| loadNamespace("rtracklayer") | |
| loadNamespace("XML") | |
| .organismToTaxid <- function(organism=character()) | |
| { | |
| ## query NCBI for taxonomy ID | |
| .eutils <- "http://eutils.ncbi.nlm.nih.gov/entrez/eutils" | |
| ## 1. ids | |
| uorganism <- unique(organism[!is.na(organism)]) |
| ## compatibility | |
| if (!exists("lengths")) | |
| lengths <- function(x) vapply(x, length, integer(1)) | |
| ## | |
| ## methods | |
| ## | |
| .S4methodsForClass <- |
| ## Imports: GEOquery, Biobase | |
| acc <- "GSE62944" | |
| if (!file.exists(acc)) | |
| GEOquery::getGEOSuppFiles(acc) | |
| setwd(acc) | |
| clinvar <- local({ | |
| message("clinvar") | |
| fl <- "GSE62944_TCGA_20_420_Clinical_Variables_7706_Samples.txt.gz" |
| library(Rsamtools) | |
| .cigarAlignInput <- | |
| function(file, param, what) | |
| { | |
| result <- readBamGappedAlignments(file, param=param) | |
| names(mcols(result))[names(mcols(result)) == what] <- "what" | |
| result | |
| } |
| library(shiny) | |
| library(org.Hs.eg.db) | |
| library(org.Mm.eg.db) | |
| library(org.Dm.eg.db) | |
| db <- c(Human="org.Hs.eg.db", Mouse="org.Mm.eg.db", | |
| Drosophila="org.Dm.eg.db") | |
| map <- lapply(db, function(elt) tryCatch({ | |
| library(elt, quietly=TRUE, character.only=TRUE) |
| .ascii_offset <- function() | |
| setNames(33:126 - 33L, strsplit(rawToChar(as.raw(33:126)), "")[[1]]) | |
| .phred2ascii_int <- | |
| function(x, scheme) | |
| { | |
| ## See https://en.wikipedia.org/wiki/FASTQ_format#Encoding | |
| ascii <- .ascii_offset() | |
| switch(scheme, "Illumina 1.8+" = { | |
| ## L - Illumina 1.8+ Phred+33, raw reads typically (0, 41) |
| #' Query DisGeNET disease / gene database | |
| #' | |
| #' Based on a script by jpinero@imim.es, retrieved from | |
| #' http://www.disgenet.org/ds/DisGeNET/scripts/disgenet.R on 7 April, | |
| #' 2016. This version is meant for interactive use within an R | |
| #' session, and makes a single query to DisGeNET rather than one query | |
| #' for each input symbol. | |
| #' | |
| #' @param input: character vector of gene or disease identifiers | |
| #' |
These functions are in response to StackOverflow questions like [this][], wanting to fill in missing NA values with preceeding values, optionally by group
fill_down <- function(v) {
if (length(v) > 1) {
keep <- c(TRUE, !is.na(v[-1]))
v[keep][cumsum(keep)]
} else v
| suppressPackageStartupMessages({ | |
| library(tibble) | |
| library(GenomicRanges) | |
| }) | |
| .g_range <- setClass("g_range", contains="GRanges") | |
| .g_columns <- c("chr", "start", "end", "strand") | |
| setAs("GRanges", "g_range", function(from) { |
| dna <- getFastaSeq() | |
| ## function for finding orfs. Returned as IRanges. | |
| ORFdef <- find_in_frame_ORFs(dna, longestORF = FALSE, minimumLength = 8) | |
| ORFdef <- ORFdef[lengths(ORFdef) > 0] | |
| ## Map (mapply) on each five prime leader | |
| uORFs <- Map( | |
| function(granges, tx_name, ORFdef) { | |
| map_granges(ORFdef, granges, tx_name) | |
| }, |