12
|
1 <tool id="gd_calc_freq" name="Rank" version="1.0.0">
|
|
2 <description>affected KEGG pathways</description>
|
|
3
|
|
4 <command interpreter="python">
|
|
5 #if str($output_format) == 'a'
|
|
6 calctfreq.py
|
|
7 #else if str($output_format) == 'b'
|
|
8 calclenchange.py
|
|
9 #end if
|
|
10 "--loc_file=${GALAXY_DATA_INDEX_DIR}/gd.rank.loc"
|
|
11 "--species=${input.metadata.dbkey}"
|
|
12 "--input=${input}"
|
|
13 "--output=${output}"
|
|
14 "--posKEGGclmn=${input.metadata.kegg_path}"
|
|
15 "--KEGGgeneposcolmn=${input.metadata.kegg_gene}"
|
|
16 </command>
|
|
17
|
|
18 <inputs>
|
|
19 <param name="input" type="data" format="gd_sap" label="Table">
|
|
20 <validator type="metadata" check="kegg_gene,kegg_path" message="Missing KEGG gene code column and/or KEGG pathway code/name column metadata. Click the pencil icon in the history item to edit/save the metadata attributes" />
|
|
21 </param>
|
|
22 <param name="output_format" type="select" label="Output format">
|
|
23 <option value="a" selected="true">ranked by percentage of genes affected</option>
|
|
24 <option value="b">ranked by change in length and number of paths</option>
|
|
25 </param>
|
|
26 </inputs>
|
|
27
|
|
28 <outputs>
|
|
29 <data name="output" format="tabular" />
|
|
30 </outputs>
|
|
31
|
|
32 <tests>
|
|
33 <test>
|
|
34 <param name="input" value="test_in/sample.gd_sap" ftype="gd_sap" />
|
|
35 <param name="output_format" value="a" />
|
|
36 <output name="output" file="test_out/rank_pathways/rank_pathways.tabular" />
|
|
37 </test>
|
|
38 </tests>
|
|
39
|
|
40 <help>
|
|
41 **What it does**
|
|
42
|
|
43 This tool produces a table ranking the pathways based on the percentage
|
|
44 of genes in an input dataset, out of the total in each pathway.
|
|
45 Alternatively, the tool ranks the pathways based on the change in
|
|
46 length and number of paths connecting sources and sinks. This change is
|
|
47 calculated between graphs representing pathways with and without excluding
|
|
48 the nodes that represent the genes in an input list. Sources are all
|
|
49 the nodes representing the initial reactants/products in the pathway.
|
|
50 Sinks are all the nodes representing the final reactants/products in
|
|
51 the pathway.
|
|
52
|
|
53 If pathways are ranked by percentage of genes affected, the output is
|
|
54 a tabular dataset with the following columns:
|
|
55
|
|
56 1. number of genes in the pathway present in the input dataset
|
|
57 2. percentage of the total genes in the pathway included in the input dataset
|
|
58 3. rank of the frequency (from high freq to low freq)
|
|
59 4. name of the pathway
|
|
60
|
|
61 If pathways are ranked by change in length and number of paths, the
|
|
62 output is a tabular dataset with the following columns:
|
|
63
|
|
64 1. change in the mean length of paths between sources and sinks
|
|
65 2. mean length of paths between sources and sinks in the pathway including the genes in the input dataset. If the pathway do not have sources/sinks, the length is assumed to be infinite (I)
|
|
66 3. mean length of paths between sources and sinks in the pathway excluding the genes in the input dataset. If the pathway do not have sources/sinks, the length is assumed to be infinite (I)
|
|
67 4. rank of the change in the mean length of paths between sources and sinks (from high change to low change)
|
|
68 5. change in the number of paths between sources and sinks
|
|
69 6. number of paths between sources and sinks in the pathway including the genes in the input dataset. If the pathway do not have sources/sinks, it is assumed to be a circuit (C)
|
|
70 7. number of paths between sources and sinks in the pathway excluding the genes in the input dataset. If the pathway do not have sources/sinks, it is assumed to be a circuit (C)
|
|
71 8. rank of the change in the number of paths between sources and sinks (from high change to low change)
|
|
72 9. name of the pathway
|
|
73 </help>
|
|
74 </tool>
|