get_UTR3eSet {InPAS} | R Documentation |
generate a UTR3eSet object with PDUI information for statistic tests
get_UTR3eSet( sqlite_db, normalize = c("none", "quantiles", "quantiles.robust", "mean", "median"), ..., singleSample = FALSE )
sqlite_db |
A path to the SQLite database for InPAS, i.e. the output of
|
normalize |
A character(1) vector, spcifying the normalization method. It can be "none", "quantiles", "quantiles.robust", "mean", or "median" |
... |
parameter can be passed into
|
singleSample |
A logical(1) vector, indicating whether data is prepared for analysis in a singleSample mode? Default, FALSE |
An object of UTR3eSet which contains following elements: usage: an GenomicRanges::GRanges object with CP sites info. PDUI: a matrix of PDUI PDUI.log2: log2 transformed PDUI matrix short: a matrix of usage of short form long: a matrix of usage of long form if singleSample is TRUE, one more element, signals, will be included.
Jianhong Ou, Haibo Liu
if (interactive()) { library(BSgenome.Mmusculus.UCSC.mm10) library(TxDb.Mmusculus.UCSC.mm10.knownGene) genome <- BSgenome.Mmusculus.UCSC.mm10 TxDb <- TxDb.Mmusculus.UCSC.mm10.knownGene ## load UTR3 annotation and convert it into a GRangesList data(utr3.mm10) utr3 <- split(utr3.mm10, seqnames(utr3.mm10)) bedgraphs <- system.file("extdata",c("Baf3.extract.bedgraph", "UM15.extract.bedgraph"), package = "InPAS") tags <- c("Baf3", "UM15") metadata <- data.frame(tag = tags, condition = c("Baf3", "UM15"), bedgraph_file = bedgraphs) outdir = tempdir() write.table(metadata, file =file.path(outdir, "metadata.txt"), sep = "\t", quote = FALSE, row.names = FALSE) sqlite_db <- setup_sqlitedb(metadata = file.path(outdir, "metadata.txt"), outdir) coverage <- list() for (i in seq_along(bedgraphs)) { coverage[[tags[i]]] <- get_ssRleCov(bedgraph = bedgraphs[i], tag = tags[i], genome = genome, sqlite_db = sqlite_db, outdir = outdir, removeScaffolds = TRUE, BPPARAM = NULL)} coverage_files <- assemble_allCov(sqlite_db, outdir, genome, removeScaffolds = TRUE) data4CPsSearch <- setup_CPsSearch(sqlite_db, genome, utr3, background = "10K", TxDb = TxDb, removeScaffolds = TRUE, BPPARAM = NULL, hugeData = TRUE, outdir = outdir) ## polyA_PWM load(system.file("extdata", "polyA.rda", package = "InPAS")) ## load the Naive Bayes classifier model from the cleanUpdTSeq package library(cleanUpdTSeq) data(classifier) CPs <- search_CPs(seqname = "chr6", sqlite_db = sqlite_db, utr3 = utr3, background = data4CPsSearch$background, z2s = data4CPsSearch$z2s, depth.weight = data4CPsSearch$depth.weight, genome = genome, MINSIZE = 10, window_size = 100, search_point_START =50, search_point_END = NA, cutStart = 10, cutEnd = 0, adjust_distal_polyA_end = TRUE, coverage_threshold = 5, long_coverage_threshold = 2, PolyA_PWM = pwm, classifier = classifier, classifier_cutoff = 0.8, shift_range = 100, step = 5, two_way = FALSE, hugeData = TRUE, outdir = outdir) utr3_cds <- InPAS:::get_UTR3CDS(sqlite_db, chr.utr3 = utr3[["chr6"]], BPPARAM = NULL) utr3_cds_cov <- get_regionCov(chr.utr3 = utr3[["chr6"]], sqlite_db, outdir, BPPARAM = NULL, phmm = FALSE) eSet <- get_UTR3eSet(sqlite_db, normalize ="none", singleSample = FALSE) test_out <- test_dPDUI(eset = eSet, method = "fisher.exact", normalize = "none", sqlite_db = sqlite_db) }