R/writerfunctions.R
In Mathelab/ALTRE: Workflow for Identifying Regulatory Elements from Chromatin Accessibility Assay Data
#' Writes annotated genomic regions
#'
#' Creates a CSV file with genomic regions annoted as TSS-proximal and TSS-distal regions.
#' categorized by cell type
#'
#' @param countsPeaks output generated from getCounts()
#' @param con connection filepath
#'
#' @examples
#' \dontrun{
#' csvfile <- file.path(dir="yourfilepath", 'sampleinfo.csv')
#' sampleinfo <- loadCSVFile(csvfile)
#' samplePeaks <- loadBedFiles(sampleinfo)
#' consPeaks <- getConsensusPeaks(samplepeaks=samplePeaks,minreps=2)
#' TSSannot <- getTSS()
#' consPeaksAnnotated <- combineAnnotatePeaks(conspeaks = consPeaks,
#' TSS = TSSannot,
#' merge = TRUE,
#' regionspecific = TRUE,
#' distancefromTSSdist = 1500,
#' distancefromTSSprox = 1000 )
#' con <- "annotatedRegions.csv"
#' writeConsensusRE(consPeaksAnnotated, con)
#' }
#' @export
writeConsensusRE <- function(countsPeaks, con) {
annotatedRegions <- GenomicRanges::as.data.frame(
countsPeaks$consPeaksAnnotated)
readr::write_csv(annotatedRegions, con)
}
#' Creates a custom track for visualization on genome browser
#'
#' Creates a color-coded BED file for visualization of peaks and their ALTRE
#' categories in a genome browser: red indicates increased log2fold change/low
#' p-value, blue indicates decreased lod2fold change/low p-value, and purple
#' indicates regions with little to no change and insignificant p-values.
#' Based on the log2fold change and p-value inputs, there is a possibility that
#' some regions will not fulfill any of the supplied criteria
#' ("in-between" shared and type-specific). They are colored grey.
#'
#' @param analysisresults output generated from categAltrePeaks()
#' @param con connection
#'
#' @examples
#' \dontrun{
#' csvfile <- file.path(dir="yourfilepath", 'sampleinfo.csv')
#' sampleinfo <- loadCSVFile(csvfile)
#' samplePeaks <- loadBedFiles(sampleinfo)
#' consPeaks <- getConsensusPeaks(samplepeaks=samplePeaks,minreps=2)
#' TSSannot <- getTSS()
#' consPeaksAnnotated <- combineAnnotatePeaks(conspeaks = consPeaks,
#' TSS = TSSannot,
#' merge = TRUE,
#' regionspecific = TRUE,
#' distancefromTSSdist = 1500,
#' distancefromTSSprox = 1000)
#' #Need to run getcounts on all chromosomes
#' counts_consPeaks <- getcounts(annotpeaks = consPeaksAnnotated,
#' csvfile = csvfile,
#' reference = 'SAEC')
#' altre_peaks <- countanalysis(counts = counts_consPeaks,
#' pval = 0.01,
#' lfcvalue = 1)
#' categaltre_peaks <- categAltrePeaks(altre_peaks, lfctypespecific = 1.5,
#' lfcshared = 1.2, pvaltypespecific = 0.01, pvalshared = 0.05)
#' writeBedFile(categaltre_peaks)
#' }
#' @export
writeBedFile <-
function(analysisresults, con) {
analysisresults <- analysisresults[[1]]
if (is.data.frame(analysisresults) == FALSE) {
stop("The input for the analysisresults arguement is not a dataframe!")
