annotate rank_pathways.xml @ 32:03c22b722882

remove BeautifulSoup dependency
author Richard Burhans <burhans@bx.psu.edu>
date Fri, 20 Sep 2013 13:54:23 -0400
parents a631c2f6d913
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
27
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
1 <tool id="gd_calc_freq" name="Rank Pathways" version="1.2.0">
22
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents: 21
diff changeset
2 <description>: Assess the impact of a gene set on KEGG pathways</description>
14
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
3
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
4 <command interpreter="python">
27
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
5 #if $rank_by.choice == 'pct'
22
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents: 21
diff changeset
6 rank_pathways_pct.py
27
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
7 --input '$rank_by.input1'
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
8 --columnENSEMBLT '$rank_by.t_col1'
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
9 --inBckgrndfile '$rank_by.input2'
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
10 --columnENSEMBLTBckgrnd '$rank_by.t_col2'
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
11 --columnKEGGBckgrnd '$rank_by.k_col2'
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
12 --statsTest '$rank_by.stat'
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
13 --output '$output'
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
14 #else if $rank_by.choice == 'paths'
14
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
15 calclenchange.py
27
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
16 '--loc_file=${GALAXY_DATA_INDEX_DIR}/gd.rank.loc'
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
17 '--species=${rank_by.input.metadata.dbkey}'
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
18 '--input=${rank_by.input}'
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
19 '--output=${output}'
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
20 '--posKEGGclmn=${rank_by.kpath}'
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
21 '--KEGGgeneposcolmn=${rank_by.kgene}'
14
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
22 #end if
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
23 </command>
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
24
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
25 <inputs>
27
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
26 <conditional name="rank_by">
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
27 <param name="choice" type="select" label="Rank by">
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
28 <option value="pct" selected="true">percentage of genes affected</option>
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
29 <option value="paths">change in length and number of paths</option>
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
30 </param>
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
31 <when value="pct">
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
32 <!-- using fields similar to the Rank Terms tool -->
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
33 <param name="input1" type="data" format="tabular" label="Query dataset" />
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
34 <param name="t_col1" type="data_column" data_ref="input1" label="Column with ENSEMBL transcript codes" />
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
35 <param name="input2" type="data" format="tabular" label="Background dataset" />
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
36 <param name="t_col2" type="data_column" data_ref="input2" label="Column with ENSEMBL transcript codes" />
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
37 <param name="k_col2" type="data_column" data_ref="input2" label="Column with KEGG pathways" />
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
38 <param name="stat" type="select" label="Statistic for determining enrichment/depletion">
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
39 <option value="fisher" selected="true">two-tailed Fisher's exact test</option>
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
40 <option value="hypergeometric">hypergeometric test</option>
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
41 <option value="binomial">binomial probability</option>
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
42 </param>
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
43 </when>
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
44 <when value="paths">
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
45 <param name="input" type="data" format="tabular" label="Dataset" />
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
46 <param name="kgene" type="data_column" data_ref="input" label="Column with KEGG gene ID" />
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
47 <param name="kpath" type="data_column" data_ref="input" numerical="false" label="Column with KEGG pathways" />
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
48 </when>
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
49 </conditional>
14
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
50 </inputs>
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
51
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
52 <outputs>
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
53 <data name="output" format="tabular" />
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
54 </outputs>
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
55
31
a631c2f6d913 Update to Miller Lab devshed revision 3c4110ffacc3
Richard Burhans <burhans@bx.psu.edu>
parents: 28
diff changeset
56 <requirements>
a631c2f6d913 Update to Miller Lab devshed revision 3c4110ffacc3
Richard Burhans <burhans@bx.psu.edu>
parents: 28
diff changeset
57 <requirement type="package" version="0.2.5">mechanize</requirement>
a631c2f6d913 Update to Miller Lab devshed revision 3c4110ffacc3
Richard Burhans <burhans@bx.psu.edu>
parents: 28
diff changeset
58 <requirement type="package" version="1.8.1">networkx</requirement>
a631c2f6d913 Update to Miller Lab devshed revision 3c4110ffacc3
Richard Burhans <burhans@bx.psu.edu>
parents: 28
diff changeset
59 <requirement type="package" version="0.1.4">fisher</requirement>
a631c2f6d913 Update to Miller Lab devshed revision 3c4110ffacc3
Richard Burhans <burhans@bx.psu.edu>
parents: 28
diff changeset
60 </requirements>
a631c2f6d913 Update to Miller Lab devshed revision 3c4110ffacc3
Richard Burhans <burhans@bx.psu.edu>
parents: 28
diff changeset
61
a631c2f6d913 Update to Miller Lab devshed revision 3c4110ffacc3
Richard Burhans <burhans@bx.psu.edu>
parents: 28
diff changeset
62
14
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
63 <tests>
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
64 <test>
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
65 </test>
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
66 </tests>
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
67
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
68 <help>
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
69
21
d6b961721037 Miller Lab Devshed version 4c04e35b18f6
Richard Burhans <burhans@bx.psu.edu>
parents: 14
diff changeset
70 **Dataset formats**
d6b961721037 Miller Lab Devshed version 4c04e35b18f6
Richard Burhans <burhans@bx.psu.edu>
parents: 14
diff changeset
71
28
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
72 The query dataset has a column containing ENSEMBL transcript codes for
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
73 the gene set of interest, while the background dataset has one column
31
a631c2f6d913 Update to Miller Lab devshed revision 3c4110ffacc3
Richard Burhans <burhans@bx.psu.edu>
parents: 28
diff changeset
74 with ENSEMBL transcript codes and another with KEGG pathways, for some larger
28
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
75 universe of genes.
