comparison find_in_reference.xml @ 0:fe0327a3ba81

Uploaded
author jjohnson
date Sat, 04 Jan 2014 09:03:57 -0500
parents
children 856033fb26e8
comparison
equal deleted inserted replaced
-1:000000000000 0:fe0327a3ba81
1 <?xml version="1.0"?>
2 <tool id="find_in_reference" name="find in reference" version="0.0.1">
3 <description>filter peptides that are present in proteins</description>
4 <command interpreter="python">find_in_reference.py --input "$input"
5 --reference "$reference"
6 #if $column.set == 'yes':
7 --input_column $column.input_column
8 --reference_column $column.reference_column
9 #end if
10 #if 'novel' in $outputs.__str__ or not 'found' in $outputs.__str__:
11 --output "$novel"
12 #end if
13 #if 'found' in $outputs.__str__:
14 --filtered "$found"
15 #end if
16 </command>
17 <inputs>
18 <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 <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 <conditional name="column">
23 <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="yes">Choose the column of input and reference to compare</option>
26 </param>
27 <when value="no"/>
28 <when value="yes">
29 <param name="input_column" type="data_column" data_ref="input" label="column in input (defaults to last column)"
30 help=""/>
31 <param name="reference_column" type="data_column" data_ref="reference" label="column in reference (defaults to last column)"
32 help=""/>
33 </when>
34 </conditional>
35 <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>
37 <option value="found">lines with match in reference</option>
38 </param>
39 </inputs>
40 <stdio>
41 <exit_code range="1:" level="fatal" description="Error" />
42 </stdio>
43 <outputs>
44 <data name="found" metadata_source="input" format_source="input" label="${tool.name} on ${on_string}: found">
45 <filter>'found' in str(outputs)</filter>
46 </data>
47 <data name="novel" metadata_source="input" format_source="input" label="${tool.name} on ${on_string}: novel">
48 <filter>'novel' in str(outputs) or not 'found' in str(outputs)</filter>
49 </data>
50 </outputs>
51 <tests>
52 <test>
53 <param name="input" value="human_peptides.tabular" ftype="tabular" dbkey="hg19"/>
54 <param name="reference" value="human_proteins.tabular" ftype="tabular" dbkey="hg19"/>
55 <output name="novel" file="novel_peptides.tabular"/>
56 </test>
57 </tests>
58 <help>
59 **Find in Reference**
60
61 Filters lines of a tabular input file by checking if the selected input column
62 is a substring of the selected column of any line in the reference file.
63
64 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.
66
67 </help>
68 </tool>