}
colors <- c("grey", "salmon", "green", "blue")
mycol <- analysisresults$REaltrecateg
mycol[which(mycol == "Ambiguous")] <-
paste(as.numeric(grDevices::col2rgb(colors[1])),
sep = ",",
collapse = ",")
mycol[which(mycol == "Shared")] <-
paste(as.numeric(grDevices::col2rgb(colors[2])),
sep = ",",
collapse = ",")
mycol[which(mycol == "Reference Specific")] <-
paste(as.numeric(grDevices::col2rgb(colors[3])),
sep = ",",
collapse = ",")
mycol[which(mycol == "Experiment Specific")] <-
paste(as.numeric(grDevices::col2rgb(colors[4])),
sep = ",",
collapse = ",")
bedfile <- data.frame(
chrom = analysisresults$chr,
chromStart = analysisresults$start,
chromEnd = analysisresults$stop,
name = paste0("peak", 1:nrow(analysisresults)),
score = "0",
strand = "+",
thickStart = ".",
thickEnd = ".",
itemRgb = mycol
)
header <-
'track name=ALTREtrack description="ALTRE categories" visibility=2 itemRgb="On"'
utils::write.table(
header,
file = con,
row.names = FALSE,
col.names = FALSE,
quote = FALSE
)
utils::write.table(
bedfile,
file = con,
row.names = FALSE,
col.names = FALSE,
append = TRUE,
quote = FALSE,
sep = "\t"
)
}
#' Writes a data table generated by comparePeaksAltre
#'
#' Creates a CSV file with the number of peaks called as experiment- or
#' reference-specific and shared using the quantitative/peak intensity or
#' peak/binary approach.
#'
#' @param comparePeaksOut output generated from comparePeaksAltre()
#' @param con connection filepath
#'
#' @examples
#' \dontrun{
#' csvfile <- file.path(dir="yourfilepath", 'sampleinfo.csv')
#' sampleinfo <- loadCSVFile(csvfile)
#' samplePeaks <- loadBedFiles(sampleinfo)
#' consPeaks <- getConsensusPeaks(samplepeaks=samplePeaks,minreps=2)
#' TSSannot <- getTSS()
#' consPeaksAnnotated <- combineAnnotatePeaks(conspeaks = consPeaks,
#' TSS = TSSannot,
#' merge = TRUE,
#' regionspecific = TRUE,
#' distancefromTSSdist = 1500,
#' distancefromTSSprox = 1000)
#' #Need to run getcounts on all chromosomes
#' counts_consPeaks <- getcounts(annotpeaks = consPeaksAnnotated,
#' csvfile = csvfile,
#' reference = 'SAEC')
#' #' altre_peaks <- countanalysis(counts = counts_consPeaks,
#' pval = 0.01,
#' lfcvalue = 1)
#' categaltre_peaks <- categAltrePeaks(altre_peaks,
#' lfctypespecific = 1.5,
#' lfcshared = 1.2,
#' pvaltypespecific = 0.01,
#' pvalshared = 0.05)
#' comparePeaksOut <- comparePeaksAltre(categaltre_peaks, reference= 'SAEC')
#' con <- "datatableRE.csv"
#' writeCompareRE(comparePeaksOut, con)
#'
#' }
#' @export
writeCompareRE <-
function(comparePeaksOut, con) {
fileOut <- tibble::rownames_to_column(as.data.frame(comparePeaksOut[[1]]))
readr::write_csv(fileOut, con)
}
#### Writes a data generated by pathenrich
####
#### Creates three CSV files containing the results of the pathway enrichment analysis for
#### experiment-specific, reference-specific, and shared REs.
####
#### @param pathenrichOut output generated from pathenrich()
#### @param con connection filepath
####
#### @examples
#### \dontrun{
#### csvfile <- file.path(dir="yourfilepath", 'sampleinfo.csv')
#### sampleinfo <- loadCSVFile(csvfile)
#### samplePeaks <- loadBedFiles(sampleinfo)
#### consPeaks <- getConsensusPeaks(samplepeaks=samplePeaks,minreps=2)
#### TSSannot <- getTSS()
#### consPeaksAnnotated <- combineAnnotatePeaks(conspeaks = consPeaks,
#### TSS = TSSannot,
#### merge = TRUE,
#### regionspecific = TRUE,
#### distancefromTSSdist = 1500,
#### distancefromTSSprox = 1000)
#### #Need to run getcounts on all chromosomes
#### counts_consPeaks <- getcounts(annotpeaks = consPeaksAnnotated,
#### csvfile = csvfile,
#### reference = 'SAEC')
#### #' altre_peaks <- countanalysis(counts = counts_consPeaks,
#### pval = 0.01,
#### lfcvalue = 1)
#### categaltre_peaks <- categAltrePeaks(altre_peaks,
#### lfctypespecific = 1.5,
#### lfcshared = 1.2,
#### pvaltypespecific = 0.01,
#### pvalshared = 0.05)
#### callGREAT <- runGREAT(peaks=categaltre_peaks)
####pathGREAT <- processPathways(callGREAT)
