annotate filter_by_fasta_ids.xml @ 3:3c623e81be77 draft

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/filter_by_fasta_ids commit 0556e0fe5aa17c84033a75a45baeb3a4c2b5ff76

<tool id="filter_by_fasta_ids" name="Filter FASTA" version="2.1">
    <description>on the headers and/or the sequences</description>
    <macros>
        <xml name="regexp_macro" token_label="Regular expression pattern">
            <param name="regexp" type="text" value="" label="@LABEL@" help="Use the Python regular expression syntax as specified in https://docs.python.org/3/library/re.html">
                <validator type="empty_field" />
                <sanitizer>
                    <valid initial="string.printable">
                        <remove value="'"/>
                    </valid>
                    <mapping initial="none">
                        <add source="'" target="'&quot;'&quot;'" />
                    </mapping>
                </sanitizer>
            </param>
        </xml>
    </macros>
    <requirements>
        <requirement type="package" version="3.6.5">python</requirement>
    </requirements>
    <command><![CDATA[
python '$__tool_directory__/filter_by_fasta_ids.py'
-i '$input'
#if $header_criteria.header_criteria_select == 'id_list'
    --id_list '$header_criteria.identifiers'
    #if $header_criteria.id_regex.find == 'pattern':
        --pattern '$header_criteria.id_regex.pattern'
    #elif $header_criteria.id_regex.find == 'beginning':
        --pattern '$header_criteria.id_regex.pattern'
    #end if
#elif $header_criteria.header_criteria_select == 'regexp'
    --header_regexp '$header_criteria.regexp'
#end if
#if $sequence_criteria.sequence_criteria_select == 'seq_length'
    --min_length $sequence_criteria.min_length
    #if str($sequence_criteria.max_length)
        --max_length $sequence_criteria.max_length
    #end if
#elif $sequence_criteria.sequence_criteria_select == 'regexp'
    --sequence_regexp '$sequence_criteria.regexp'
#end if
$dedup
-o '$output'
#if $output_discarded
    -d '$discarded'
#end if
    ]]></command>
    <inputs>
        <param name="input" type="data" format="fasta" label="FASTA sequences"/>
        <conditional name="header_criteria">
            <param name="header_criteria_select" type="select" label="Criteria for filtering on the headers">
                <option value="">No filtering</option>
                <option value="id_list">List of IDs</option>
                <option value="regexp">Regular expression on the headers</option>
            </param>
            <when value="" />
            <when value="id_list">
                <param name="identifiers" type="data" format="txt" label="List of IDs to extract sequences for"/>
                
                
                <conditional name="id_regex">
                    <param name="find" type="select" label="Match IDs by">
                        <option value="beginning">Default: ID is expected at the beginning: &gt;ID </option>
                        <help>Default: &gt;ID will use search pattern >([^| ]+) to input ID; Use custom regex to change</help>
                        <option value="pattern">Custom regex pattern</option>
                    </param>
                    <when value="beginning">
                        <param name="pattern" type="hidden" value=">([^| ]+)" label="regex search pattern for ID" >
                            <sanitizer sanitize="False"/>
                            <validator type="regex" message="must include a group that returns an ID">^.*[(](?![?]:).*[)].*$</validator>
                        </param>
                    </when>
                    <when value="pattern">
                        <param name="pattern" type="text" value="" label="regex search pattern for ID">
                            <help>search pattern must contain %s where the ID will be substituted. Use this for Uniprot Acc: >.+?\|(.+?)\|.*$ </help>
                            <sanitizer sanitize="False"/>
                            <validator type="regex" message="must include a group that returns an ID">^.*[(](?![?]:).*[)].*$</validator>
                        </param>
                    </when>
                </conditional>
                