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
76
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
77 All of the input and output datasets are in tabular_ format. The input
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
78 dataset (i.e. query) to rank by "percentage of genes affected" has a
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
79 column containing ENSEMBL transcript codes for the gene set of interest,
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
80 while the background dataset has one column with ENSEMBL transcript
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
81 codes and another with KEGG pathways, for some larger universe of genes.
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
82 The input dataset to rank by "change in length and number of paths"
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
83 must have columns with KEGG gene ID and pathways. The output datasets
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
84 are described below. (`Dataset missing?`_)
21
d6b961721037 Miller Lab Devshed version 4c04e35b18f6
Richard Burhans <burhans@bx.psu.edu>
parents: 14
diff changeset
85
d6b961721037 Miller Lab Devshed version 4c04e35b18f6
Richard Burhans <burhans@bx.psu.edu>
parents: 14
diff changeset
86 .. _tabular: ./static/formatHelp.html#tab
d6b961721037 Miller Lab Devshed version 4c04e35b18f6
Richard Burhans <burhans@bx.psu.edu>
parents: 14
diff changeset
87 .. _Dataset missing?: ./static/formatHelp.html
d6b961721037 Miller Lab Devshed version 4c04e35b18f6
Richard Burhans <burhans@bx.psu.edu>
parents: 14
diff changeset
88
d6b961721037 Miller Lab Devshed version 4c04e35b18f6
Richard Burhans <burhans@bx.psu.edu>
parents: 14
diff changeset
89 -----
d6b961721037 Miller Lab Devshed version 4c04e35b18f6
Richard Burhans <burhans@bx.psu.edu>
parents: 14
diff changeset
90
14
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
91 **What it does**
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
92
28
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
93 Given a query set of genes from a larger background dataset, this tool
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
94 evaluates the over- or under-representation of KEGG pathways in the query
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
95 set, using the specified statistical test. Alternatively, the tool ranks
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
96 the pathways based on the change in length and number of paths connecting
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
97 sources and sinks. This change is calculated between graphs representing
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
98 pathways with and without excluding the nodes that represent the genes
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
99 in an input list. Sources are all the nodes representing the initial
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
100 reactants/products in the pathway. Sinks are all the nodes representing
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
101 the final reactants/products in the pathway.
14
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
102
28
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
103 If pathways are ranked by percentage of genes affected, the output
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
104 contains a row for each KEGG pathway, with the following columns:
14
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
105
27
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
106 1. count: the number of genes in the query set that are in this pathway
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
107 2. representation: the percentage of this pathway's genes (from the background dataset) that appear in the query set
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
108 3. ranking of this pathway, based on its representation ("1" is highest)
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
109 4. probability of depletion of this pathway in the query dataset
8997f2ca8c7a Update to Miller Lab devshed revision bae0d3306d3b
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
110 5. probability of enrichment of this pathway in the query dataset
28
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
111 6. name of the pathway
14
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
112
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
113 If pathways are ranked by change in length and number of paths, the
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
114 output is a tabular dataset with the following columns:
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
115
21
d6b961721037 Miller Lab Devshed version 4c04e35b18f6
Richard Burhans <burhans@bx.psu.edu>
parents: 14
diff changeset
116 1. change in the mean length of paths between sources and sinks
28
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
117 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)
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
118 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)
21
d6b961721037 Miller Lab Devshed version 4c04e35b18f6
Richard Burhans <burhans@bx.psu.edu>
parents: 14
diff changeset
119 4. rank of the change in the mean length of paths between sources and sinks (from high change to low change)
d6b961721037 Miller Lab Devshed version 4c04e35b18f6
Richard Burhans <burhans@bx.psu.edu>
parents: 14
diff changeset
120 5. change in the number of paths between sources and sinks
28
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
121 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)
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
122 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)
21
d6b961721037 Miller Lab Devshed version 4c04e35b18f6
Richard Burhans <burhans@bx.psu.edu>
parents: 14
