Created
May 22, 2025 23:20
-
-
Save tomsing1/63bd5f253b7802dcbfbce8748312c3b3 to your computer and use it in GitHub Desktop.
Downloading Ensembl GTF file, creating an SQlite file and accessing the database as an EnsDb object in R
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library(ensembldb) | |
# 1. retrieve the GTF file for Homo sapiens, Ensembl release 114 | |
kEnsemblRelease <- 114 | |
kUrl <- paste0("https://ftp.ensembl.org/pub/release-", kEnsemblRelease, | |
"/gtf/homo_sapiens/", | |
"Homo_sapiens.GRCh38.", kEnsemblRelease, ".gtf.gz") | |
gff_file <- file.path(tempdir(), basename(kUrl)) | |
download.file(kUrl, gff_file) | |
# 2. Parse the GTF file and create a SQLite database | |
sqlite_file <- tempfile(fileext = ".sqlite") | |
dbFile <- ensDbFromGtf(gff_file, outfile = sqlite_file, path = tempdir(), | |
organism = "Homo_sapiens", genomeVersion = "GRCh38", | |
version = ) | |
# 3. Access the SQLite database as an EnsDb object in R | |
edb <- EnsDb(dbFile) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment