createSVMinput {SVM2CRM} | R Documentation |
Take the output of findFeatureOverlap and then create a positive and negative set of cis-regulatory elements
createSVMinput(inputpos,inputfull,label1,label2)
inputpos |
output of findFeatureOverlap (see documentation findFeatureOverlap) |
inputfull |
output of cisREfindbed (see documentation cisREfinbed) |
label1 |
a string to define the first class (e.g. enhancers) |
label2 |
a string to define the second class (e.g. not_enhancers) |
Some detailled description
A data.frame with the signals of the histone modifications for positive (e.g. enhancers) and negative (e.g. not_enhancers) examples.
Guidantonio Malagoli Tagliazucchi guidantonio.malagolitagliazucchi@unimore.it
findFeatureOverlap, cisREfindbed
library("SVM2CRMdata") library("GenomicRanges") setwd(system.file("data",package="SVM2CRMdata")) load("CD4_matrixInputSVMbin100window1000.rda") completeTABLE<-CD4_matrixInputSVMbin100window1000 new.strings<-gsub(x=colnames(completeTABLE[,c(6:ncol(completeTABLE))]),pattern="CD4.",replacement="") new.strings<-gsub(new.strings,pattern=".norm.w100.bed",replacement="") colnames(completeTABLE)[c(6:ncol(completeTABLE))]<-new.strings #list_file<-grep(dir(),pattern=".sort.txt",value=TRUE) #train_positive<-getSignal(list_file,chr="chr1",reference="p300.distal.fromTSS.txt",win.size=500,bin.size=100,label1="enhancers") #train_negative<-getSignal(list_file,chr="chr1",reference="random.region.hg18.nop300.txt",win.size=500,bin.size=100,label1="not_enhancers") setwd(system.file("data",package="SVM2CRMdata")) load("train_positive.rda") load("train_negative.rda") training_set<-rbind(train_positive,train_negative) colnames(training_set)[c(5:ncol(training_set))]<-gsub(x=gsub(x=colnames(training_set[,c(5:ncol(training_set))]),pattern="sort.txt.",replacement=""),pattern="CD4.",replacement="") setwd(system.file("extdata",package="SVM2CRMdata")) data_level2 <- read.table(file = "GSM393946.distal.p300fromTSS.txt",sep = "\t", stringsAsFactors = FALSE) data_level2<-data_level2[data_level2[,1]=="chr1",] DB <- data_level2[, c(1:3)] colnames(DB)<-c("chromosome","start","end") label <- "p300" table.final.overlap<-findFeatureOverlap(query=completeTABLE,subject=DB) data_enhancer_svm<-createSVMinput(inputpos=table.final.overlap,inputfull=completeTABLE,label1="enhancers",label2="not_enhancers")