Mercurial > repos > peterjc > seq_filter_by_id
changeset 11:8a34c565a473 draft
Uploaded v0.0.6h, depend on Biopython 1.62, tabs to spaces in XML
| author | peterjc |
|---|---|
| date | Fri, 27 Sep 2013 06:13:28 -0400 |
| parents | b7ec1c9db38d |
| children | 324893f5751e |
| files | tools/seq_filter_by_id/repository_dependencies.xml tools/seq_filter_by_id/seq_filter_by_id.xml |
| diffstat | 2 files changed, 51 insertions(+), 52 deletions(-) [+] |
line wrap: on
line diff
--- a/tools/seq_filter_by_id/repository_dependencies.xml Thu Sep 26 10:05:52 2013 -0400 +++ b/tools/seq_filter_by_id/repository_dependencies.xml Fri Sep 27 06:13:28 2013 -0400 @@ -2,5 +2,5 @@ <repositories description="This requires Biopython as a dependency."> <!-- Leave out the tool shed and revision to get the current tool shed and latest revision at the time of upload --> -<repository changeset_revision="2f6c871cfa35" name="package_biopython_1_61" owner="biopython" toolshed="http://testtoolshed.g2.bx.psu.edu" /> +<repository changeset_revision="ac9cc2992b69" name="package_biopython_1_62" owner="biopython" toolshed="http://testtoolshed.g2.bx.psu.edu" /> </repositories>
--- a/tools/seq_filter_by_id/seq_filter_by_id.xml Thu Sep 26 10:05:52 2013 -0400 +++ b/tools/seq_filter_by_id/seq_filter_by_id.xml Fri Sep 27 06:13:28 2013 -0400 @@ -1,11 +1,11 @@ <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="1.61">biopython</requirement> - <requirement type="python-module">Bio</requirement> - </requirements> - <version_command interpreter="python">seq_filter_by_id.py --version</version_command> - <command interpreter="python"> + <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 $output_neg @@ -17,32 +17,32 @@ ## TODO - Decide on best way to expose multiple ID files via the XML wrapper. ## Single tabular file, can call the Python script with either UNION or INTERSECTION UNION "$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> - </param> - <!-- 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"> + </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> + </param> + <!-- 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" /> @@ -52,9 +52,9 @@ <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"> + <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" /> @@ -64,20 +64,19 @@ <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_file" value="k12_ten_proteins.fasta" ftype="fasta" /> - <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> - + <filter>output_choice_cond["output_choice"] != "pos"</filter> + </data> + </outputs> + <tests> + <test> + <param name="input_file" value="k12_ten_proteins.fasta" ftype="fasta" /> + <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 @@ -122,5 +121,5 @@ 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> + </help> </tool>