| export BIOCVERSION_REPOS=~/b/git/BiocVersion | |
| export BIOCMANAGER_REPOS=~/b/git/BiocManager | |
| export BIOCMANAGER_SANDBOX=/Users/ma38727/tmp/BiocManagerSandbox | |
| # | |
| # R-4.0 | |
| # | |
| echo "R-4.0" | |
| export R_LIBS_USER=$BIOCMANAGER_SANDBOX/R-4.0-Bioc-3.10 |
| ## package biocViews dumbbell | |
| library(BiocPkgTools) | |
| library(dplyr) | |
| library(tidyr) | |
| library(graph) | |
| library(biocViews) | |
| data(biocViewsVocab) |
| <!DOCTYPE html> | |
| <html lang="en"> | |
| <head> | |
| <script src="//cdnjs.cloudflare.com/ajax/libs/jquery/3.3.1/jquery.min.js"></script> | |
| <script src="//netdna.bootstrapcdn.com/bootstrap/3.3.7/js/bootstrap.min.js"></script> | |
| <script src="//cdnjs.cloudflare.com/ajax/libs/highlight.js/9.11.0/highlight.min.js"></script> | |
| <script src="//cdnjs.cloudflare.com/ajax/libs/highlight.js/9.11.0/languages/r.min.js"></script> | |
| <link rel="stylesheet" type="text/css" href="/static/lib/prism/prism.css"> |
| .host <- "localhost" | |
| .port <- 5001 | |
| library(httr) | |
| library(BiocParallel) | |
| .get <- | |
| function(fmt, ..., host = .host, port = .port) | |
| { | |
| query <- sprintf(fmt, host, port, ...) |
| 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) | |
| }, |
| 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) { |
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
| geneRanges <- | |
| function(db, column="ENTREZID") | |
| { | |
| g <- genes(db, columns=column) | |
| col <- mcols(g)[[column]] | |
| genes <- granges(g)[rep(seq_along(g), elementNROWS(col))] | |
| mcols(genes)[[column]] <- as.character(unlist(col)) | |
| genes | |
| } |
| #' 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 | |
| #' |
| .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) |