annotate mutspecFilter.xml @ 1:748b7a8b634c draft

Uploaded
author iarc
date Thu, 21 Apr 2016 09:36:32 -0400
parents 8c682b3a7c5b
children 9d363eb081b5
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
1 <tool id="MutSpecfilter" name="MutSpec Filter" version="0.1" hidden="false">
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
2 <description>Filter out variants present in public databases</description>
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
3
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
4 <requirements>
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
5 <requirement type="set_environment">SCRIPT_PATH</requirement>
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
6 <requirement type="package" version="5.18.1">perl</requirement>
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
7 </requirements>
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
8
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
9 <command interpreter="perl">
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
10 mutspecFilter.pl
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
11 --dir \$SCRIPT_PATH
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
12 $segDup
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
13 $esp
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
14 $thG
1
748b7a8b634c Uploaded
iarc
parents: 0
diff changeset
15 #if $FilterdbSNP.dbSNP == True:
0
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
16 --dbSNP ${FilterdbSNP.column}
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
17 #else
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
18 --dbSNP 0
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
19 #end if
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
20 --refGenome ${refGenome}
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
21 --outfile $output
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
22 $input
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
23 </command>
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
24
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
25 <inputs>
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
26 <param name="input" type="data" format="txt" label="Input file"/>
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
27
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
28 <param name="refGenome" type="select" label="Reference genome" help="All your data should have been annotated with the selected genome">
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
29 <options from_data_table="annovar_index" />
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
30 </param>
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
31
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
32 <conditional name="FilterdbSNP">
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
33 <param name="dbSNP" type="boolean" checked="true" truevalue="true" label="Filter against dbSNP database" help="Remove variants with a RS number" />
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
34 <when value="true">
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
35 <param name="column" type="data_column" data_ref="input" label="Select the dbSNP column for filtering" use_header_names="true" help="Select a column name snp or snpNonFlagged" />
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
36 </when>
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
37 </conditional>
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
38
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
39
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
40 <param name="segDup" type="boolean" checked="true" truevalue="--segDup" falsevalue="" label="Filter against SegDup database" help="Remove variants present at &#62;= 0.9 frequency in the genomic duplicate segments database" />
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
41 <param name="esp" type="boolean" checked="true" truevalue="--esp" falsevalue="" label="Filter against the ESP database" help="Remove variants present at frequency &#62; 0.001 in the Exome Sequencing Project database (only valid for human genomes)" />
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
42 <param name="thG" type="boolean" checked="true" truevalue="--thG" falsevalue="" label="Filter against the 1000g database project" help="Remove variants present at frequency &#62; 0.001 in the 1000 genome database (only valid for human genomes)" />
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
43 </inputs>
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
44
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
45 <outputs>
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
46 <data type="data" name="output" format="tabular" label="${input.name.split(' ')[0]} filtered" />
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
47 </outputs>
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
48
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
49 <help>
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
50
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
51 **What it does**
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
52
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
53 Filter a file annotated with MutSpec-Annot tool. Variants present in public databases (dbSNP, SegDup, ESP, 1000 genome obtained from Annovar) will be removed from the input file (with frequency limits described above).
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
54
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
55 .. class:: warningmark
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
56
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
57 The databases ESP and 1000 genome can be used only for human genomes
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
58
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
59 --------------------------------------------------------------------------------------------------------------------------------------------------
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
60
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
61 **Input**
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
62
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
63 .. class:: warningmark
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
64
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
65 Tab delimited text files generated by MutSpec-Annot tool.
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
66
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
67 --------------------------------------------------------------------------------------------------------------------------------------------------
