|
0
|
1 <?xml version="1.0" encoding="utf-8"?>
|
|
|
2 <tool id="gistc" name="GISTIC2.0" version="2.0.22">
|
|
|
3 <description>The GISTIC module identifies regions of the genome that are significantly amplified or deleted across a set of samples.</description>
|
|
|
4 <requirements>
|
|
|
5 <requirement type="package" version="2.0.22">gistic</requirement>
|
|
|
6 <requirement type="set_environment">GISTIC_SCRIPT_PATH</requirement>
|
|
|
7 <requirement type="set_environment">GISTIC_DIR</requirement>
|
|
|
8 </requirements>
|
|
|
9
|
|
|
10 <stdio>
|
|
|
11 <exit_code range="1:" />
|
|
|
12 <exit_code range=":-1" />
|
|
|
13 </stdio>
|
|
|
14
|
|
|
15 <command>
|
|
|
16 <![CDATA[
|
|
|
17 ##make directory for results
|
|
|
18 mkdir ./results;
|
|
|
19 touch ./results/sig_regions.bed;
|
|
|
20 ##start command line
|
|
|
21 \$GISTIC_DIR/gp_gistic2_from_seg
|
|
|
22 -b ./results
|
|
|
23 -seg $segfile
|
|
|
24 -mk $markersfile
|
|
|
25 ##reference sequence selector
|
|
|
26 #if str($ref_select) == "hg19":
|
|
|
27 -refgene \$GISTIC_DIR/refgenefiles/hg19.mat
|
|
|
28 #elif str($ref_select) == "hg18":
|
|
|
29 -refgene \$GISTIC_DIR/refgenefiles/hg18.mat
|
|
|
30 #elif str($ref_select) == "hg17":
|
|
|
31 -refgene \$GISTIC_DIR/refgenefiles/hg17.mat
|
|
|
32 #elif str($ref_select) == "hg16":
|
|
|
33 -refgene \$GISTIC_DIR/refgenefiles/hg16.mat
|
|
|
34 #end if
|
|
|
35 #if $broad:
|
|
|
36 -broad 1
|
|
|
37 #end if
|
|
|
38 #if $armpeel:
|
|
|
39 -armpeel 1
|
|
|
40 #end if
|
|
|
41 #if $rx:
|
|
|
42 -rx 1
|
|
|
43 #end if
|
|
|
44 -brlen $brlen
|
|
|
45 -conf $conf
|
|
|
46 -qvt $qvt;
|
|
|
47 cut -f 1,3,6,7 results/all_lesions.conf_75.txt | awk 'BEGIN {FS="\t"; OFS="\t";};{if (\$3 < $qvt) print \$2, \$1}' | perl -pe 's/\(\S+\s\S+//;s/Delet.+/hetd/;s/Ampl.+/gain/;s/[:-]/\t/g;s/chr//;' >> results/sig_regions.bed ;
|
|
|
48 cp results/sig_regions.bed $sig_regions;
|
|
|
49 rm -f results/*.mat;
|
|
|
50 ]]>
|
|
|
51 </command>
|
|
|
52
|
|
|
53 <inputs>
|
|
|
54 <param name="segfile" type="data" format="tabular" label="Seg file created using IGV2Gistic tool." />
|
|
|
55 <param name="markersfile" type="data" format="tabular" label="markers file created using IGV2Gistic tool." />
|
|
|
56 <param name="ref_select" type="select" label="Select reference gene file">
|
|
|
57 <option value="hg19" selected="True">hg19</option>
|
|
|
58 <option value="hg18">hg18</option>
|
|
|
59 <option value="hg17">hg17</option>
|
|
|
60 <option value="hg16">hg16</option>
|
|
|
61 </param>
|
|
|
62 <param name="genegistic" type="boolean" checked="true" truevalue="yes" falsevalue="" label="Flag indicating that the gene GISTIC algorithm should be used to calculate the significance of deletions at a gene level instead of a marker level."/>
|
|
|
63 <param name="broad" type="boolean" checked="false" truevalue="yes" falsevalue="" label="Flag indicating whether an additional broad-level analysis should be performed."/>
|
|
|
64 <param name="armpeel" type="boolean" truevalue="yes" checked="false" falsevalue="" label="Whether to perform arm level peel off"/>
|
|
|
65 <param name="rx" type="boolean" truevalue="yes" checked="false" falsevalue="" label="Whether to ignore the X chromosome"/>
|
|
|
66 <param name="brlen" type="float" value="0.98" label="Threshold used to distinguish broad from focal events. given in units of fraction of chromosome arm."/>
|
|
|
67 <param name="conf" type="float" value="0.75" label="Confidence level used to calculate the region"/>
|
|
|
