comparison tools/seq_filter_by_id/seq_filter_by_id.xml @ 10:4a7d8ad2a983 draft

Bump Biopython dependency

9:141612f8c3e3

<tool id="seq_filter_by_id" name="Filter sequences by ID" version="0.2.7">
    <description>from a tabular file</description>
    <requirements>
        <requirement type="package" version="1.67">biopython</requirement>
    </requirements>
    <version_command>
python $__tool_directory__/seq_filter_by_id.py --version
    </version_command>
    <command detect_errors="aggressive">

    </command>
    <inputs>
        <param name="input_file" type="data" format="fasta,fastq,sff" label="Sequence file to be filtered" help="FASTA, FASTQ, or SFF format." />
        <conditional name="id_opts">
            <param name="id_opts_selector" type="select" label="Filter using the ID list from">
                <option value="tabular" selected="True">tabular file</option>
                <option value="list">provided list</option>
                <!-- add UNION or INTERSECTION of multiple tabular files here? -->
            </param>
            <when value="tabular">
                <param name="input_tabular" type="data" format="tabular" label="Tabular file containing sequence identifiers"/>
                <param name="columns" type="data_column" data_ref="input_tabular" multiple="True" numerical="False"
                       label="Column(s) containing sequence identifiers"
                       help="Multi-select list - hold the appropriate key while clicking to select multiple columns">
                    <validator type="no_options" message="Pick at least one column"/>
                </param>
            </when>
            <when value="list">
                <param name="id_list" type="text" size="20x80" area="True" format="tabular"
                       label="List of sequence identifiers (white space separated)"
                       help="You can use both spaces and new lines to separate your identifiers.">
                    <sanitizer>
                        <valid>
                            <!-- default includes underscore, hyphen, etc -->

            <when value="pos" />
            <when value="neg" />
        </conditional>
        <conditional name="adv_opts">
            <param name="adv_opts_selector" type="select" label="Advanced Options">
              <option value="basic" selected="True">Hide Advanced Options</option>
              <option value="advanced">Show Advanced Options</option>
            </param>
            <when value="basic" />
            <when value="advanced">
                <param name="strip_suffix" type="boolean" value="false" label="Remove typical pair read name suffices when matching identifiers?" help="Will remove suffices including Illumina /1 and /2, Roche 454 .f and .r, and assorted Sanger names like .p* and .q*" />
            </when>
        </conditional>
    </inputs>
    <outputs>
        <data name="output_pos" format_source="input_file" metadata_source="input_file" label="$input_file.name with matched ID">

            <param name="columns" value="1" />
            <param name="output_choice" value="both" />
            <param name="adv_opts_selector" value="advanced" />
            <param name="strip_suffix" value="true" />
            <output name="output_pos" file="sanger-pairs-mixed.fastq" ftype="fastq" />
	    <output name="output_neg" file="empty_file.dat" ftype="fastq" />
        </test>
        <test>
            <param name="input_file" value="sanger-pairs-mixed.fastq" ftype="fastq" />
            <param name="input_tabular" value="sanger-pairs-names.tabular" ftype="tabular" />
            <param name="columns" value="1" />

cite the following papers:

Peter J.A. Cock, Björn A. Grüning, Konrad Paszkiewicz and Leighton Pritchard (2013).
Galaxy tools and workflows for sequence analysis with applications
in molecular plant pathology. PeerJ 1:e167
http://dx.doi.org/10.7717/peerj.167

This tool uses Biopython to read and write SFF files, so you may also wish to
cite the Biopython application note (and Galaxy too of course):

Cock et al (2009). Biopython: freely available Python tools for computational
molecular biology and bioinformatics. Bioinformatics 25(11) 1422-3.
http://dx.doi.org/10.1093/bioinformatics/btp163 pmid:19304878.

