annotate minfi_dmr.xml @ 65:9ee05ae14aa5 draft

Uploaded
author kpbioteam
date Thu, 09 May 2019 10:15:17 -0400
parents 2ee6ac5227f1
children 1334312dc198
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
16
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
1 <tool id="minfi_dmr" name="Minfi DMR" version="@MINFI_VERSION@">
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
2 <description>to find differentially methylated regions</description>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
3 <macros>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
4 <import>macros.xml</import>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
5 </macros>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
6 <expand macro="requirements" />
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
7 <command detect_errors="exit_code">
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
8 <![CDATA[
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
9 Rscript '$minfi_dmr_script'
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
10 ]]>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
11 </command>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
12 <configfiles>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
13 <configfile name="minfi_dmr_script">
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
14 <![CDATA[
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
15 require("minfi", quietly = TRUE)
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
16 options(warn = -1)
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
17
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
18 GRSet <- get(load('$grset'))
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
19
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
20 pheno <- read.table('$phenotype_table',skip = 1)
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
21
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
22 group <- pheno\$V2
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
23
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
24 pair <- factor(pheno\$V3)
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
25
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
26 design.matrix <- model.matrix(~ group + pair)
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
27
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
28 maxGap <- as.numeric('$maxgap_size')
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
29
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
30 if(is.null(GRSet\$cluster)){
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
31 cluster = NULL
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
32 maxGap = maxGap
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
33 } else {
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
34 cluster = GRSet\$cluster
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
35 maxGap = NULL
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
36 }
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
37
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
38 cutoff <- as.numeric('$cutoff_size')
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
39 B <- as.numeric('$number_of_resamples')
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
40 nullMethod <- '$null_method'
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
41 coef <- 2
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
42
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
43 dmrs <- bumphunter(GRSet,
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
44 design = design.matrix,
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
45 cluster = cluster,
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
46 maxGap = maxGap,
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
47 cutoff = cutoff,
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
48 nullMethod = nullMethod,
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
49 B = B)
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
50
63
2ee6ac5227f1 Uploaded
kpbioteam
parents: 16
diff changeset
51 dmrGR <- dmrs\$table[,c(1,2,3)]
2ee6ac5227f1 Uploaded
kpbioteam
parents: 16
diff changeset
52 colnames(dmrGR) <- c("chr","start","end")
16
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
53
63
2ee6ac5227f1 Uploaded
kpbioteam
parents: 16
diff changeset
54 write.table(dmrGR, file= '$dmr', quote = FALSE,col.names = TRUE, row.names = FALSE, sep = "\t")
16
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
55 ]]>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
56 </configfile>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
57 </configfiles>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
58 <inputs>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
59 <param type="data" name="grset" format="rdata" label="Genomic Ratio Set" help="This class holds preprocessed data for Illumina methylation microarrays, mapped to a genomic
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
60 location." />
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
61 <param type="data" name="phenotype_table" format="tabular" label="Phenotype Table"
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
62 help="Phenotype Table must include the following information: sampleID, phenotype and paird or unpaired samples column"/>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
63 <param name="maxgap_size" type="integer" value="250" label="maxGap Size"
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
64 help="If cluster is not provided this maximum location gap will be used to define cluster"/>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
65 <param name="cutoff_size" type="float" value="0.1" label="Cutoff Size"
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
66 help="A numeric value. Values of the estimate of the genomic profile above the cutoff or below the negative of the cutoff will be used as candidate regions. It is possible to give two separate values (upper and lower bounds). If one value is given, the lower bound is minus the value."/>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
67 <param name="number_of_resamples" type="integer" value="0" label="Number of Resamples"
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
68 help="An integer denoting the number of resamples to use when computing null distributions. This defaults to 0. If permutations is supplied that defines the number of permutations/bootstraps and B is ignored."/>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
69 <param name="null_method" type="select" label="null Method" help="Method used to generate null candidate regions.">
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
70 <option value="permutation" selected="True">permutation</option>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
71 <option value="bootstrap">bootstrap</option>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
72 </param>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
73 </inputs>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
74 <outputs>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
75 <data name="dmr" format="interval" label="Differentially Methylated Regions"/>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
76 </outputs>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
77 <tests>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
78 <test>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
79 <param name="grset" value="GRSet_without_SNPs.rdata"/>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
80 <param name="phenotype_table" value="phenotypeTable.txt"/>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
81 <param name="maxgap_size" value="250"/>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
82 <param name="cutoff_size" value="0.1"/>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
83 <param name="number_of_resamples" value="0"/>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
84 <param name="null_method" value="permutation"/>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
85 <output name="dmr" file="Differentially_Methylated_Regions.interval"/>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
86 </test>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
87 </tests>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
88 <help><![CDATA[
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
89 Genomic Ratio Set should contain 450k arrays reads for each sample listed in Phenotype Table: sampleID phenotype paired e.g. GSM1588708 sensitive 1
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
90
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
91 This tool is a version of the bump hunting algorithm (Andrew E Jaffe et al. 2012) adapted to the 450k array finding find differentially methylated regions DMR.
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
92
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
93 The output is an interval file with the following columns:
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
94
63
2ee6ac5227f1 Uploaded
kpbioteam
parents: 16
diff changeset
95 - chr
16
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
96 - start
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
97 - end
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
98
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
99 ]]></help>
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
100 <expand macro="citations" />
491cf4ada3a3 Uploaded
kpbioteam
parents:
diff changeset
101 </tool>