## ----设置，eval = true，echo = false，警告= false，消息= false ----------选项（max.print = 1000）knitr :: opts_chunk $ set（缓存=true）suppresspackageStartUpMessages（{库（org.hs.eg.db）库（txdb.hsapiens.ucsc.hg19.knowngene）库（bsgenome.hsapiens.ucsc.hg19）库（基因组）库（BioMart）库（Rtracklayer）}）## ----选择 - 设置------------------------------------------------------------- EXSIDS < - C（“ENSG00000130720”，“ENSG00000156414”，“ENSG00000144644”，“ENSG00000159307”，“ENSG00000144485”）## ----选择 - - - - - - - - - - - - - - - - - - - - - - - ---------------库（org.hs.eg.db）keytypes（org.hs.eg.db）列（org.hs.eg.db）cols < - c（“符号“，”genename“）选择（org.hs.eg.db，keys = ensids，columns = cols，keytype =”ensembl“）## ----生物草图1，eval = false，结果=”隐藏“ ---------------------------- ######需要互联网访问！##库（Biomart）## head（listmarts（），3）##列出了MARTS ## Head（ListDatasets（USEMART（“EnsemBl”）），3）## Mart DataSets ## Ensembl < - ##完全指定Mart ## Usemart（“ensembl”，dataset =“hsapiens_gene_ensembl”）#####1,50）##返回值## MyValues < - C（“21”，“22”）## head（listAttributes（ensembl），3）##属性## myattributes < - c（“ensembl_gene_id”，“chromosome_name“## ## ##汇编和查询Mart ## Res < - getBm（属性= myattributes，filters = myfilter，##值= MyValues，Mart = Ensembl）## ----符号到entrez------------------------------------------------------------------ 库（org.hs.eg.db）eid < - select（org.hs.eg.db，“brca1”，“EntrezID”，“符号”）[[“EntrezID”]] ## ---- entrez-to-tx，message = false -------------------------------------图书馆(TxDb.Hsapiens.UCSC.hg19.knownGene) txdb <- TxDb.Hsapiens.UCSC.hg19.knownGene txid <- select(txdb, eid, "TXNAME", "GENEID")[["TXNAME"]] ## ----tx-to-cds-coords---------------------------------------------------- cds <- cdsBy(txdb, by="tx", use.names=TRUE) brca1cds <- cds[names(cds) %in% txid] class(brca1cds) length(brca1cds) brca1cds[[1]] # exons in cds cdswidth <- width(brca1cds) # width of each exon all((sum(cdswidth) %% 3) == 0) # sum within cds, modulus 3 ## ----Gviz, message=FALSE------------------------------------------------- require(Gviz) anno <- AnnotationTrack(brca1cds) plotTracks(list(GenomeAxisTrack(), anno)) ## ----cds-to-seq---------------------------------------------------------- library(BSgenome.Hsapiens.UCSC.hg19) genome <- BSgenome.Hsapiens.UCSC.hg19 tx_seq <- extractTranscriptSeqs(genome, brca1cds) tx_seq ## ----introns------------------------------------------------------------- introns <- psetdiff(range(brca1cds), brca1cds) ## ----intron-seqs--------------------------------------------------------- seq <- getSeq(genome, introns) names(seq) seq[["uc010whl.2"]] # 21 introns ## ----rtracklayer-roi----------------------------------------------------- library(GenomicRanges) roi <- GRanges("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")