This tool is available to install into other Galaxy Instances via the Galaxy
Tool Shed at http://toolshed.g2.bx.psu.edu/view/peterjc/seq_filter_by_id
    </help>
    <citations>

10:4a7d8ad2a983

<tool id="seq_filter_by_id" name="Filter sequences by ID" version="0.2.8">
    <description>from a tabular file</description>
    <requirements>
        <requirement type="package" version="1.81">biopython</requirement>
    </requirements>
    <version_command>
python $__tool_directory__/seq_filter_by_id.py --version
    </version_command>
    <command detect_errors="aggressive">

    </command>
    <inputs>
        <param name="input_file" type="data" format="fasta,fastq,sff" label="Sequence file to be filtered" help="FASTA, FASTQ, or SFF format." />
        <conditional name="id_opts">
            <param name="id_opts_selector" type="select" label="Filter using the ID list from">
                <option value="tabular" selected="true">tabular file</option>
                <option value="list">provided list</option>
                <!-- add UNION or INTERSECTION of multiple tabular files here? -->
            </param>
            <when value="tabular">
                <param name="input_tabular" type="data" format="tabular" label="Tabular file containing sequence identifiers"/>
                <param name="columns" type="data_column" data_ref="input_tabular" multiple="true" numerical="false"
                       label="Column(s) containing sequence identifiers"
                       help="Multi-select list - hold the appropriate key while clicking to select multiple columns">
                    <validator type="no_options" message="Pick at least one column"/>
                </param>
            </when>
            <when value="list">
                <param name="id_list" type="text" size="20x80" area="true" format="tabular"
                       label="List of sequence identifiers (white space separated)"
                       help="You can use both spaces and new lines to separate your identifiers.">
                    <sanitizer>
                        <valid>
                            <!-- default includes underscore, hyphen, etc -->

            <when value="pos" />
            <when value="neg" />
        </conditional>
        <conditional name="adv_opts">
            <param name="adv_opts_selector" type="select" label="Advanced Options">
              <option value="basic" selected="true">Hide Advanced Options</option>
              <option value="advanced">Show Advanced Options</option>
            </param>
            <when value="basic" />
            <when value="advanced">
                <param name="strip_suffix" type="boolean" value="false" label="Remove typical pair read name suffixes when matching identifiers?" help="Will remove suffixes including Illumina /1 and /2, Roche 454 .f and .r, and assorted Sanger names like .p* and .q*" />
            </when>
        </conditional>
    </inputs>
    <outputs>
        <data name="output_pos" format_source="input_file" metadata_source="input_file" label="$input_file.name with matched ID">

            <param name="columns" value="1" />
            <param name="output_choice" value="both" />
            <param name="adv_opts_selector" value="advanced" />
            <param name="strip_suffix" value="true" />
            <output name="output_pos" file="sanger-pairs-mixed.fastq" ftype="fastq" />
            <output name="output_neg" file="empty_file.dat" ftype="fastq" />
        </test>
        <test>
            <param name="input_file" value="sanger-pairs-mixed.fastq" ftype="fastq" />
            <param name="input_tabular" value="sanger-pairs-names.tabular" ftype="tabular" />
            <param name="columns" value="1" />

cite the following papers:

Peter J.A. Cock, Björn A. Grüning, Konrad Paszkiewicz and Leighton Pritchard (2013).
Galaxy tools and workflows for sequence analysis with applications
in molecular plant pathology. PeerJ 1:e167
https://doi.org/10.7717/peerj.167

This tool uses Biopython to read and write SFF files, so you may also wish to
cite the Biopython application note (and Galaxy too of course):

Cock et al (2009). Biopython: freely available Python tools for computational
molecular biology and bioinformatics. Bioinformatics 25(11) 1422-3.
https://doi.org/10.1093/bioinformatics/btp163 pmid:19304878.

This tool is available to install into other Galaxy Instances via the Galaxy
Tool Shed at http://toolshed.g2.bx.psu.edu/view/peterjc/seq_filter_by_id
    </help>
    <citations>