Contents
COAD from curatedTCGAData
suppressPackageStartupMessages({
library(curatedTCGAData)
})
suppressMessages({
coad <- curatedTCGAData(
diseaseCode = "COAD",
assays = "miRNA*",
version = "1.1.38",
dry.run = FALSE
)
})
Try miRBaseConverter
suppressPackageStartupMessages({
library(miRBaseConverter)
})
checkMiRNAVersion(test_mirs)
## Version Proportion Recommend
## 1 v6 83.33%
## 2 v7_1 83.33%
## 3 v8 83.33%
## 4 v8_1 83.33%
## 5 v8_2 83.33%
## 6 v9 83.33%
## 7 v9_1 83.33%
## 8 v9_2 83.33%
## 9 v10 100% ***BEST Matched***
## 10 v10_1 100% ***BEST Matched***
## 11 v11 100% ***BEST Matched***
## 12 v12 100% ***BEST Matched***
## 13 v13 100% ***BEST Matched***
## 14 v14 100% ***BEST Matched***
## 15 v15 100% ***BEST Matched***
## 16 v16 100% ***BEST Matched***
## 17 v17 100% ***BEST Matched***
## 18 v18 100% ***BEST Matched***
## 19 v19 100% ***BEST Matched***
## 20 v20 100% ***BEST Matched***
## 21 v21 100% ***BEST Matched***
## 22 v22 100% ***BEST Matched***
## [1] "v22"
#' [1] "v22"
version <- "v22"
Get accessions
mirna_info <- miRNA_NameToAccession(test_mirs, version = version)
mirna_info
## miRNAName_v22 Accession
## 1 hsa-mir-944 MI0005769
## 2 hsa-mir-95 MI0000097
## 3 hsa-mir-96 MI0000098
## 4 hsa-mir-98 MI0000100
## 5 hsa-mir-99a MI0000101
## 6 hsa-mir-99b MI0000746
mirna_accessions <- mirna_info[["Accession"]]
mirna_accessions
## [1] "MI0005769" "MI0000097" "MI0000098" "MI0000100" "MI0000101" "MI0000746"
Get Annotated GRanges for GRCh38
suppressPackageStartupMessages({
library(AnnotationHub)
})
ah <- AnnotationHub()
ens_db_query <- query(ah, c("EnsDb", "Homo sapiens"))
edb <- ens_db_query[[tail(names(ens_db_query), 1)]]
## loading from cache
## require("ensembldb")
edb
## EnsDb for Ensembl:
## |Backend: SQLite
## |Db type: EnsDb
## |Type of Gene ID: Ensembl Gene ID
## |Supporting package: ensembldb
## |Db created by: ensembldb package from Bioconductor
## |script_version: 0.3.10
## |Creation time: Sat Oct 26 21:34:14 2024
## |ensembl_version: 113
## |ensembl_host: 127.0.0.1
## |Organism: Homo sapiens
## |taxonomy_id: 9606
## |genome_build: GRCh38
## |DBSCHEMAVERSION: 2.2
## |common_name: human
## |species: homo_sapiens
## | No. of genes: 87726.
## | No. of transcripts: 413674.
## |Protein data available.
all_mirnas <- ensembldb::genes(edb, filter = GeneBiotypeFilter("miRNA"))
all_mirnas
## GRanges object with 1945 ranges and 9 metadata columns:
## seqnames ranges strand | gene_id
## <Rle> <IRanges> <Rle> | <character>
## ENSG00000278267 1 17369-17436 - | ENSG00000278267
## ENSG00000284332 1 30366-30503 + | ENSG00000284332
## ENSG00000273874 1 187891-187958 - | ENSG00000273874
## ENSG00000278791 1 632325-632413 - | ENSG00000278791
## ENSG00000207730 1 1167104-1167198 + | ENSG00000207730
## ... ... ... ... . ...
## ENSG00000221533 X 154887360-154887458 - | ENSG00000221533
## ENSG00000221190 X 155383100-155383198 - | ENSG00000221190
## ENSG00000221603 X 155457517-155457615 + | ENSG00000221603
## ENSG00000292355 Y 1293918-1293992 + | ENSG00000292355
## ENSG00000292346 Y 2609191-2609254 + | ENSG00000292346
## gene_name gene_biotype seq_coord_system
## <character> <character> <character>
## ENSG00000278267 MIR6859-1 miRNA chromosome
## ENSG00000284332 MIR1302-2 miRNA chromosome
## ENSG00000273874 MIR6859-2 miRNA chromosome
## ENSG00000278791 miRNA chromosome
## ENSG00000207730 MIR200B miRNA chromosome
## ... ... ... ...
## ENSG00000221533 MIR1184-1 miRNA chromosome
## ENSG00000221190 MIR1184-2 miRNA chromosome
## ENSG00000221603 MIR1184-3 miRNA chromosome
## ENSG00000292355 MIR3690 miRNA chromosome
## ENSG00000292346 MIR6089 miRNA chromosome
## description gene_id_version canonical_transcript
## <character> <character> <character>
## ENSG00000278267 microRNA 6859-1 [Sou.. ENSG00000278267.1 ENST00000619216
## ENSG00000284332 microRNA 1302-2 [Sou.. ENSG00000284332.1 ENST00000607096
## ENSG00000273874 microRNA 6859-2 [Sou.. ENSG00000273874.1 ENST00000612080
## ENSG00000278791 ENSG00000278791.1 ENST00000621981
## ENSG00000207730 microRNA 200b [Sourc.. ENSG00000207730.3 ENST00000384997
## ... ... ... ...
## ENSG00000221533 microRNA 1184-1 [Sou.. ENSG00000221533.1 ENST00000408606
## ENSG00000221190 microRNA 1184-2 [Sou.. ENSG00000221190.1 ENST00000408263
## ENSG00000221603 microRNA 1184-3 [Sou.. ENSG00000221603.1 ENST00000408676
## ENSG00000292355 microRNA 3690 [Sourc.. ENSG00000292355.1 ENST00000711140
## ENSG00000292346 microRNA 6089 [Sourc.. ENSG00000292346.1 ENST00000711167
## symbol entrezid
## <character> <list>
## ENSG00000278267 MIR6859-1 102466751
## ENSG00000284332 MIR1302-2 100302278
## ENSG00000273874 MIR6859-2 102465909
## ENSG00000278791 <NA>
## ENSG00000207730 MIR200B 406984
## ... ... ...
## ENSG00000221533 MIR1184-1 100302111
## ENSG00000221190 MIR1184-2 100422985
## ENSG00000221603 MIR1184-3 100422977
## ENSG00000292355 MIR3690 100500894
## ENSG00000292346 MIR6089 102464837
## -------
## seqinfo: 61 sequences from GRCh38 genome
No matches found
all_mirnas[mcols(all_mirnas)$symbol %in% mirna_accessions]
## GRanges object with 0 ranges and 9 metadata columns:
## seqnames ranges strand | gene_id gene_name gene_biotype
## <Rle> <IRanges> <Rle> | <character> <character> <character>
## seq_coord_system description gene_id_version canonical_transcript
## <character> <character> <character> <character>
## symbol entrezid
## <character> <list>
## -------
## seqinfo: 61 sequences from GRCh38 genome