Mercurial > repos > jjohnson > find_in_reference

comparison find_in_reference.xml @ 1:856033fb26e8

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Add case insensitive option
author Jim Johnson <jj@umn.edu>
date Fri, 17 Jan 2014 14:50:53 -0600
parents fe0327a3ba81
children 30975b3ff0dc
comparison
equal deleted inserted replaced
0:fe0327a3ba81 1:856033fb26e8
5 --reference "$reference" 5 --reference "$reference"
6 #if $column.set == 'yes': 6 #if $column.set == 'yes':
7 --input_column $column.input_column 7 --input_column $column.input_column
8 --reference_column $column.reference_column 8 --reference_column $column.reference_column
9 #end if 9 #end if
10 $case_insensitive
10 #if 'novel' in $outputs.__str__ or not 'found' in $outputs.__str__: 11 #if 'novel' in $outputs.__str__ or not 'found' in $outputs.__str__:
11 --output "$novel" 12 --output "$novel"
12 #end if 13 #end if
13 #if 'found' in $outputs.__str__: 14 #if 'found' in $outputs.__str__:
14 --filtered "$found" 15 --filtered "$found"
15 #end if 16 #end if
16 </command> 17 </command>
17 <inputs> 18 <inputs>
18 <param name="input" type="data" format="tabular" label="Input file to be filtered" 19 <param name="input" type="data" format="tabular" label="Input file to be filtered"
19 help="e.g. tophat junctions.bed run without GTF option or no-novel-junctions"/> 20 help="e.g. a peptide fasta converted to tabular"/>
20 <param name="reference" type="data" format="tabular" label="reference file to search" 21 <param name="reference" type="data" format="tabular" label="reference file to search"
21 help="e.g. tophat junctions.bed run with GTF option and no-novel-junctions"/> 22 help="e.g. a protein fasta converted to tabular"/>
22 <conditional name="column"> 23 <conditional name="column">
23 <param name="set" type="select" label="select columns to compare"> 24 <param name="set" type="select" label="select columns to compare">
24 <option value="no" selected="true">Use last column of input and reference</option> 25 <option value="no" selected="true">Use last column of input and reference</option>
25 <option value="yes">Choose the column of input and reference to compare</option> 26 <option value="yes">Choose the column of input and reference to compare</option>
26 </param> 27 </param>
30 help=""/> 31 help=""/>
31 <param name="reference_column" type="data_column" data_ref="reference" label="column in reference (defaults to last column)" 32 <param name="reference_column" type="data_column" data_ref="reference" label="column in reference (defaults to last column)"
32 help=""/> 33 help=""/>
33 </when> 34 </when>
34 </conditional> 35 </conditional>
36 <param name="case_insensitive" type="boolean" truevalue="--case_insensitive" falsevalue="" checked="false" label="Ignore case when comparing"/>
35 <param name="outputs" type="select" multiple="true" display="checkboxes" label="Choose outputs"> 37 <param name="outputs" type="select" multiple="true" display="checkboxes" label="Choose outputs">
36 <option value="novel" selected="true">lines with no match in reference</option> 38 <option value="novel" selected="true">lines with no match in reference</option>
37 <option value="found">lines with match in reference</option> 39 <option value="found">lines with match in reference</option>
38 </param> 40 </param>
39 </inputs> 41 </inputs>
56 </test> 58 </test>
57 </tests> 59 </tests>
58 <help> 60 <help>
59 **Find in Reference** 61 **Find in Reference**
60 62
61 Filters lines of a tabular input file by checking if the selected input column 63 Filters lines of a tabular input file by checking if the selected input column value
62 is a substring of the selected column of any line in the reference file. 64 is a substring of the selected column of any line in the reference file.
63 65
64 This can be used to check if peptides sequences are present in a set of reference proteins, 66 This can be used to check if peptides sequences are present in a set of reference proteins,
65 as a means of filtering out uninteresting peptide sequences. 67 as a means of filtering out uninteresting peptide sequences.
66 68
69 For Example with::
70
71 Input
72 >pep1 LIL
73 >pep2 WTF
74 >pep3 ISK
75
76 Reference
77 >prot1 RLET
78 >prot2 LLIL
79 >prot3 LAPSE
80 >prot3 RISKY
81
82 The outputs
83
84 Not found in reference
85 >pep2 WTF
86
87 Found in reference
88 >pep1 LIL
89 >pep3 ISK
90
91
67 </help> 92 </help>
68 </tool> 93 </tool>