Mercurial > repos > peterjc > fasta_filter_by_id
diff tools/fasta_tools/fasta_filter_by_id.xml @ 3:812383b5d3b8 draft default tip
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
author | peterjc |
---|---|
date | Fri, 03 Feb 2017 05:32:34 -0500 |
parents | 5b552b3005f2 |
children |
line wrap: on
line diff
--- a/tools/fasta_tools/fasta_filter_by_id.xml Tue Jun 07 17:23:07 2011 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,90 +0,0 @@ -<tool id="fasta_filter_by_id" name="Filter FASTA by ID" version="0.0.4" hidden="true"> - <description>from a tabular file</description> - <command interpreter="python"> -fasta_filter_by_id.py $input_tabular $columns $input_fasta -#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 - </command> - <inputs> - <param name="input_fasta" type="data" format="fasta" label="FASTA file to filter on the identifiers"/> - <param name="input_tabular" type="data" format="tabular" label="Tabular file containing FASTA identifiers"/> - <param name="columns" type="data_column" data_ref="input_tabular" multiple="True" numerical="False" label="Column(s) containing FASTA 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 FASTA files</option> - <option value="pos">Just positive matches (ID on list), as a single FASTA file</option> - <option value="neg">Just negative matches (ID not on list), as a single FASTA 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"> - <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"] != "pos"</filter> - </data> - </outputs> - <tests> - <!-- Can't get these unit tests to run, may be a Galaxy problem - <test> - <param name="input_fasta" value="four_human_proteins.fasta" ftype="fasta" /> - <param name="input_tabular" value="blastp_four_human_vs_rhodopsin.tabular" ftype="tabular" /> - <param name="columns" value="1" /> - <param name="output_choice" value="both" /> - <output name="output_pos" file="four_human_proteins_filter_a.fasta" ftype="fasta" /> - <output name="output_neg" file="four_human_proteins_filter_b.fasta" ftype="fasta" /> - </test> - <test> - <param name="input_fasta" value="four_human_proteins.fasta" ftype="fasta" /> - <param name="input_tabular" value="blastp_four_human_vs_rhodopsin.tabular" ftype="tabular" /> - <param name="columns" value="1" /> - <param name="output_choice" value="pos" /> - <output name="output_pos" file="four_human_proteins_filter_a.fasta" ftype="fasta" /> - </test> - <test> - <param name="input_fasta" value="four_human_proteins.fasta" ftype="fasta" /> - <param name="input_tabular" value="blastp_four_human_vs_rhodopsin.tabular" ftype="tabular" /> - <param name="columns" value="1" /> - <param name="output_choice" value="neg" /> - <output name="output_neg" file="four_human_proteins_filter_b.fasta" ftype="fasta" /> - </test> - --> - </tests> - <help> - -**Deprecated** - -This tool is now obsolete, and should not be used in future. It has been -replaced by a more general version covering FASTA, FASTQ and SFF in one -single tool. - -**What it does** - -By default it divides a FASTA 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 FASTA file is preserved. -Also, if any sequences share an identifier, duplicates are not removed. - -**Example Usage** - -Given a FASTA file of proteins you might run a signal peptide search (e.g. -via the SignalP wrapper for Galaxy), then filtered these tabular results to -select just those with a signal peptide. You could then use this tool to get -a FASTA file of only the proteins with predicted signal peptides. - - </help> -</tool>