tomsing1

#' Retrieve Reactome sets of Entrez identifiers for a selected species
#'
#' @param species Scalar character, the species of interest, e.g. `Homo sapiens`
#' @importFrom dplyr tbl right_join select collect mutate check_dbplyr
#' @importFrom glue glue_sql glue
#' @importFrom checkmate assert_choice
#' @export
#' @return A named list of Entrez identifiers
#' @examples
#' ReactomeSets("Mycobacterium tuberculosis")

tomsing1

library(limma)
library(AnnotationDbi)
library(GO.db)
library(org.Hs.eg.db)

# KEGG
kegg.names <- getKEGGPathwayNames("hsa", remove.qualifier = TRUE)
kegg.sets <- getGeneKEGGLinks("hsa", convert = TRUE)
kegg.gsc <- with(kegg.sets, split(GeneID, PathwayID))
names(kegg.gsc) <- kegg.names[

tomsing1

library(checkmate)
library(dplyr)
library(glue)
library(htmltidy)
library(httr)
library(purrr)
library(xml2)

# https://ena-docs.readthedocs.io/en/latest/submit/general-guide/accessions.html
identify_accession_type <- function(accessions) {

tomsing1

ENA APIs

The ENA has multiple APIs. The most important ones are:

1. ENA Portal API: search ENA's databases using (potentially complex) queries.
2. ENA Browser API: retrieve entire records programmatically

In addition, quick summaries of metadata and file retrieval locations can be retrieved

tomsing1

library(DiagrammeR)  # must be v 1.0.6.1 https://github.com/cynkra/dm/issues/823
library(dm)
library(RSQLite)

# download and decompress the chinook example SQLite database
zip_file <- tempfile(fileext = ".zip")
download.file(
  "https://www.sqlitetutorial.net/wp-content/uploads/2018/03/chinook.zip", 
  destfile = zip_file)
chinook <- unzip(zip_file, exdir = tempdir())

tomsing1

library(BSgenome.Hsapiens.UCSC.hg38)
library(Biostrings)
library(Rsubread)
library(GenomicRanges)
library(parallel)
library(GenomicAlignments)

kCores <- parallel::detectCores() - 1L
kQuery <- GRanges(seqnames = "chr12", IRanges(40263807, 40264221))

tomsing1

libraries = c("zellkonverter", "SingleCellExperiment")
for (lib in libraries) {
  suppressPackageStartupMessages(library(lib, character.only = TRUE,
                                         quietly = TRUE))
} 

# dummy SingleCellExperiment
ncells <- 100
u <- matrix(rpois(20000, 5), ncol = ncells)
v <- log2(u + 1)

tomsing1

libraries = c("basilisk", "mypackage", "zellkonverter",
              "SingleCellExperiment")
for (lib in libraries) {
  suppressPackageStartupMessages(library(lib, character.only = TRUE,
                                         quietly = TRUE))
} 

# create dummy SingleCellExperiment
ncells <- 100
u <- matrix(rpois(20000, 5), ncol = ncells)

tomsing1

#!/usr/bin/env bash

set -e
set -x
set -o pipefail

# This bash script retrieves SRA archives for a runs listed in the
# SRR_Acc_List.txt file (available from the SRA Run Selector).
#
# It requires:

tomsing1

#!/usr/bin/env bash

set -e
set -x
set -o pipefail

declare -r CORES=$(getconf _NPROCESSORS_ONLN)
declare -r REFERENCE="s3://your-reference-bucket/gencode/release_30/GRCh38_p12/"
declare -r S3_FASTQ="s3://your-bucket/Fastq/"
declare -r MIN_OVERLAP=10  # the larger the better