4  注释数据资源

4.1 人类基因组 Human Genome

人类基因组参考联盟（Genome Reference Consortium Human）

基因组名称 UCSC数据库别名 发布年份 描述
GRCh37 hg19 2009 存在部分未完全填补的“缺口”（gaps），实际覆盖约92%的人类基因组，已逐步淘汰
GRCh38 hg38 2013 目前的主流版本，修正了基因坐标错误，增加假染色体（ALT）
T2T-CHM13 无 2022.The complete sequence of a human genome. Science 首个完整人类基因组，填补了 GRCh38 缺失的 8% DNA

4.2 注释包

https://bioconductor.org/packages/release/workflows/html/annotation.html

https://bioconductor.org/packages/release/bioc/html/AnnotationDbi.html

Object Type Example Package Name Contents
TxDb TxDb.Hsapiens.UCSC.hg19.knownGene Transcriptome ranges for the known gene track of Homo sapiens, e.g., introns, exons, UTR regions.
OrgDb

org.Hs.eg.db

org.Mm.eg.db

 Gene-based information ; useful for mapping between gene IDs, Names, Symbols, GO and KEGG identifiers, etc.
BSgenome BSgenome.Hsapiens.UCSC.hg38 Full genome sequence for Homo sapiens.

4.2.1 BSgenome

Code 
library(BSgenome)
bs <- available.genomes(splitNameParts = T)
human_genomes <- bs[bs$organism == "Hsapiens", ] 
human_genomes
#>                                       pkgname organism    provider
#> 55       BSgenome.Hsapiens.1000genomes.hs37d5 Hsapiens 1000genomes
#> 56              BSgenome.Hsapiens.NCBI.GRCh38 Hsapiens        NCBI
#> 57       BSgenome.Hsapiens.NCBI.T2T.CHM13v2.0 Hsapiens        NCBI
#> 58                BSgenome.Hsapiens.UCSC.hg17 Hsapiens        UCSC
#> 59         BSgenome.Hsapiens.UCSC.hg17.masked Hsapiens        UCSC
#> 60                BSgenome.Hsapiens.UCSC.hg18 Hsapiens        UCSC
#> 61         BSgenome.Hsapiens.UCSC.hg18.masked Hsapiens        UCSC
#> 62                BSgenome.Hsapiens.UCSC.hg19 Hsapiens        UCSC
#> 63         BSgenome.Hsapiens.UCSC.hg19.masked Hsapiens        UCSC
#> 64                BSgenome.Hsapiens.UCSC.hg38 Hsapiens        UCSC
#> 65 BSgenome.Hsapiens.UCSC.hg38.dbSNP151.major Hsapiens        UCSC
#> 66 BSgenome.Hsapiens.UCSC.hg38.dbSNP151.minor Hsapiens        UCSC
#> 67         BSgenome.Hsapiens.UCSC.hg38.masked Hsapiens        UCSC
#> 68                 BSgenome.Hsapiens.UCSC.hs1 Hsapiens        UCSC
#>                 genome masked
#> 55              hs37d5  FALSE
#> 56              GRCh38  FALSE
#> 57       T2T.CHM13v2.0  FALSE
#> 58                hg17  FALSE
#> 59                hg17   TRUE
#> 60                hg18  FALSE
#> 61                hg18   TRUE
#> 62                hg19  FALSE
#> 63                hg19   TRUE
#> 64                hg38  FALSE
#> 65 hg38.dbSNP151.major  FALSE
#> 66 hg38.dbSNP151.minor  FALSE
#> 67                hg38   TRUE
#> 68                 hs1  FALSE
installed.genomes()
#> [1] "BSgenome.Hsapiens.UCSC.hg38"

从UCSC hg38中加载智人的全基因组序列，计算14号染色体GC含量

Code 
# pak::pak("BSgenome.Hsapiens.UCSC.hg38")
library(BSgenome.Hsapiens.UCSC.hg38)
chr14_range = GRanges(seqnames = "chr14",
                      ranges =  IRanges(start = 1, 
                                       end = seqlengths(Hsapiens)["chr14"])
                      )
chr14_dna <- getSeq(Hsapiens, chr14_range)
letterFrequency(chr14_dna, letters = "GC", as.prob=TRUE)
#>            G|C
#> [1,] 0.3454924

4.2.2 OrgDb

org.Hs.eg.db

Code 
library(AnnotationDbi)
library(org.Hs.eg.db)


AnnotationDbi::keytypes(org.Hs.eg.db)  # 等价 AnnotationDbi::columns(org.Hs.eg.db)
#>  [1] "ACCNUM"       "ALIAS"        "ENSEMBL"      "ENSEMBLPROT"  "ENSEMBLTRANS"
#>  [6] "ENTREZID"     "ENZYME"       "EVIDENCE"     "EVIDENCEALL"  "GENENAME"    
#> [11] "GENETYPE"     "GO"           "GOALL"        "IPI"          "MAP"         
#> [16] "OMIM"         "ONTOLOGY"     "ONTOLOGYALL"  "PATH"         "PFAM"        
#> [21] "PMID"         "PROSITE"      "REFSEQ"       "SYMBOL"       "UCSCKG"      
#> [26] "UNIPROT"


# 示例 
entrez_id <- c("1017", "1018", "1019")  # 替换为你自己的 entrez_id

# 进行映射
AnnotationDbi::select(org.Hs.eg.db, 
                       keys = entrez_id, 
                       columns = c("GENENAME","ALIAS","SYMBOL","GO","ONTOLOGY"), 
                       keytype = "ENTREZID", multiVals = "CharacterList") |> 
  head()
#>   ENTREZID                  GENENAME ALIAS SYMBOL         GO EVIDENCE ONTOLOGY
#> 1     1017 cyclin dependent kinase 2 CDKN2   CDK2 GO:0000082      IBA       BP
#> 2     1017 cyclin dependent kinase 2 CDKN2   CDK2 GO:0000082      IEA       BP
#> 3     1017 cyclin dependent kinase 2 CDKN2   CDK2 GO:0000082      NAS       BP
#> 4     1017 cyclin dependent kinase 2 CDKN2   CDK2 GO:0000086      NAS       BP
#> 5     1017 cyclin dependent kinase 2 CDKN2   CDK2 GO:0000122      IEA       BP
#> 6     1017 cyclin dependent kinase 2 CDKN2   CDK2 GO:0000166      IEA       MF


# mapIds can only use one column.
mapIds(org.Hs.eg.db, 
     keys = entrez_id, 
     column = c("ALIAS"),   # 别名
     keytype = "ENTREZID", multiVals = "CharacterList") 
#> CharacterList of length 3
#> [["1017"]] CDKN2 p33(CDK2) CDK2
#> [["1018"]] CDK3
#> [["1019"]] CMM3 PSK-J3 CDK4