comparison tools/seq_filter_by_id/seq_filter_by_id.xml @ 5:832c1fd57852 draft

v0.2.2; New options for IDs via text parameter, ignore paired read suffix; misc changes

4:1c36cf8ef133

<tool id="seq_filter_by_id" name="Filter sequences by ID" version="0.0.6">
    <description>from a tabular file</description>
    <requirements>
        <requirement type="package" version="1.62">biopython</requirement>
        <requirement type="python-module">Bio</requirement>
    </requirements>
    <version_command interpreter="python">seq_filter_by_id.py --version</version_command>
    <command interpreter="python">
seq_filter_by_id.py "$input_file" "$input_file.ext"
#if $output_choice_cond.output_choice=="both"
 $output_pos $output_neg
#elif $output_choice_cond.output_choice=="pos"
 $output_pos -
#elif $output_choice_cond.output_choice=="neg"
 - $output_neg
#end if
## TODO - Decide on best way to expose multiple ID files via the XML wrapper.
## Single tabular file, can call the Python script with either UNION or INTERSECTION
UNION "$input_tabular" "$columns"
    </command>
    <stdio>
        <!-- Anything other than zero is an error -->
        <exit_code range="1:" />
        <exit_code range=":-1" />
    </stdio>
    <inputs>
        <param name="input_file" type="data" format="fasta,fastq,sff" label="Sequence file to filter on the identifiers" help="FASTA, FASTQ, or SFF format." />
        <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>
        <conditional name="output_choice_cond">
            <param name="output_choice" type="select" label="Output positive matches, negative matches, or both?">
                <option value="both">Both positive matches (ID on list) and negative matches (ID not on list), as two files</option>
                <option value="pos">Just positive matches (ID on list), as a single file</option>
                <option value="neg">Just negative matches (ID not on list), as a single file</option>

            <!-- Seems need these dummy entries here, compare this to indels/indel_sam2interval.xml -->
            <when value="both" />
            <when value="pos" />
            <when value="neg" />
        </conditional>
    </inputs>
    <outputs>
        <data name="output_pos" format="fasta" label="With matched ID">
            <!-- TODO - Replace this with format="input:input_fastq" if/when that works -->
            <change_format>
                <when input_dataset="input_file" attribute="extension" value="sff" format="sff" />
                <when input_dataset="input_file" attribute="extension" value="fastq" format="fastq" />
                <when input_dataset="input_file" attribute="extension" value="fastqsanger" format="fastqsanger" />
                <when input_dataset="input_file" attribute="extension" value="fastqsolexa" format="fastqsolexa" />
                <when input_dataset="input_file" attribute="extension" value="fastqillumina" format="fastqillumina" />
                <when input_dataset="input_file" attribute="extension" value="fastqcssanger" format="fastqcssanger" />
            </change_format>
            <filter>output_choice_cond["output_choice"] != "neg"</filter>
        </data>
        <data name="output_neg" format="fasta" label="Without matched ID">
            <!-- TODO - Replace this with format="input:input_fastq" if/when that works -->
            <change_format>
                <when input_dataset="input_file" attribute="extension" value="sff" format="sff" />
                <when input_dataset="input_file" attribute="extension" value="fastq" format="fastq" />
                <when input_dataset="input_file" attribute="extension" value="fastqsanger" format="fastqsanger" />
                <when input_dataset="input_file" attribute="extension" value="fastqsolexa" format="fastqsolexa" />
                <when input_dataset="input_file" attribute="extension" value="fastqillumina" format="fastqillumina" />
                <when input_dataset="input_file" attribute="extension" value="fastqcssanger" format="fastqcssanger" />
            </change_format>
            <filter>output_choice_cond["output_choice"] != "pos"</filter>
        </data>
    </outputs>
    <tests>
        <test>

            <param name="input_tabular" value="k12_hypothetical.tabular" ftype="tabular" />
            <param name="columns" value="1" />
            <param name="output_choice" value="pos" />
            <output name="output_pos" file="k12_hypothetical.fasta" ftype="fasta" />
        </test>
    </tests>
    <help>
**What it does**

By default it divides a FASTA, FASTQ or Standard Flowgram Format (SFF) file in
two, those sequences with or without an ID present in the tabular file column(s)
specified. You can opt to have a single output file of just the matching records,
or just the non-matching ones.

Note that the order of sequences in the original sequence file is preserved, as
is any Roche XML Manifest in an SFF file. Also, if any sequences share an
identifier (which would be very unusual in SFF files), duplicates are not removed.