#### con <- "GREAToutput.zip"
#### writeGREATpathExcell(pathenrichOut = pathGREAT, con = con)
#### }
####
###
###writeGREATpathExcell <-
### function(pathenrichOut, con) {
###
### listNames <- names(pathenrichOut)
### pathNames <- names(pathenrichOut[[1]]$Sig_Pathways)
### fileExt <- tools::file_ext(con)
### fileCon <- stringr::str_replace(con,
### fileExt ,
### stringr::str_c(listNames,
### "xlsx",
### sep = "."))
###
### for(i in 1:length(pathNames)) {
### xlsx::write.xlsx(pathenrichOut[[1]]$Sig_Pathways[[i]],file=fileCon[[1]],
### sheetName=pathNames[i],append=TRUE,row.names=FALSE)
### }
###
### for(files in 2:length(fileCon)) {
### for(i in 1:length(pathNames)) {
### xlsx::write.xlsx(pathenrichOut[[files]]$Sig_Pathways[[i]],
### file=fileCon[[files]],
### sheetName=pathNames[i],append=TRUE, row.names=FALSE)
### }
### }
###
### utils::zip(zipfile = con, files = fileCon)
### #if(file.exists(con)) {
### # file.rename(paste0(con, ".zip"), con)}
### #tar(pathenrichOut,fileCon)
### }
#' Writes a data generated by pathenrich
#'
#' Creates three CSV files containing the results of the pathway enrichment analysis for
#' experiment-specific, reference-specific, and shared REs.
#'
#' @param pathenrichOut output generated from pathenrich()
#' @param con connection filepath
#'
#' @examples
#' \dontrun{
#' csvfile <- file.path(dir="yourfilepath", 'sampleinfo.csv')
#' sampleinfo <- loadCSVFile(csvfile)
#' samplePeaks <- loadBedFiles(sampleinfo)
#' consPeaks <- getConsensusPeaks(samplepeaks=samplePeaks,minreps=2)
#' TSSannot <- getTSS()
#' consPeaksAnnotated <- combineAnnotatePeaks(conspeaks = consPeaks,
#' TSS = TSSannot,
#' merge = TRUE,
#' regionspecific = TRUE,
#' distancefromTSSdist = 1500,
#' distancefromTSSprox = 1000)
#' #Need to run getcounts on all chromosomes
#' counts_consPeaks <- getcounts(annotpeaks = consPeaksAnnotated,
#' csvfile = csvfile,
#' reference = 'SAEC')
#' #' altre_peaks <- countanalysis(counts = counts_consPeaks,
#' pval = 0.01,
#' lfcvalue = 1)
#' categaltre_peaks <- categAltrePeaks(altre_peaks,
#' lfctypespecific = 1.5,
#' lfcshared = 1.2,
#' pvaltypespecific = 0.01,
#' pvalshared = 0.05)
#' callGREAT <- runGREAT(peaks=categaltre_peaks)
#' pathGREAT <- processPathways(callGREAT)
#' con <- "GREAToutput.zip"
#' writeGREATpath(pathenrichOut = pathGREAT, con = con)
#' }
#'
#' @export
writeGREATpath <- function(pathenrichOut, con) {
listNames <- names(pathenrichOut)
pathNames <- names(pathenrichOut[[1]]$Sig_Pathways)
# fileNames <- as.character(unlist(lapply(listNames,
# function(x)
# paste(x,
# pathNames,
# sep = "_"))))
fileExt <- tools::file_ext(con)
allfiles = c()
for (l in listNames) {
for (p in pathNames) {
fileCon <- stringr::str_replace(con,
fileExt,
stringr::str_c(paste(l, p, sep = "_"),
"csv", sep = "."))
message(paste("Writing", fileCon))
readr::write_csv(pathenrichOut[[l]]$Sig_Pathways[[p]], fileCon)
allfiles <- c(allfiles, fileCon)
}
}
utils::zip(zipfile = con, files = allfiles)
#if(file.exists(con)) {
# file.rename(paste0(con, ".zip"), con)}
#tar(pathenrichOut,fileCon)
}
Mathelab/ALTRE documentation built on May 7, 2019, 3:41 p.m.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
#' Writes annotated genomic regions
#'
#' Creates a CSV file with genomic regions annoted as TSS-proximal and TSS-distal regions.