                
            </when>
            <when value="regexp">
                <expand macro="regexp_macro" label="Regular expression pattern the header should match" />
            </when>
        </conditional>
        <conditional name="sequence_criteria">
            <param name="sequence_criteria_select" type="select" label="Criteria for filtering on the sequences">
                <option value="">No filtering</option>
                <option value="seq_length">Sequence length</option>
                <option value="regexp">Regular expression on the sequences</option>
            </param>
            <when value="" />
            <when value="seq_length">
                <param name="min_length" type="integer" value="0" label="Minimum length" />
                <param name="max_length" type="integer" min="1" value="" optional="true" label="Maximum length" />
            </when>
            <when value="regexp">
                <expand macro="regexp_macro" label="Regular expression pattern the sequence should match" />
            </when>
        </conditional>
        <param name="dedup" type="boolean" truevalue="--dedup" falsevalue="" label="Remove duplicate sequences" />
        <param name="output_discarded" type="boolean" label="Output discarded FASTA entries" />
    </inputs>
    <outputs>
        <data name="output" format="fasta" label="${tool.name} on ${on_string}: FASTA sequences"/>
        <data name="discarded" format="fasta" label="${tool.name} on ${on_string}: discarded entries">
            <filter>output_discarded</filter>
        </data>
    </outputs>
    <tests>
        <test expect_num_outputs="1">
            <param name="input" ftype="fasta" value="input.fasta" />
            <param name="header_criteria_select" value="id_list" />
            <param name="identifiers" ftype="txt" value="ids.txt" />
            <param name="dedup" value="True" />
            <output name="output" file="output_dedup.fasta" />
        </test>
        <test expect_num_outputs="1">
            <param name="input" ftype="fasta" value="input_sp.fasta" />
            <param name="header_criteria_select" value="id_list" />
            <param name="find" value="pattern" />
            <param name="pattern" value=">.+?\|(.+?)\|.*$" />
            <param name="identifiers" ftype="txt" value="ids_sp.txt" />
            <param name="dedup" value="True" />
            <output name="output" file="output_sp_dedup.fasta" />
        </test>
        <test expect_num_outputs="2">
            <param name="input" ftype="fasta" value="input.fasta" />
            <param name="header_criteria_select" value="id_list" />
            <param name="identifiers" ftype="txt" value="ids.txt" />
            <param name="dedup" value="False" />
            <param name="output_discarded" value="True" />
            <output name="output" file="output_not_dedup.fasta" />
            <output name="discarded" file="discarded_not_dedup.fasta" />
        </test>
        <test expect_num_outputs="2">
            <param name="input" ftype="fasta" value="input.fasta" />
            <param name="header_criteria_select" value="regexp" />
            <param name="regexp" value="2" />
            <param name="dedup" value="False" />
            <param name="output_discarded" value="True" />
            <output name="output" file="output_header_regexp.fasta" />
            <output name="discarded" file="discarded_header_regexp.fasta" />
        </test>
        <test expect_num_outputs="2">
            <param name="input" ftype="fasta" value="input.fasta" />
            <param name="sequence_criteria_select" value="seq_length" />
            <param name="min_length" value="5" />
            <param name="dedup" value="False" />
            <param name="output_discarded" value="True" />
            <output name="output" file="output_min_length5.fasta" />
            <output name="discarded" file="discarded_min_length5.fasta" />
        </test>
        <test expect_num_outputs="2">
            <param name="input" ftype="fasta" value="input.fasta" />
            <param name="sequence_criteria_select" value="seq_length" />
            <param name="max_length" value="4" />
            <param name="dedup" value="False" />
            <param name="output_discarded" value="True" />
            <output name="output" file="output_max_length4.fasta" />
            <output name="discarded" file="discarded_max_length4.fasta" />
        </test>
        <test expect_num_outputs="2">
            <param name="input" ftype="fasta" value="input.fasta" />
            <param name="sequence_criteria_select" value="regexp" />
            <param name="regexp" value="T{2,}" />
            <param name="dedup" value="False" />
            <param name="output_discarded" value="True" />
            <output name="output" file="output_sequence_regexp.fasta" />
            <output name="discarded" file="discarded_sequence_regexp.fasta" />
        </test>
    </tests>
    <help><![CDATA[
**What it does**

Filter entries of a FASTA file on the headers and/or the sequences based on various criteria.
    ]]></help>
</tool>