diff changeset
123 8. rank of the change in the number of paths between sources and sinks (from high change to low change)
d6b961721037 Miller Lab Devshed version 4c04e35b18f6
Richard Burhans <burhans@bx.psu.edu>
parents: 14
diff changeset
124 9. name of the pathway
d6b961721037 Miller Lab Devshed version 4c04e35b18f6
Richard Burhans <burhans@bx.psu.edu>
parents: 14
diff changeset
125
d6b961721037 Miller Lab Devshed version 4c04e35b18f6
Richard Burhans <burhans@bx.psu.edu>
parents: 14
diff changeset
126 -----
d6b961721037 Miller Lab Devshed version 4c04e35b18f6
Richard Burhans <burhans@bx.psu.edu>
parents: 14
diff changeset
127
d6b961721037 Miller Lab Devshed version 4c04e35b18f6
Richard Burhans <burhans@bx.psu.edu>
parents: 14
diff changeset
128 **Examples**
d6b961721037 Miller Lab Devshed version 4c04e35b18f6
Richard Burhans <burhans@bx.psu.edu>
parents: 14
diff changeset
129
28
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
130 Rank by percentage of genes affected:
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
131
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
132 - input background dataset (column 5 for ENSEMBL transcript, column 12 for KEGG pathways, two-tailed Fisher's exact test for statistic)::
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
133
21
d6b961721037 Miller Lab Devshed version 4c04e35b18f6
Richard Burhans <burhans@bx.psu.edu>
parents: 14
diff changeset
134 Contig39_chr1_3261104_3261850 414 chr1 3261546 ENSCAFT00000000001 ENSCAFP00000000001 S 667 F 476153 probably damaging cfa00230=Purine metabolism.cfa00500=Starch and sucrose metabolism.cfa00740=Riboflavin metabolism.cfa00760=Nicotinate and nicotinamide metabolism.cfa00770=Pantothenate and CoA biosynthesis.cfa01100=Metabolic pathways
d6b961721037 Miller Lab Devshed version 4c04e35b18f6
Richard Burhans <burhans@bx.psu.edu>
parents: 14
diff changeset
135 Contig62_chr1_19011969_19012646 265 chr1 19012240 ENSCAFT00000000144 ENSCAFP00000000125 * 161 R 483960 probably damaging N
d6b961721037 Miller Lab Devshed version 4c04e35b18f6
Richard Burhans <burhans@bx.psu.edu>
parents: 14
diff changeset
136 etc.
28
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
137
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
138 - input query dataset (column 5 for ENSEMBL transcript)::
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
139
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
140 Contig12_chr20_101969_112646 265 chr20 9822141 ENSCAFT00000001234 ENSCAFP00000021123 T 101 R 476153 probably damaging
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
141 Contig39_chr1_3261104_3261850 414 chr1 3261546 ENSCAFT00000000001 ENSCAFP00000000001 S 667 F 476153 probably damaging
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
142 etc.
21
d6b961721037 Miller Lab Devshed version 4c04e35b18f6
Richard Burhans <burhans@bx.psu.edu>
parents: 14
diff changeset
143
28
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
144 - output::
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
145
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
146 3 0.20 1 1.0 0.0065 cfa03450=Non-homologous end-joining
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
147 1 0.067 2 1.0 0.019 cfa00750=Vitamin B6 metabolism
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
148 2 0.062 3 1.0 0.021 cfa00290=Valine, leucine and isoleucine biosynthesis
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
149 1 0.037 4 1.0 0.035 cfa00770=Pantothenate and CoA biosynthesis
21
d6b961721037 Miller Lab Devshed version 4c04e35b18f6
Richard Burhans <burhans@bx.psu.edu>
parents: 14
diff changeset
150 etc.
d6b961721037 Miller Lab Devshed version 4c04e35b18f6
Richard Burhans <burhans@bx.psu.edu>
parents: 14
diff changeset
151
28
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
152 Rank by change in length and number of paths:
21
d6b961721037 Miller Lab Devshed version 4c04e35b18f6
Richard Burhans <burhans@bx.psu.edu>
parents: 14
diff changeset
153
28
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
154 - input (column 10 for KEGG gene ID, column 12 for KEGG pathways)::
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
155
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
156 Contig39_chr1_3261104_3261850 414 chr1 3261546 ENSCAFT00000000001 ENSCAFP00000000001 S 667 F 476153 probably damaging cfa00230=Purine metabolism.cfa00500=Starch and sucrose metabolism.cfa00740=Riboflavin metabolism.cfa00760=Nicotinate and nicotinamide metabolism.cfa00770=Pantothenate and CoA biosynthesis.cfa01100=Metabolic pathways
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
157 Contig62_chr1_19011969_19012646 265 chr1 19012240 ENSCAFT00000000144 ENSCAFP00000000125 * 161 R 483960 probably damaging N
21
d6b961721037 Miller Lab Devshed version 4c04e35b18f6
Richard Burhans <burhans@bx.psu.edu>
parents: 14
diff changeset
158 etc.
14
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
159
28
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
160 - output::
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
161
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
162 3.64 8.44 4.8 2 4 9 5 1 cfa00260=Glycine, serine and threonine metabolism
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
163 7.6 9.6 2 1 3 5 2 2 cfa00240=Pyrimidine metabolism
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
164 0.05 2.67 2.62 6 1 30 29 3 cfa00982=Drug metabolism - cytochrome P450
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
165 -0.08 8.33 8.41 84 1 30 29 3 cfa00564=Glycerophospholipid metabolism
184d14e4270d Update to Miller Lab devshed revision 4ede22dd5500
Richard Burhans <burhans@bx.psu.edu>
parents: 27
diff changeset
166 etc.
14
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
167 </help>
8ae67e9fb6ff Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
miller-lab
parents:
diff changeset
168 </tool>