#' categorized by cell type
#'
#' @param countsPeaks output generated from getCounts()
#' @param con connection filepath
#'
#' @examples
#' \dontrun{
#' csvfile <- file.path(dir="yourfilepath", 'sampleinfo.csv')
#' sampleinfo <- loadCSVFile(csvfile)
#' samplePeaks <- loadBedFiles(sampleinfo)
#' consPeaks <- getConsensusPeaks(samplepeaks=samplePeaks,minreps=2)
#' TSSannot <- getTSS()
#' consPeaksAnnotated <- combineAnnotatePeaks(conspeaks = consPeaks,
#' TSS = TSSannot,
#' merge = TRUE,
#' regionspecific = TRUE,
#' distancefromTSSdist = 1500,
#' distancefromTSSprox = 1000 )
#' con <- "annotatedRegions.csv"
#' writeConsensusRE(consPeaksAnnotated, con)
#' }
#' @export
writeConsensusRE <- function(countsPeaks, con) {
annotatedRegions <- GenomicRanges::as.data.frame(
countsPeaks$consPeaksAnnotated)
readr::write_csv(annotatedRegions, con)
}
#' Creates a custom track for visualization on genome browser
#'
#' Creates a color-coded BED file for visualization of peaks and their ALTRE
#' categories in a genome browser: red indicates increased log2fold change/low
#' p-value, blue indicates decreased lod2fold change/low p-value, and purple
#' indicates regions with little to no change and insignificant p-values.
#' Based on the log2fold change and p-value inputs, there is a possibility that
#' some regions will not fulfill any of the supplied criteria
#' ("in-between" shared and type-specific). They are colored grey.
#'
#' @param analysisresults output generated from categAltrePeaks()
#' @param con connection
#'
#' @examples
#' \dontrun{
#' csvfile <- file.path(dir="yourfilepath", 'sampleinfo.csv')
#' sampleinfo <- loadCSVFile(csvfile)
#' samplePeaks <- loadBedFiles(sampleinfo)
#' consPeaks <- getConsensusPeaks(samplepeaks=samplePeaks,minreps=2)
#' TSSannot <- getTSS()
#' consPeaksAnnotated <- combineAnnotatePeaks(conspeaks = consPeaks,
#' TSS = TSSannot,
#' merge = TRUE,
#' regionspecific = TRUE,
#' distancefromTSSdist = 1500,
#' distancefromTSSprox = 1000)
#' #Need to run getcounts on all chromosomes
#' counts_consPeaks <- getcounts(annotpeaks = consPeaksAnnotated,
#' csvfile = csvfile,
#' reference = 'SAEC')
#' altre_peaks <- countanalysis(counts = counts_consPeaks,
#' pval = 0.01,
#' lfcvalue = 1)
#' categaltre_peaks <- categAltrePeaks(altre_peaks, lfctypespecific = 1.5,
#' lfcshared = 1.2, pvaltypespecific = 0.01, pvalshared = 0.05)
#' writeBedFile(categaltre_peaks)
#' }
#' @export
writeBedFile <-
function(analysisresults, con) {
analysisresults <- analysisresults[[1]]
if (is.data.frame(analysisresults) == FALSE) {
stop("The input for the analysisresults arguement is not a dataframe!")
