This function uses AnnotationHub to obtain the objects provided by this
package. These are: the TxDb object made with gencode_txdb(), the
annotated genes object made with gencode_annotated_genes() or the
GenomicState object made with gencode_genomic_state().
GenomicStateHub(
version = "31",
genome = c("hg38", "hg19"),
filetype = c("TxDb", "AnnotatedGenes", "GenomicState"),
ah = AnnotationHub::AnnotationHub()
)A character(1) with the Gencode version number.
A character(1) with the human genome version number. Valid
options are 'hg38' or 'hg19'.
A character() with either TxDb, AnnotatedGenes or
GenomicState.
An AnnotationHub object
AnnotationHub-class.
The AnnotationHub-class query for the file you requested.
## Query AnnotationHub for the GenomicState object for Gencode v31 on
## hg19 coordinates
hub_query_gs_gencode_v31_hg19 <- GenomicStateHub(
version = "31",
genome = "hg19",
filetype = "GenomicState"
)
hub_query_gs_gencode_v31_hg19
#> AnnotationHub with 1 record
#> # snapshotDate(): 2024-10-28
#> # names(): AH75184
#> # $dataprovider: GENCODE
#> # $species: Homo sapiens
#> # $rdataclass: list
#> # $rdatadateadded: 2019-10-22
#> # $title: GenomicState for Gencode v31 on hg19 coordinates
#> # $description: Gencode v31 GenomicState from derfinder::makeGenomicState() ...
#> # $taxonomyid: 9606
#> # $genome: GRCh37
#> # $sourcetype: GTF
#> # $sourceurl: ftp://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/releas...
#> # $sourcesize: NA
#> # $tags: c("Gencode", "GenomicState", "hg19", "v31")
#> # retrieve record with 'object[["AH75184"]]'
## Check the metadata
mcols(hub_query_gs_gencode_v31_hg19)
#> DataFrame with 1 row and 15 columns
#> title dataprovider species taxonomyid genome
#> <character> <character> <character> <integer> <character>
#> AH75184 GenomicState for Gen.. GENCODE Homo sapiens 9606 GRCh37
#> description coordinate_1_based maintainer
#> <character> <integer> <character>
#> AH75184 Gencode v31 GenomicS.. 1 Leonardo Collado-Tor..
#> rdatadateadded preparerclass tags rdataclass
#> <character> <character> <AsIs> <character>
#> AH75184 2019-10-22 GenomicState Gencode,GenomicState,hg19,... list
#> rdatapath sourceurl sourcetype
#> <character> <character> <character>
#> AH75184 GenomicState/gencode.. ftp://ftp.ebi.ac.uk/.. GTF
## Access the file through AnnotationHub
if (length(hub_query_gs_gencode_v31_hg19) == 1) {
hub_gs_gencode_v31_hg19 <- hub_query_gs_gencode_v31_hg19[[1]]
hub_gs_gencode_v31_hg19
}
#> loading from cache
#> $fullGenome
#> GRanges object with 659263 ranges and 5 metadata columns:
#> seqnames ranges strand | theRegion tx_id
#> <Rle> <IRanges> <Rle> | <character> <IntegerList>
#> 1 chr1 11869-12227 + | exon 1,2
#> 2 chr1 12228-12612 + | intron 1,2
#> 3 chr1 12613-12721 + | exon 1,2
#> 4 chr1 12722-12974 + | intron 1,2
#> 5 chr1 12975-13052 + | exon 2
#> ... ... ... ... . ... ...
#> 659259 chrY 59208555-59214013 * | intergenic
#> 659260 chrY 59276440-59311662 * | intergenic
#> 659261 chrY 59311997-59318040 * | intergenic
#> 659262 chrY 59318921-59330251 * | intergenic
#> 659263 chrY 59360549-59373566 * | intergenic
#> tx_name gene symbol
#> <CharacterList> <IntegerList> <CharacterList>
#> 1 ENST00000450305.2_1,ENST00000456328.2_1 26085 DDX11L1
#> 2 ENST00000450305.2_1,ENST00000456328.2_1 26085 DDX11L1
#> 3 ENST00000450305.2_1,ENST00000456328.2_1 26085 DDX11L1
#> 4 ENST00000450305.2_1,ENST00000456328.2_1 26085 DDX11L1
#> 5 ENST00000450305.2_1 26085 DDX11L1
#> ... ... ... ...
#> 659259
#> 659260
#> 659261
#> 659262
#> 659263
#> -------
#> seqinfo: 24 sequences from hg19 genome
#>
#> $codingGenome
#> GRanges object with 878954 ranges and 5 metadata columns:
#> seqnames ranges strand | theRegion tx_id
#> <Rle> <IRanges> <Rle> | <character> <IntegerList>
#> 1 chr1 9869-11868 + | promoter 1,2
#> 2 chr1 11869-12227 + | exon 1,2
#> 3 chr1 12228-12612 + | intron 1,2
#> 4 chr1 12613-12721 + | exon 1,2
#> 5 chr1 12722-12974 + | intron 1,2
#> ... ... ... ... . ... ...
#> 878950 chrY 59208555-59212013 * | intergenic
#> 878951 chrY 59276440-59311662 * | intergenic
#> 878952 chrY 59313997-59318040 * | intergenic
#> 878953 chrY 59320921-59328251 * | intergenic
#> 878954 chrY 59362549-59373566 * | intergenic
#> tx_name gene symbol
#> <CharacterList> <IntegerList> <CharacterList>
#> 1 ENST00000450305.2_1,ENST00000456328.2_1 26085 DDX11L1
#> 2 ENST00000450305.2_1,ENST00000456328.2_1 26085 DDX11L1
#> 3 ENST00000450305.2_1,ENST00000456328.2_1 26085 DDX11L1
#> 4 ENST00000450305.2_1,ENST00000456328.2_1 26085 DDX11L1
#> 5 ENST00000450305.2_1,ENST00000456328.2_1 26085 DDX11L1
#> ... ... ... ...
#> 878950
#> 878951
#> 878952
#> 878953
#> 878954
#> -------
#> seqinfo: 24 sequences from hg19 genome
#>