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>
</tool>

5:832c1fd57852

<tool id="seq_filter_by_id" name="Filter sequences by ID" version="0.2.2">
    <description>from a tabular file</description>
    <requirements>
        <requirement type="package" version="1.64">biopython</requirement>
        <requirement type="python-module">Bio</requirement>
    </requirements>
    <stdio>
        <!-- Anything other than zero is an error -->
        <exit_code range="1:" />
        <exit_code range=":-1" />
    </stdio>
    <version_command interpreter="python">seq_filter_by_id.py --version</version_command>
    <command interpreter="python">
seq_filter_by_id.py -i "$input_file" -f "$input_file.ext"
#if $output_choice_cond.output_choice=="both"
 -p $output_pos -n $output_neg
#elif $output_choice_cond.output_choice=="pos"
 -p $output_pos
#elif $output_choice_cond.output_choice=="neg"
 -n $output_neg
#end if
#if $adv_opts.adv_opts_selector=="advanced" and $adv_opts.strip_suffix
 -s
#end if
#if $id_opts.id_opts_selector=="tabular":
## TODO - Decide on best way to expose multiple ID files via the XML wrapper.
## Single tabular file, can call the Python script with either UNION or INTERSECTION
-l UNION "$id_opts.input_tabular" "$id_opts.columns"
#else
-t "$id_opts.id_list"
#end if
    </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 -->
                            <add value="%"/>
                            <add value="|"/>
                        </valid>
                    </sanitizer>
                </param>
            </when>
        </conditional>
        <conditional name="output_choice_cond">
            <param name="output_choice" type="select" label="Output positive matches, negative matches, or both?">
                <option value="both">Both positive matches (ID on list) and negative matches (ID not on list), as two files</option>
                <option value="pos">Just positive matches (ID on list), as a single file</option>
                <option value="neg">Just negative matches (ID not on list), as a single file</option>

            <!-- Seems need these dummy entries here, compare this to indels/indel_sam2interval.xml -->
            <when value="both" />
            <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="$input_file.name with matched ID">
            <filter>output_choice_cond["output_choice"] != "neg"</filter>
        </data>
        <data name="output_neg" format_source="input_file" metadata_source="input_file" label="$input_file.name without matched ID">
            <filter>output_choice_cond["output_choice"] != "pos"</filter>
        </data>
    </outputs>
    <tests>
        <test>

            <param name="input_tabular" value="k12_hypothetical.tabular" ftype="tabular" />
            <param name="columns" value="1" />
            <param name="output_choice" value="pos" />
            <output name="output_pos" file="k12_hypothetical.fasta" ftype="fasta" />
        </test>
        <test>
            <param name="input_file" value="k12_ten_proteins.fasta" ftype="fasta" />
            <param name="input_tabular" value="k12_hypothetical_alt.tabular" ftype="tabular" />
            <param name="columns" value="1" />
            <param name="output_choice" value="pos" />
            <param name="adv_opts_selector" value="advanced" />
            <param name="strip_suffix" value="true" />
            <output name="output_pos" file="k12_hypothetical.fasta" ftype="fasta" />
        </test>
        <test>
            <param name="input_file" value="k12_ten_proteins.fasta" ftype="fasta" />
            <param name="id_opts_selector" value="list" />
            <param name="id_list" value="gi|16127999|ref|NP_414546.1|" />
            <param name="output_choice" value="pos" />
            <output name="output_pos" file="k12_hypothetical.fasta" ftype="fasta" />
        </test>
        <test>
            <param name="input_file" value="sanger-pairs-mixed.fastq" ftype="fastq" />
            <param name="id_opts_selector" value="list" />
            <param name="id_list" value="WTSI_1055_1a05 WTSI_1055_1g02" />
            <param name="output_choice" value="pos" />
            <param name="adv_opts_selector" value="advanced" />
            <param name="strip_suffix" value="true" />
            <output name="output_pos" file="sanger-sample.fastq" ftype="fastq" />
        </test>
        <test>
            <param name="input_file" value="sanger-pairs-mixed.fastq" ftype="fastq" />
            <param name="id_opts_selector" value="tabular" />
            <param name="input_tabular" value="sanger-pairs-names.tabular" ftype="tabular" />
            <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" />
            <param name="output_choice" value="both" />
            <param name="adv_opts_selector" value="advanced" />
            <param name="strip_suffix" value="false" />
            <output name="output_pos" file="empty_file.dat" ftype="fastq" />
            <output name="output_neg" file="sanger-pairs-mixed.fastq" ftype="fastq" />
        </test>
    </tests>
    <help>
**What it does**

By default it divides a FASTA, FASTQ or Standard Flowgram Format (SFF) file in
two, those sequences with or without an ID present in the tabular file column(s)
specified. You can opt to have a single output file of just the matching records,
or just the non-matching ones.

Instead of providing the identifiers in a tabular file, you can alternatively
provide them as a parameter (type or paste them into the text box). This is a
useful shortcut for extracting a few sequences of interest without first having
to prepare a tabular file.

Note that the order of sequences in the original sequence file is preserved, as
is any Roche XML Manifest in an SFF file. Also, if any sequences share an
identifier (which would be very unusual in SFF files), duplicates are not removed.

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>
        <citation type="doi">10.7717/peerj.167</citation>
        <citation type="doi">10.1093/bioinformatics/btp163</citation>
    </citations>
</tool>