}
colors <- c("grey", "salmon", "green", "blue")
mycol <- analysisresults$REaltrecateg
mycol[which(mycol == "Ambiguous")] <-
paste(as.numeric(grDevices::col2rgb(colors[1])),
sep = ",",
collapse = ",")
mycol[which(mycol == "Shared")] <-
paste(as.numeric(grDevices::col2rgb(colors[2])),
sep = ",",
collapse = ",")
mycol[which(mycol == "Reference Specific")] <-
paste(as.numeric(grDevices::col2rgb(colors[3])),
sep = ",",
collapse = ",")
mycol[which(mycol == "Experiment Specific")] <-
paste(as.numeric(grDevices::col2rgb(colors[4])),
sep = ",",
collapse = ",")
bedfile <- data.frame(
chrom = analysisresults$chr,
chromStart = analysisresults$start,
chromEnd = analysisresults$stop,
name = paste0("peak", 1:nrow(analysisresults)),
score = "0",
strand = "+",
thickStart = ".",
thickEnd = ".",
itemRgb = mycol
)
header <-
'track name=ALTREtrack description="ALTRE categories" visibility=2 itemRgb="On"'
utils::write.table(
header,
file = con,
row.names = FALSE,
col.names = FALSE,
quote = FALSE
)
utils::write.table(
bedfile,
file = con,
row.names = FALSE,
col.names = FALSE,
append = TRUE,
quote = FALSE,
sep = "\t"
)
}
#' Writes a data table generated by comparePeaksAltre
#'
#' Creates a CSV file with the number of peaks called as experiment- or
#' reference-specific and shared using the quantitative/peak intensity or
#' peak/binary approach.
#'
#' @param comparePeaksOut output generated from comparePeaksAltre()
#' @param con connection filepath
#'
#' @examples
#' \dontrun{
#' csvfile <- file.path(dir="yourfilepath", 'sampleinfo.csv')
#' sampleinfo <- loadCSVFile(csvfile)
#' samplePeaks <- loadBedFiles(sampleinfo)
#' consPeaks <- getConsensusPeaks(samplepeaks=samplePeaks,minreps=2)
#' TSSannot <- getTSS()
#' consPeaksAnnotated <- combineAnnotatePeaks(conspeaks = consPeaks,
#' TSS = TSSannot,
#' merge = TRUE,
#' regionspecific = TRUE,
#' distancefromTSSdist = 1500,
#' distancefromTSSprox = 1000)
#' #Need to run getcounts on all chromosomes
#' counts_consPeaks <- getcounts(annotpeaks = consPeaksAnnotated,
#' csvfile = csvfile,
#' reference = 'SAEC')
#' #' altre_peaks <- countanalysis(counts = counts_consPeaks,
#' pval = 0.01,
#' lfcvalue = 1)
#' categaltre_peaks <- categAltrePeaks(altre_peaks,
#' lfctypespecific = 1.5,
#' lfcshared = 1.2,
#' pvaltypespecific = 0.01,
#' pvalshared = 0.05)
#' comparePeaksOut <- comparePeaksAltre(categaltre_peaks, reference= 'SAEC')
#' con <- "datatableRE.csv"
#' writeCompareRE(comparePeaksOut, con)
#'
#' }
#' @export
writeCompareRE <-
function(comparePeaksOut, con) {
fileOut <- tibble::rownames_to_column(as.data.frame(comparePeaksOut[[1]]))
readr::write_csv(fileOut, con)
}
#### Writes a data generated by pathenrich
####
#### Creates three CSV files containing the results of the pathway enrichment analysis for
#### experiment-specific, reference-specific, and shared REs.
####
#### @param pathenrichOut output generated from pathenrich()
#### @param con connection filepath
####
#### @examples
#### \dontrun{
#### csvfile <- file.path(dir="yourfilepath", 'sampleinfo.csv')
#### sampleinfo <- loadCSVFile(csvfile)
#### samplePeaks <- loadBedFiles(sampleinfo)
#### consPeaks <- getConsensusPeaks(samplepeaks=samplePeaks,minreps=2)
#### TSSannot <- getTSS()
#### consPeaksAnnotated <- combineAnnotatePeaks(conspeaks = consPeaks,
#### TSS = TSSannot,
#### merge = TRUE,
#### regionspecific = TRUE,
#### distancefromTSSdist = 1500,
#### distancefromTSSprox = 1000)
#### #Need to run getcounts on all chromosomes
#### counts_consPeaks <- getcounts(annotpeaks = consPeaksAnnotated,
#### csvfile = csvfile,
#### reference = 'SAEC')
#### #' altre_peaks <- countanalysis(counts = counts_consPeaks,
#### pval = 0.01,
#### lfcvalue = 1)
#### categaltre_peaks <- categAltrePeaks(altre_peaks,
#### lfctypespecific = 1.5,
#### lfcshared = 1.2,
#### pvaltypespecific = 0.01,
#### pvalshared = 0.05)
#### callGREAT <- runGREAT(peaks=categaltre_peaks)
####pathGREAT <- processPathways(callGREAT)
