## ----setup, include = FALSE---------------------------------------------- library(BiocAnno2016) library(hugene20sttranscriptcluster.db) library(EnsDb.Mmusculus.v79) library(org.Hs.eg.db) library(TxDb.Hsapiens.UCSC.hg19.knownGene) library(Homo.sapiens) library(BSgenome) library(BSgenome.Hsapiens.UCSC.hg19) library(AnnotationHub) ## ------------------------------------------------------------------------ load(system.file("data/eset.Rdata", package = "BiocAnno2016")) eset ## ------------------------------------------------------------------------ head(exprs(eset)) head(pData(phenoData(eset))) ## ------------------------------------------------------------------------ head(pData(featureData(eset))) ## ---- results = "asis", echo = FALSE------------------------------------- df <- data.frame("Package type" = c("ChipDb","OrgDb","TxDb/EnsDb","OrganismDb","BSgenome","Others","AnnotationHub","biomaRt"), Example = c("hugene20sttranscriptcluster.db","org.Hs.eg.db","TxDb.Hsapiens.UCSC.hg19.knownGene; EnsDb.Hsapiens.v75", "Homo.sapiens","BSgenome.Hsapiens.UCSC.hg19","GO.db; KEGG.db", "Online resource","Online resource"), check.names = FALSE) knitr::kable(df) ## ------------------------------------------------------------------------ library(hugene20sttranscriptcluster.db) set.seed(12345) ids <- featureNames(eset)[sample(1:25000, 5)] ids select(hugene20sttranscriptcluster.db, ids, "SYMBOL") ## ------------------------------------------------------------------------ keytypes(hugene20sttranscriptcluster.db) columns(hugene20sttranscriptcluster.db) ## ------------------------------------------------------------------------ ids <- c('16737401','16657436' ,'16678303') select(hugene20sttranscriptcluster.db, ids, c("SYMBOL","MAP")) ## ------------------------------------------------------------------------ mapIds(hugene20sttranscriptcluster.db, ids, "SYMBOL", "PROBEID") ## ------------------------------------------------------------------------ mapIds(hugene20sttranscriptcluster.db, ids, "SYMBOL", "PROBEID", multiVals = "list") ## ------------------------------------------------------------------------ mapIds(hugene20sttranscriptcluster.db, ids, "SYMBOL", "PROBEID", multiVals = "CharacterList") mapIds(hugene20sttranscriptcluster.db, ids, "SYMBOL", "PROBEID", multiVals = "filter") mapIds(hugene20sttranscriptcluster.db, ids, "SYMBOL", "PROBEID", multiVals = "asNA") ## ------------------------------------------------------------------------ select(TxDb.Hsapiens.UCSC.hg19.knownGene, c("1","10"), c("TXNAME","TXCHROM","TXSTART","TXEND"), "GENEID") select(EnsDb.Hsapiens.v79, c("1", "10"), c("GENEID","GENENAME","SEQNAME","GENESEQSTART","GENESEQEND"), "ENTREZID") ## ------------------------------------------------------------------------ gns <- genes(TxDb.Hsapiens.UCSC.hg19.knownGene) gns ## ------------------------------------------------------------------------ txs <- transcriptsBy(TxDb.Hsapiens.UCSC.hg19.knownGene) txs ## ------------------------------------------------------------------------ txs[txs %over% gns[1:2,]] ## ------------------------------------------------------------------------ library(Homo.sapiens) Homo.sapiens ## ------------------------------------------------------------------------ head(genes(Homo.sapiens, columns = c("ENTREZID","ALIAS","UNIPROT")),4) ## ------------------------------------------------------------------------ library(BSgenome) head(available.genomes()) ## ------------------------------------------------------------------------ library(BSgenome.Hsapiens.UCSC.hg19) Hsapiens ## ------------------------------------------------------------------------ getSeq(Hsapiens, "chr1") getSeq(Hsapiens, gns["5467",]) ## ---- include = FALSE---------------------------------------------------- library(AnnotationHub) hub <- AnnotationHub() ## ------------------------------------------------------------------------ library(AnnotationHub) hub <- AnnotationHub() hub ## ------------------------------------------------------------------------ names(mcols(hub)) ## ------------------------------------------------------------------------ unique(hub$dataprovider) ## ------------------------------------------------------------------------ unique(hub$rdataclass) ## ------------------------------------------------------------------------ head(unique(hub$species)) length(unique(hub$species)) ## ------------------------------------------------------------------------ unique(hub$sourcetype) ## ------------------------------------------------------------------------ qry <- query(hub, c("granges","homo sapiens","ensembl")) qry ## ------------------------------------------------------------------------ qry$sourceurl ## ---- message = FALSE---------------------------------------------------- whatIwant <- qry[["AH50377"]] ## ------------------------------------------------------------------------ GRCh38TxDb <- makeTxDbFromGRanges(whatIwant) GRCh38TxDb ## ------------------------------------------------------------------------ library(biomaRt) listMarts() ## ------------------------------------------------------------------------ mart <- useMart("ENSEMBL_MART_ENSEMBL") head(listDatasets(mart)) ## ------------------------------------------------------------------------ mart <- useMart("ENSEMBL_MART_ENSEMBL","hsapiens_gene_ensembl") ## ------------------------------------------------------------------------ atrib <- listAttributes(mart) filts <- listFilters(mart) head(atrib) head(filts) ## ------------------------------------------------------------------------ afyids <- c("1000_at","1001_at","1002_f_at","1007_s_at") getBM(c("affy_hg_u95av2", "hgnc_symbol"), c("affy_hg_u95av2"), afyids, mart)