mtmorgan’s gists

mtmorgan / cigarAlign.R

Created November 13, 2012 17:32

Represent aligned DNA sequences as a DNAStringSet based on position and CIGAR

	library(Rsamtools)

	.cigarAlignInput <-
	function(file, param, what)
	{
	result <- readBamGappedAlignments(file, param=param)
	names(mcols(result))[names(mcols(result)) == what] <- "what"
	result
	}

mtmorgan / global.R

Created December 5, 2012 23:21

shiny AnnotationTable

	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)

mtmorgan / ucscAnnotateGenome.R

Created September 29, 2014 02:02

Retrieve UCSC genomes() and their latin bionomial by scraping UCSC web pages, and translate these to NCBI taxonomyId through entrez eutils calls

	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)])

mtmorgan / methods.R

Last active August 29, 2015 14:16

wrap methods() to report S3 and S4 methods for generic or class

	## compatibility

	if (!exists("lengths"))
	lengths <- function(x) vapply(x, length, integer(1))

	##
	## methods
	##

	.S4methodsForClass <-

mtmorgan / GSE62944_TCGA_Rusbread_featureCounts.R

Last active August 29, 2015 14:17

	## 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"

mtmorgan / readKallisto.R

Last active December 4, 2017 11:51

read kallisto RNA-seq quantification into R / Bioconductor data structures

	.require <-
	function(pkg)
	{
	withCallingHandlers({
	suppressPackageStartupMessages({
	require(pkg, character.only=TRUE, quietly=TRUE)
	})
	}, warning=function(w) {
	invokeRestart("muffleWarning")
	}) \|\| {

mtmorgan / gist:bd147505b89e42a151f9

Created June 24, 2015 18:54

dplyr / SummarizedExperiment compatibility layer -- half baked

	## dplyr compatibility

	as.data.frame.RangedSummarizedExperiment <-
	function(x, row.names=NULL, optional=FALSE, ...)
	{
	colData <- colData(x)
	rownames(colData) <- NULL
	cbind(as.data.frame(rowRanges(x)[as.vector(row(x))]),
	as.data.frame(colData[as.vector(col(x)),, drop=FALSE]),
	sapply(assays(x), as.vector))

mtmorgan / phred2ASCIIOffset.R

Created March 15, 2016 14:44

Translate integer or ASCII character fastq phred score encodings to integer offsets useful in Rsamtools

	.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)

mtmorgan / DisGeNET.R

Created April 7, 2016 09:04

Query DisGeNET disease / gene database from R

	#' Query DisGeNET disease / gene database
	#'
	#' Based on a script by [email protected], 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
	#'

mtmorgan / grangesToSymbol

Created July 29, 2016 20:50

Extract ranges of genes, and map ranges to corresponding genes

	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
	}

Martin Morgan mtmorgan