Mercurial > repos > peterjc > fasta_filter_by_id
annotate tools/fasta_filter_by_id/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 | |
children |
rev | line source |
---|---|
3
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
1 <tool id="fasta_filter_by_id" name="Filter FASTA by ID" version="0.0.5" hidden="true"> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
2 <description>from a tabular file</description> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
3 <requirements> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
4 <requirement type="package" version="1.0.1">galaxy_sequence_utils</requirement> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
5 </requirements> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
6 <version_command interpreter="python">fasta_filter_by_id.py --version</version_command> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
7 <command interpreter="python"> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
8 fasta_filter_by_id.py $input_tabular $columns $input_fasta |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
9 #if $output_choice_cond.output_choice=="both" |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
10 $output_pos $output_neg |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
11 #elif $output_choice_cond.output_choice=="pos" |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
12 $output_pos - |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
13 #elif $output_choice_cond.output_choice=="neg" |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
14 - $output_neg |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
15 #end if |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
16 </command> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
17 <inputs> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
18 <param name="input_fasta" type="data" format="fasta" label="FASTA file to filter on the identifiers"/> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
19 <param name="input_tabular" type="data" format="tabular" label="Tabular file containing FASTA identifiers"/> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
20 <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"> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
21 <validator type="no_options" message="Pick at least one column"/> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
22 </param> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
23 <conditional name="output_choice_cond"> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
24 <param name="output_choice" type="select" label="Output positive matches, negative matches, or both?"> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
25 <option value="both">Both positive matches (ID on list) and negative matches (ID not on list), as two FASTA files</option> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
26 <option value="pos">Just positive matches (ID on list), as a single FASTA file</option> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
27 <option value="neg">Just negative matches (ID not on list), as a single FASTA file</option> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
28 </param> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
29 <!-- Seems need these dummy entries here, compare this to indels/indel_sam2interval.xml --> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
30 <when value="both" /> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
31 <when value="pos" /> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
32 <when value="neg" /> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
33 </conditional> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
34 </inputs> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
35 <outputs> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
36 <data name="output_pos" format="fasta" label="With matched ID"> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
37 <filter>output_choice_cond["output_choice"] != "neg"</filter> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
38 </data> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
39 <data name="output_neg" format="fasta" label="Without matched ID"> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
40 <filter>output_choice_cond["output_choice"] != "pos"</filter> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
41 </data> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
42 </outputs> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
43 <tests> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
44 <test> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
45 <param name="input_fasta" value="four_human_proteins.fasta" ftype="fasta" /> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
46 <param name="input_tabular" value="blastp_four_human_vs_rhodopsin.tabular" ftype="tabular" /> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
47 <param name="columns" value="1" /> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
48 <param name="output_choice" value="both" /> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
49 <output name="output_pos" file="four_human_proteins_filter_a.fasta" ftype="fasta" /> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
50 <output name="output_neg" file="four_human_proteins_filter_b.fasta" ftype="fasta" /> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
51 </test> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
52 <test> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
53 <param name="input_fasta" value="four_human_proteins.fasta" ftype="fasta" /> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
54 <param name="input_tabular" value="blastp_four_human_vs_rhodopsin.tabular" ftype="tabular" /> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
55 <param name="columns" value="1" /> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
56 <param name="output_choice" value="pos" /> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
57 <output name="output_pos" file="four_human_proteins_filter_a.fasta" ftype="fasta" /> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
58 </test> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
59 <test> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
60 <param name="input_fasta" value="four_human_proteins.fasta" ftype="fasta" /> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
61 <param name="input_tabular" value="blastp_four_human_vs_rhodopsin.tabular" ftype="tabular" /> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
62 <param name="columns" value="1" /> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
63 <param name="output_choice" value="neg" /> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
64 <output name="output_neg" file="four_human_proteins_filter_b.fasta" ftype="fasta" /> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
65 </test> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
66 </tests> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
67 <help> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
68 |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
69 **Deprecated** |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
70 |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
71 This tool is now obsolete, and should not be used in future. It has been |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
72 replaced by a more general version covering FASTA, FASTQ and SFF in one |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
73 single tool. |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
74 |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
75 **What it does** |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
76 |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
77 By default it divides a FASTA file in two, those sequences with or without an |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
78 ID present in the tabular file column(s) specified. You can opt to have a |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
79 single output file of just the matching records, or just the non-matching ones. |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
80 |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
81 Note that the order of sequences in the original FASTA file is preserved. |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
82 Also, if any sequences share an identifier, duplicates are not removed. |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
83 |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
84 **Example Usage** |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
85 |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
86 Given a FASTA file of proteins you might run a signal peptide search (e.g. |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
87 via the SignalP wrapper for Galaxy), then filtered these tabular results to |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
88 select just those with a signal peptide. You could then use this tool to get |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
89 a FASTA file of only the proteins with predicted signal peptides. |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
90 |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
91 </help> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
92 <citations> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
93 <citation type="doi">10.7717/peerj.167</citation> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
94 </citations> |
812383b5d3b8
v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license
peterjc
parents:
diff
changeset
|
95 </tool> |