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
68
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
69 **Output**
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
70
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
71 Tab delimited text file filtered for variants considered as neutral polymorphisms.
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
72
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
73 --------------------------------------------------------------------------------------------------------------------------------------------------
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
74
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
75 **Example**
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
76
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
77 Filter the following file::
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
78
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
79 Chr Start End Ref Alt Func.refGene Gene.refGene ExonicFunc.refGene AAChange.refGene genomicSuperDups snp138 1000g2014oct_all esp6500si_all Strand context Chromosome Start_Position End_Position Reference_Allele Tumor_Seq_Allele2
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
80 chr7 121717919 121717920 - G exonic AASS frameshift insertion AASS:NM_005763:exon23:c.2634dupC:p.A879fs NA rs147476318 NA NA - GCG chr7 121717919 121717920 - G
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
81 chr1 230846235 230846235 T A exonic AGT nonsynonymous SNV AGT:NM_000029:exon2:c.A362T:p.H121L NA NA NA NA - GTG chr1 230846235 230846235 T A
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
82 chr14 33290999 33290999 A G exonic AKAP6 nonsynonymous SNV AKAP6:NM_004274:exon13:c.A3980G:p.D1327G NA NA NA NA + GAC chr14 33290999 33290999 A G
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
83 chr12 8082458 8082458 C T exonic SLC2A3 nonsynonymous SNV SLC2A3:NM_006931:exon6:c.G683A:p.R228Q NA rs200481428 0.000199681 NA - CCG chr12 8082458 8082458 C T
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
84 chr4 70156391 70156391 T C exonic UGT2B28 nonsynonymous SNV UGT2B28:NM_053039:exon5:c.T1172C:p.V391A score=0.949699;Name=chr4:70035680 NA 0.000199681 NA + GTA chr4 70156391 70156391 T C
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
85
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
86 Will produce::
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
87
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
88 Chr Start End Ref Alt Func.refGene Gene.refGene ExonicFunc.refGene AAChange.refGene genomicSuperDups snp138 1000g2014oct_all esp6500si_all Strand context Chromosome Start_Position End_Position Reference_Allele Tumor_Seq_Allele2
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
89 chr1 230846235 230846235 T A exonic AGT nonsynonymous SNV AGT:NM_000029:exon2:c.A362T:p.H121L NA NA NA NA - GTG chr1 230846235 230846235 T A
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
90 chr14 33290999 33290999 A G exonic AKAP6 nonsynonymous SNV AKAP6:NM_004274:exon13:c.A3980G:p.D1327G NA NA NA NA + GAC chr14 33290999 33290999 A G
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
91 chr4 70156391 70156391 T C exonic UGT2B28 nonsynonymous SNV UGT2B28:NM_053039:exon5:c.T1172C:p.V391A score=0.949699;Name=chr4:70035680 NA 0.000199681 NA + GTA chr4 70156391 70156391 T C
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
92
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
93
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
94
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
95 </help>
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
96
1
748b7a8b634c Uploaded
iarc
parents: 0
diff changeset
97 <citations>
748b7a8b634c Uploaded
iarc
parents: 0
diff changeset
98 <citation type="bibtex">
748b7a8b634c Uploaded
iarc
parents: 0
diff changeset
99 @ARTICLE{ardin_mutspec:_2016,
748b7a8b634c Uploaded
iarc
parents: 0
diff changeset
100 author = {Ardin et al},
748b7a8b634c Uploaded
iarc
parents: 0
diff changeset
101 keywords = {Galaxy, Mutation signatures, Mutation spectra, Single base substitutions},
748b7a8b634c Uploaded
iarc
parents: 0
diff changeset
102 title = {{MutSpec}: a Galaxy toolbox for streamlined analyses of somatic mutation spectra in human and mouse cancer genomes},
748b7a8b634c Uploaded
iarc
parents: 0
diff changeset
103 url = {http://bmcbioinformatics.biomedcentral.com/articles/10.1186/s12859-016-1011-z}
748b7a8b634c Uploaded
iarc
parents: 0
diff changeset
104 }
748b7a8b634c Uploaded
iarc
parents: 0
diff changeset
105 </citation>
748b7a8b634c Uploaded
iarc
parents: 0
diff changeset
106 </citations>
748b7a8b634c Uploaded
iarc
parents: 0
diff changeset
107
0
8c682b3a7c5b Uploaded
iarc
parents:
diff changeset
108 </tool>