The zenith
package
builds on EnrichmentBrowser
to provde access to a range of gene set databases. Genesets can take ~1
min to download and load the first time. They are automatically cached
on disk, so loading the second time takes just a second.
Here are some shortcuts to load common databases:
library(zenith)
## MSigDB as ENSEMBL genes
# all genesets in MSigDB
gs.msigdb = get_MSigDB()
# only Hallmark gene sets
gs = get_MSigDB('H')
# only C1
gs = get_MSigDB('C1')
# C1 and C2
gs = get_MSigDB(c('C1', 'C2'))
# C1 as gene SYMBOL
gs = get_MSigDB('C1', to="SYMBOL")
# C1 as gene ENTREZ
gs = get_MSigDB('C1', to="ENTREZ")
## Gene Ontology
gs.go = get_GeneOntology()
# load Biological Process and gene SYMBOL
gs.go = get_GeneOntology("BP", to="SYMBOL")
EnrichmentBrowser provides additional databases (i.e. KEGG, Enrichr), alternate gene identifiers (i.e. ENSEMBL, ENTREZ) or species (i.e. hsa, mmu)
library(EnrichmentBrowser)
# KEGG
gs.kegg = getGenesets(org = "hsa",
db = "kegg",
gene.id.type = "ENSEMBL",
return.type = "GeneSetCollection")
## ENRICHR resource
# provides many additional gene set databases
df = showAvailableCollections( org = "hsa", db = "enrichr")
head(df)
# Allen_Brain_Atlas_10x_scRNA_2021
gs.allen = getGenesets( org = "hsa",
db = "enrichr",
lib = "Allen_Brain_Atlas_10x_scRNA_2021",
gene.id.type = "ENSEMBL",
return.type = "GeneSetCollection")