# #设置,回声= FALSE --------------------------------------------------- 库(LearnBioconductor) stopifnot (BiocInstaller:: biocVersion() = = 3.0” ") ## ---- 风格,回声= FALSE,结果= '飞机 '------------------------------- BiocStyle:减价 () ## ---- 包裹,eval = TRUE,呼应= FALSE,警告= FALSE,消息= FALSE ----------- 选项(max.print = 1000) suppressPackageStartupMessages({库(org.Hs.eg.db)库(TxDb.Hsapiens.UCSC.hg19.knownGene)图书馆(BSgenome.Hsapiens.UCSC.hg19)图书馆(GenomicRanges)图书馆(biomaRt)图书馆(rtracklayer ) }) ## ---- 选择安装 -------------------------------------------------------- ensids < -c(“ENSG00000130720”、“ENSG00000103257”,“ENSG00000156414”、“ENSG00000144644”、“ENSG00000159307”、“ENSG00000144485 ") ## ---- 选择 -------------------------------------------------------------- 库(org.Hs.eg.db) keytypes (org.Hs.eg.db)列(org.Hs.eg.db)关口< - c(“象征”、“GENENAME”)选择(org.Hs.eg.db键= ensids列=关口,keytype = "运用 ") ## ---- biomaRt1, eval = FALSE,结果=“隐藏 "-------------------------------- # ## 需要上网! !#库(biomaRt) #头(listMarts(), 3)集市# # #列表头(listDatasets (useMart(“运用”)),3)#运用< - # # # #集市数据集完全指定的集市# useMart(“运用”,数据集=“hsapiens_gene_ensembl”)# #头(listFilters(运用),3)# # #过滤器myFilter < -“chromosome_name”# substr (filterOptions (myFilter运用),1,50) ## return values # myValues <- c("21"， "22") # head(listAttributes(ensembl)， 3) ## attributes # myAttributes <- c("ensembl_gene_id"，"chromosome_name") ## ## assemble and query the mart # res <- c(attributes = myAttributes, filters = myFilter， # values = myValues，集市= # #——symbol-to-entrez运用) ---------------------------------------------------- 库(org.Hs.eg.db)开斋节< -选择(org.Hs.eg.db,“BRCA1”,“ENTREZID”、“符号”)[[”ENTREZID "]] ## ---- entrez-to-tx,消息= FALSE ---------------------------------------- 库(TxDb.Hsapiens.UCSC.hg19.knownGene) txdb < - TxDb.Hsapiens.UCSC.hg19。knownGene txid < - select (txdb开斋节,“TXNAME”、“GENEID”)[[”TXNAME "]] ## ---- tx-to-cds-coords ---------------------------------------------------- cd < - cdsBy (txdb =“tx”,use.names=TRUE) brca1cds <- cds[names(cds) %in% txid] class(brca1cds) length(brca1cds) brca1cds[[1]] # exons in cds cdwidth <- width(brca1cds) # width of each exon all((sum(cdswidth) %% 3) == 0) ## sum within cds, modulus 3 ## # Gviz，消息= FALSE ------------------------------------------------- 要求(Gviz)伊斯兰教纪元< - AnnotationTrack brca1cds plotTracks(列表(GenomeAxisTrack(),伊斯兰教纪元 )) ## ---- cds-to-seq ---------------------------------------------------------- < - BSgenome.Hsapiens.UCSC库(BSgenome.Hsapiens.UCSC.hg19)基因组。brca1cds hg19 tx_seq < - extractTranscriptSeqs(基因组)tx_seq # #——内含子 ------------------------------------------------------------- 内含子< - psetdiff(范围(brca1cds) brca1cds) # #——intron-seqs --------------------------------------------------------- seq < - getSeq(基因内含子)名称(seq) seq[[”uc010whl。2》]]21号内含子# #——rtracklayer-roi ----------------------------------------------------- 库(GenomicRanges) roi < -农庄(“chr10”,IRanges (92106877, 112106876, names="ENSG00000099194")) ## ----rtracklayer-session------------------------------------------------- library(rtracklayer) session <- browserSession() ## ----rtracklayer-marks--------------------------------------------------- trackName <- "wgEncodeRegTfbsClusteredV2" tableName <- "wgEncodeRegTfbsClusteredV2" trFactor <- "ERalpha_a" ucscTable <- getTable(ucscTableQuery(session, track=trackName, range=roi, table=tableName, name=trFactor)) ## ----rtracklayer-plot, fig.height=3-------------------------------------- plot(score ~ chromStart, ucscTable, pch="+") abline(v=start(roi) + (end(roi) - start(roi) + 1) / 2, col="blue")