# Connect to AnnotationHub
ah <- AnnotationHub()
# Access the Ensembl database for organism
ahDb <- query(ah,
pattern = c("Homo sapiens", "EnsDb"),
ignore.case = TRUE)
# Acquire the latest annotation files
id <- ahDb %>%
mcols() %>%
rownames() %>%
tail(n = 1)
# Download the appropriate Ensembldb database
edb <- ah[[id]]
# Extract gene-level information from database
annotations <- genes(edb,
return.type = "data.frame")
# Select annotations of interest
annotations <- annotations %>%
dplyr::select(gene_id, gene_name, seq_name, gene_biotype, description)
head(annotations)
gene_id gene_name seq_name gene_biotype
1 ENSG00000290825 DDX11L2 1 lncRNA
6 ENSG00000223972 DDX11L1 1 transcribed_unprocessed_pseudogene
7 ENSG00000227232 WASH7P 1 unprocessed_pseudogene
8 ENSG00000278267 MIR6859-1 1 miRNA
9 ENSG00000243485 MIR1302-2HG 1 lncRNA
10 ENSG00000284332 MIR1302-2 1 miRNA
description
1 DEAD/H-box helicase 11 like 2 (pseudogene) [Source:NCBI gene (formerly Entrezgene);Acc:84771]
6 DEAD/H-box helicase 11 like 1 (pseudogene) [Source:HGNC Symbol;Acc:HGNC:37102]
7 WASP family homolog 7, pseudogene [Source:HGNC Symbol;Acc:HGNC:38034]
8 microRNA 6859-1 [Source:HGNC Symbol;Acc:HGNC:50039]
9 MIR1302-2 host gene [Source:HGNC Symbol;Acc:HGNC:52482]
10 microRNA 1302-2 [Source:HGNC Symbol;Acc:HGNC:35294]