68 <param name="qvt" type="float" value="0.75" label="Q value threshold for significance"/>
|
|
|
69
|
|
|
70 </inputs>
|
|
|
71
|
|
|
72 <outputs>
|
|
|
73 <data format="bed" name="sig_regions" />
|
|
|
74 <collection name="list_output" type="list" description="GISTIC outputs">
|
|
|
75 <discover_datasets pattern="__name_and_ext__" directory="results"/>
|
|
|
76 </collection>
|
|
|
77 </outputs>
|
|
|
78
|
|
|
79 <help>
|
|
|
80
|
|
|
81 The GISTIC module identifies regions of the genome that are significantly amplified or deleted across a set of samples. Each aberration is assigned a G-score that considers the amplitude of the aberration as well as the frequency of its occurrence across samples. False Discovery Rate q-values are then calculated for the aberrant regions, and regions with q-values below a user-defined threshold are considered significant. For each significant region, a “peak region” is identified, which is the part of the aberrant region with greatest amplitude and frequency of alteration. In addition, a “wide peak” is determined using a leave-one-out algorithm to allow for errors in the boundaries in a single sample. The “wide peak” boundaries are more robust for identifying the most likely gene targets in the region. Each significantly aberrant region is also tested to determine whether it results primarily from broad events (longer than half a chromosome arm), focal events, or significant levels of both. The GISTIC module reports the genomic locations and calculated q-values for the aberrant regions. It identifies the samples that exhibit each significant amplification or deletion, and it lists genes found in each “wide peak” region.
|
|
|
82
|
|
|
83 </help>
|
|
|
84 <citations>
|
|
|
85 <citation type="bibtex">
|
|
|
86 @article {Albuquerque089631,
|
|
|
87 author = {Albuquerque, Marco A and Grande, Bruno M and Ritch, Elie and Jessa, Selin and Krzywinski, Martin I and Grewal, Jasleen and Shah, Sohrab and Boutros, Paul and Morin, Ryan},
|
|
|
88 title = {Enhancing Knowledge Discovery from Cancer Genomics Data with Galaxy},
|
|
|
89 year = {2016},
|
|
|
90 doi = {10.1101/089631},
|
|
|
91 publisher = {Cold Spring Harbor Labs Journals},
|
|
|
92 URL = {http://biorxiv.org/content/early/2016/11/26/089631},
|
|
|
93 eprint = {http://biorxiv.org/content/early/2016/11/26/089631.full.pdf},
|
|
|
94 journal = {bioRxiv}
|
|
|
95 }
|
|
|
96 </citation>
|
|
|
97
|
|
|
98 <citation type="bibtex">
|
|
|
99 @article{
|
|
|
100 goecks2010galaxy,
|
|
|
101 title={Galaxy: a comprehensive approach for supporting accessible, reproducible, and transparent computational research in the life sciences},
|
|
|
102 author={Goecks, Jeremy and Nekrutenko, Anton and Taylor, James and others},
|
|
|
103 journal={Genome Biol},
|
|
|
104 volume={11},
|
|
|
105 number={8},
|
|
|
106 pages={R86},
|
|
|
107 year={2010}
|
|
|
108 }
|
|
|
109 </citation>
|
|
|
110
|
|
|
111
|
|
|
112 <citation type="bibtex">
|
|
|
113 @article{
|
|
|
114 Schumacher2011gistic,
|
|
|
115 title={GISTIC2.0 facilitates sensitive and confident localization of the targets of focal somatic copy-number alteration in human cancers},
|
|
|
116 author={Mermel, Craig H and Schumacher, Steven E and Hill, Barbara and Meyerson, Matthew L and Beroukhim, Rameem and Getz, Gad},
|
|
|
117 journal={Genome Biol},
|
|
|
118 volume={12},
|
|
|
119 number={4},
|
|
|
120 pages={R41},
|
|
|
121 year={2011}
|
|
|
122 }
|
|
|
123 </citation>
|
|
|
124 </citations>
|
|
|
125 </tool>
|
