Make a Tx2Gene object from transcriptome FASTA

makeTx2GeneFromFASTA(file)

Arguments

file	`character(1)`. File path.

Value

Tx2Gene.

Note

RefSeq transcript FASTA (e.g. "GCF_000001405.39_GRCh38.p13_rna.fna.gz") doesn't contain gene identifiers, and is not supported.

Updated 2021-01-29.

Examples

## Ensembl ====
file <- pasteURL(
    "ftp.ensembl.org",
    "pub",
    "release-102",
    "fasta",
    "homo_sapiens",
    "cdna",
    "Homo_sapiens.GRCh38.cdna.all.fa.gz",
    protocol = "ftp"
)
t2g <- makeTx2GeneFromFASTA(file)
#> → Making `Tx2Gene` from FASTA file (Homo_sapiens.GRCh38.cdna.all.fa.gz).
#> → Importing 129e5a395880_Homo_sapiens.GRCh38.cdna.all.fa.gz at /opt/koopa/opt/r/cache/AcidGenomes using data.table::`fread()`.
#> ℹ Ensembl transcriptome detected.
print(t2g)
#> Tx2Gene with 194360 rows and 2 columns
#>                      txId             geneId
#>               <character>        <character>
#> 1      ENST00000000233.10 ENSG00000004059.11
#> 2       ENST00000000412.8  ENSG00000003056.8
#> 3      ENST00000000442.11 ENSG00000173153.17
#> 4       ENST00000001008.6  ENSG00000004478.8
#> 5       ENST00000001146.6  ENSG00000003137.8
#> ...                   ...                ...
#> 194356  ENST00000679345.1 ENSG00000148334.16
#> 194357  ENST00000679346.1 ENSG00000182481.10
#> 194358  ENST00000679347.1 ENSG00000174080.12
#> 194359  ENST00000679348.1 ENSG00000115053.17
#> 194360  ENST00000679349.1 ENSG00000099284.15

## GENCODE ====
## > file <- pasteURL(
## >     "ftp.ebi.ac.uk",
## >     "pub",
## >     "databases",
## >     "gencode",
## >     "Gencode_human",
## >     "release_32",
## >     "gencode.v32.transcripts.fa.gz",
## >     protocol = "ftp"
## > )
## > t2g <- makeTx2GeneFromFASTA(file)
## > print(t2g)

## FlyBase ====
## > file <- pasteURL(
## >     "ftp.flybase.net",
## >     "releases",
## >     "FB2019_05",
## >     "dmel_r6.30",
## >     "fasta",
## >     "dmel-all-transcript-r6.30.fasta.gz",
## >     protocol = "ftp"
## > )
## > t2g <- makeTx2GeneFromFASTA(file)
## > print(t2g)

## WormBase ====
## > file <- pasteURL(
## >     "ftp.wormbase.org",
## >     "pub",
## >     "wormbase",
## >     "releases",
## >     "WS272",
## >     "species",
## >     "c_elegans",
## >     "PRJNA13758",
## >     "c_elegans.PRJNA13758.WS272.mRNA_transcripts.fa.gz",
## >     protocol = "ftp"
## > )
## > t2g <- makeTx2GeneFromFASTA(file)
## > print(t2g)