annotate cherry_pick_fasta.xml @ 8:ee689b6999d5 draft default tip

planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/main/tools/cherry_pick_fasta commit 6cbabbaa6706494c530833f0fb0cbeebce4f150b

<tool id="cherry_pick_fasta" name="Pick Fasta sequences" version="4.1">
  <description>with header satisfying a string query</description>
  <requirements>
        <requirement type="package" version="3.8.0">python</requirement>
  </requirements>
  <command detect_errors="exit_code"><![CDATA[
                            python '$__tool_directory__/cherry_pick_fasta.py'
                                   --input $input
                                   --searchfor '$search.searchfor'
                                   #if $search.options_selector == 'single':
                                       #if $search.match == 'exact':
                                           --query-string '$search.query' --mode exact
                                       #else:
                                           --query-string '$search.query' --mode includes
                                       #end if
                                   #else:
                                       #if $search.match == 'exact':
                                           --query-file '$search.query' --mode exact
                                       #else:
                                           --query-file '$search.query' --mode includes
                                       #end if
                                   #end if
                                   --output $output
  ]]></command>

  <inputs>
    <param name="input" type="data" format="fasta" label="Source file" help="Fasta file to parse" />

    <conditional name="search">
        <param name="options_selector" type="select" display="radio" label="for a">
            <option value="single" selected="True">single string</option>
            <option value="textdataset">list of strings</option>
        </param>
        <when value="single">
            <param name="match" type="select"  label="retrieve sequences whose headers...">
                <option value="include" selected="true">partially</option>
                <option value="exact">exactly</option>
            </param>
            <param name="searchfor" type="select" label=" ">
                <option value="with" selected="true">contain this string</option>
                <option value="without">do not contain this string</option>
            </param>
            <param name="query" type="text" size="30" value="" label="Search string" help="exemple: gi|40557596">
                <sanitizer>
                    <valid initial="string.printable">
                        <remove value="&quot;"/>
                        <remove value="\"/>
                    </valid>
                    <mapping initial="none">
                        <add source="&quot;" target="\&quot;"/>
                        <add source="\" target="\\"/>
                    </mapping>
                </sanitizer>
            </param>
        </when>
        <when value="textdataset">
            <param name="match" type="select"  label="retrieve sequences whose headers...">
                <option value="includes" selected="true">partially</option>
                <option value="exact">exactly</option>
            </param>
            <param name="searchfor" type="select" label=" ">
                <option value="with" selected="true">contain one of these list strings</option>
                <option value="without">do not contain one of these list strings</option>
            </param>
            <param name="query" type="data" format="txt" label="list of strings dataset" help="a list of strings to search for, one string per line" />
        </when>
    </conditional>
  </inputs>
  <outputs>
    <data name="output" format="fasta" label="Fasta sequences ${search.searchfor.value} ${search.options_selector} term(s) in header" />
  </outputs>
  <tests>
    <!-- test headers with space -->
    <test>
        <param ftype="fasta" name="input" value="input_withspace.fa" />
        <param name="query" value="type=rRNA" />
        <param name="searchfor" value="with" />
        <param name="match" value="include" />
        <output name="output" ftype="fasta" file="output_withspace.fa" />
    </test>
    <!-- exact matches -->
    <test>
        <param ftype="fasta" name="input" value="input.fa" />
        <param name="query" value="gi|81971654|sp|Q9IJX4.1|POLN_CRPVC_RecName:_Full_Replicase_polyprotein;_Contains:_RecName:_Full_Pro--Locus_65_Transcript_1/2_Confidence_0.667_Length_1344_hit1_IdMatch=43.46,AligLength=451,E-val=2e-122" />
        <param name="searchfor" value="without" />
        <param name="match" value="exact" />
        <output name="output" ftype="fasta" file="output_exactly_not.fa" />
    </test>
    <test>
        <param ftype="fasta" name="input" value="input.fa" />
        <param name="query" value="gi|81971654|sp|Q9IJX4.1|POLN_CRPVC_RecName:_Full_Replicase_polyprotein;_Contains:_RecName:_Full_Pro--Locus_65_Transcript_1/2_Confidence_0.667_Length_1344_hit1_IdMatch=43.46,AligLength=451,E-val=2e-122" />
        <param name="searchfor" value="with" />
        <param name="match" value="exact" />
        <output name="output" ftype="fasta" file="output_exact.fa" />
    </test>
    <test>
        <param ftype="fasta" name="input" value="input.fa" />
        <param name="options_selector" value="textdataset" />
        <param name="query" ftype="txt" value="alt_termlist.txt" />
        <param name="searchfor" value="without" />
        <param name="match" value="exact" />
        <output name="output" ftype="fasta" file="output_alt_termlist_without.fa" />
    </test>
    <test>
        <param ftype="fasta" name="input" value="input.fa" />
        <param name="options_selector" value="textdataset" />
        <param name="query" ftype="txt" value="alt_termlist.txt" />
        <param name="searchfor" value="with" />
        <param name="match" value="exact" />
        <output name="output" ftype="fasta" file="output_alt_termlist.fa" />
    </test>
    <!-- partial matches -->
    <test>
        <param ftype="fasta" name="input" value="input.fa" />
        <param name="query" value="gi|81971654" />
        <param name="searchfor" value="with" />
        <output name="output" ftype="fasta" file="output.fa" />
    </test>
    <test>
        <param ftype="fasta" name="input" value="input.fa" />
        <param name="query" value="RNA" />
        <param name="searchfor" value="without" />
        <output name="output" ftype="fasta" file="output_without.fa" />
    </test>
    <test>
        <param ftype="fasta" name="input" value="input.fa" />
        <param name="options_selector" value="textdataset" />
        <param name="query" ftype="txt" value="termlist.txt" />
        <param name="searchfor" value="without" />
        <output name="output" ftype="fasta" file="output_termlist.fa" />
    </test>
    <test>
        <param ftype="fasta" name="input" value="input.fa" />
        <param name="options_selector" value="textdataset" />
        <param name="query" ftype="txt" value="termlist.txt" />
        <param name="searchfor" value="without" />
        <output name="output" ftype="fasta" file="output_termlist_without.fa" />
    </test>
  </tests>
  <help>
**What it does**

This tool retrieves nucleotide/peptide sequences from a fasta file whose headers match
or do not match a given string, or a list of strings.

Note that the version 4 of the tools is amazingly accelerated !

  </help>
  <citations>
   <citation type="doi">10.1002/0471142727.mb1910s89</citation>
  </citations>
</tool>