#### con <- "GREAToutput.zip"
#### writeGREATpathExcell(pathenrichOut = pathGREAT, con = con)
#### }
####
###
###writeGREATpathExcell <-
### function(pathenrichOut, con) {
###
### listNames <- names(pathenrichOut)
### pathNames <- names(pathenrichOut[[1]]$Sig_Pathways)
### fileExt <- tools::file_ext(con)
### fileCon <- stringr::str_replace(con,
### fileExt ,
### stringr::str_c(listNames,
### "xlsx",
### sep = "."))
###
### for(i in 1:length(pathNames)) {
### xlsx::write.xlsx(pathenrichOut[[1]]$Sig_Pathways[[i]],file=fileCon[[1]],
### sheetName=pathNames[i],append=TRUE,row.names=FALSE)
### }
###
### for(files in 2:length(fileCon)) {
### for(i in 1:length(pathNames)) {
### xlsx::write.xlsx(pathenrichOut[[files]]$Sig_Pathways[[i]],
### file=fileCon[[files]],
### sheetName=pathNames[i],append=TRUE, row.names=FALSE)
### }
### }
###
### utils::zip(zipfile = con, files = fileCon)
### #if(file.exists(con)) {
### # file.rename(paste0(con, ".zip"), con)}
### #tar(pathenrichOut,fileCon)
### }
#' Writes a data generated by pathenrich
#'
#' Creates three CSV files containing the results of the pathway enrichment analysis for
#' experiment-specific, reference-specific, and shared REs.
#'
#' @param pathenrichOut output generated from pathenrich()
#' @param con connection filepath
#'
#' @examples
#' \dontrun{
#' csvfile <- file.path(dir="yourfilepath", 'sampleinfo.csv')
#' sampleinfo <- loadCSVFile(csvfile)
#' samplePeaks <- loadBedFiles(sampleinfo)
#' consPeaks <- getConsensusPeaks(samplepeaks=samplePeaks,minreps=2)
#' TSSannot <- getTSS()
#' consPeaksAnnotated <- combineAnnotatePeaks(conspeaks = consPeaks,
#' TSS = TSSannot,
#' merge = TRUE,
#' regionspecific = TRUE,
#' distancefromTSSdist = 1500,
#' distancefromTSSprox = 1000)
#' #Need to run getcounts on all chromosomes
#' counts_consPeaks <- getcounts(annotpeaks = consPeaksAnnotated,
#' csvfile = csvfile,
#' reference = 'SAEC')
#' #' altre_peaks <- countanalysis(counts = counts_consPeaks,
#' pval = 0.01,
#' lfcvalue = 1)
#' categaltre_peaks <- categAltrePeaks(altre_peaks,
#' lfctypespecific = 1.5,
#' lfcshared = 1.2,
#' pvaltypespecific = 0.01,
#' pvalshared = 0.05)
#' callGREAT <- runGREAT(peaks=categaltre_peaks)
#' pathGREAT <- processPathways(callGREAT)
#' con <- "GREAToutput.zip"
#' writeGREATpath(pathenrichOut = pathGREAT, con = con)
#' }
#'
#' @export
writeGREATpath <- function(pathenrichOut, con) {
listNames <- names(pathenrichOut)
pathNames <- names(pathenrichOut[[1]]$Sig_Pathways)
# fileNames <- as.character(unlist(lapply(listNames,
# function(x)
# paste(x,
# pathNames,
# sep = "_"))))
fileExt <- tools::file_ext(con)
allfiles = c()
for (l in listNames) {
for (p in pathNames) {
fileCon <- stringr::str_replace(con,
fileExt,
stringr::str_c(paste(l, p, sep = "_"),
"csv", sep = "."))
message(paste("Writing", fileCon))
readr::write_csv(pathenrichOut[[l]]$Sig_Pathways[[p]], fileCon)
allfiles <- c(allfiles, fileCon)
}
}
utils::zip(zipfile = con, files = allfiles)
#if(file.exists(con)) {
# file.rename(paste0(con, ".zip"), con)}
#tar(pathenrichOut,fileCon)
}
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Embedding an R snippet on your website
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.