <param name="out_files" argument="--bed,--bed12,--dna,--rna,--pep" type="select" multiple="true" display="checkboxes" label="Select outputs"
               help="DNA, RNA, and Peptide options will produce FASTA outputs">
          <option value="BED" selected="true">BED</option>
          <option value="BED12">BED12</option>
          <option value="DNA">DNA</option>
          <option value="RNA">RNA</option>
          <option value="PEP">Peptides</option>
        </param>
        <param argument="--strand" type="select" display="radio" label="Select strand" help="Identify ORFs on which strand">
            <option value="b" selected="true">Both</option>
            <option value="f">Forward</option>
            <option value="r">Reverse</option>
        </param>
        <param argument="--min" type="integer" min="0" optional="true" label="Minimum length of ORFs"
               help="No ORFs below this value will be reported. All ORFs will be reported if this parameter is not set. Default is 30"/>
        <param argument="--max" type="integer" min="0" optional="true" label="Maximum length of ORFs"
               help="This value doesn't take in account the STOP codon. No ORFs over this value will be reported. Default is 1.000.000.000."/>
        <param argument="--start" type="text" optional="true" label="Start codon(s) to use"
               help="A comma-separated list without spaces. Only ATCG and comma are allowed">
            <validator type="regex" message="Only 'ATCGatcg' and ',' are allowed in this field">^[ATGCatcg,]*$</validator>
        </param>
        <param argument="--stop" type="text" optional="true" label="Stop codon(s) to use"
               help="A commma separated list without spaces. Only ATCG and comma are allowed">
            <validator type="regex" message="Only 'ATCGatcg' and ',' are allowed in this field">^[ATGCatcg,]*$</validator>
        </param>
        <param argument="--ignore-case" type="boolean" truevalue="--ignore-case" falsevalue="" display="radio" label="Ignore case?"
               help="Ignore case and find ORFs in lower case sequences too. NO = do not ignore (use upper case only). YES = ignore"/>
        <param argument="--partial-3" type="boolean" truevalue="--partial-3" falsevalue="" display="radio" label="Output ORFs with Start but no Stop?"
               help="Output ORFs with a start codon but lacking an inframe stop codon. NO = do not output. YES = do output"/>
        <param argument="--partial-5" type="boolean" truevalue="--partial-5" falsevalue="" display="radio" label="Output ORFs with Stop but no Start?"
               help="Output ORFs with an inframe stop codon lacking an inframe start codon. NO = do not output. YES = do output"/>
        <param argument="--between-stops" type="boolean" display="radio" truevalue="--between-stops" falsevalue="" label="Output ORFs bound by Stop codons?"
               help="Output ORFs defined as regions between stop codons (regions free of stop codon). This will set --partial-3 and --partial-5 true"/>
        <param argument="--include-stop" type="boolean" truevalue="--include-stop" falsevalue="" display="radio" label="Include stop codon in the results?"
               help="Output ORFs with an inframe stop codon lacking an inframe start codon. NO = do not include. YES = include"/>
    </inputs>
    <outputs>
        <data name="out_bed" format="bed6" label="ORFs on ${on_string} (BED format)">
            <filter>"BED" in out_files</filter>
        </data>
        <data name="out_bed12" format="bed12" label="ORFs on ${on_string} (BED12 format)">
            <filter>"BED12" in out_files</filter>
        </data>
        <data name="out_dna" format="fasta" label="ORFs on ${on_string} (FASTA DNA)">
            <filter>"DNA" in out_files</filter>
        </data>
        <data name="out_rna" format="fasta" label="ORFs on ${on_string} (FASTA RNA)">
            <filter>"RNA" in out_files</filter>
        </data>
        <data name="out_pep" format="fasta" label="ORFs on ${on_string} (FASTA Protein)">
            <filter>"PEP" in out_files</filter>
        </data>
    </outputs>
    <tests>
        <test expect_num_outputs="1">
            <param name="input1" value="orfipy.fa"/>
            <param name="out_files" value="BED"/>
            <output name="out_bed" file="test1.bed"/>
        </test>
        <test expect_num_outputs="1">
            <param name="input1" value="orfipy.fa"/>
            <param name="out_files" value="DNA"/>
            <param name="min" value="100"/>
            <param name="partial_5" value="true"/>
            <output name="out_dna" file="test2.fa"/>
        </test>
        <test expect_num_outputs="1">
            <param name="input1" value="orfipy.fa.gz"/>
            <param name="out_files" value="DNA"/>
            <param name="min" value="100"/>
            <param name="partial_5" value="true"/>
            <output name="out_dna" file="test2.fa"/>
        </test>
        <test expect_num_outputs="1">
            <param name="input1" value="orfipy.fa.gz"/>
            <param name="out_files" value="DNA"/>
            <param name="max" value="100000000"/>
            <output name="out_dna" file="test3.fa"/>
        </test>
    </tests>
    <help><![CDATA[
**What it does**

Orfipy is a tool for finding open reading frames (ORFs). 

**Parameters**

Galaxy interface of Orfipy supports the following parameters (the following is taken from the tool help)::
    
  --table TABLE         The codon table number to use or path to .json file
                        with codon table. Use --show-tables to see available
                        tables compiled from: https://www.ncbi.nlm.nih.gov/Taxonomy/Utils/wprintgc.cgi?chapter=cgencodes Default: 1
  --start START         Comma-separated list of start-codons. This will
                        override start codons described in translation table.
                        E.g. "--start ATG,ATT" Default: Derived from the
                        translation table selected
  --stop STOP           Comma-separated list of stop codons. This will
                        override stop codons described in translation table.
                        E.g. "--start TAG,TTT" Default: Derived from the
                        translation table selected
  --outdir OUTDIR       Path to outdir default: orfipy_<infasta>_out
  --bed12 BED12         bed12 out file Default: None
  --bed BED             bed out file Default: None
  --dna DNA             fasta (DNA) out file Default: None
  --rna RNA             fasta (RNA) out file Default: None
  --pep PEP             fasta (peptide) out file Default: None
  --min MIN             Minimum length of ORF, excluding stop codon
                        (nucleotide) Default: 30
  --max MAX             Maximum length of ORF, excluding stop codon
                        (nucleotide) Default: 1,000,000,000
  --strand {f,r,b}      Strands to find ORFs [(f)orward,(r)everse,(b)oth]
                        Default: b
  --ignore-case         Ignore case and find ORFs in lower case sequences too.
                        Useful for soft-masked sequences. Default: False
  --partial-3           Output ORFs with a start codon but lacking an inframe
                        stop codon. E.g. "ATG TTT AAA" Default: False
  --partial-5           Output ORFs with an inframe stop codon lacking an
                        inframe start codon. E.g. "TTT AAA TAG" Default: False
  --between-stops       Output ORFs defined as regions between stop codons
                        (regions free of stop codon). This will set
                        --partial-3 and --partial-5 true. Default: False
  --include-stop        Include stop codon in the results, if a stop codon
                        exists. This output format is compatible with
                        TransDecoder's which includes stop codon coordinates
                        Default: False
    ]]></help>
    <citations>
        <citation type="doi">10.1093/bioinformatics/btab090</citation>
    </citations>
</tool>