# #设置,回声= FALSE --------------------------------------------------- knitr: opts_chunk美元集(缓存= TRUE) # #——范围,消息= FALSE ----------------------------------------------- 要求(GenomicRanges) gr < -农庄(“A”,IRanges (c(10年,20年,22),宽度= 5),“+”)转变(gr, 1) #基于坐标!setdiff(range(gr)， gr) # 'introns' ## ----BSgenome-require, message=FALSE------------------------------------- require(BSgenome.Hsapiens.UCSC.hg19) chr14_range = grange ("chr14"， IRanges(1, seqlength (Hsapiens)["chr14"]) chr14_dna <- getSeq(Hsapiens，chr14_range) letterFrequency (chr14_dna GC, as.prob = TRUE) # #——bam-require --------------------------------------------------------- 需要(GenomicRanges)要求(GenomicAlignments)要求(Rsamtools) # #我们感兴趣的区域的roi < -农庄(“chr14”,IRanges (19653773,width=1)) ## sample data require('RNAseqData.HNRNPC.bam.chr14') bf <- BamFile(RNAseqData.HNRNPC.bam. chr14')## readGAlignmentsList(bf) j <- summarizeations (paln, with.revmap=TRUE) j_overlap <- j[j %over% roi] ## supporting reads paln[j_overlap$revmap[[1]]] ## ----vcf，消息= FALSE -------------------------------------------------- ## 输入变量需要(VariantAnnotation) fl < -系统。文件(“extdata”、“chr22.vcf.gz”、包=“VariantAnnotation”)vcf < - readVcf (fl, hg19) seqlevels (vcf) <——“chr22”# #已知基因模型需要(TxDb.Hsapiens.UCSC.hg19.knownGene)编码< - locateVariants (rowData (vcf) TxDb.Hsapiens.UCSC.hg19。knownGene, CodingVariants()) head(coding) ## ---- summarizeoverlay -roi, message=FALSE-------------------------------- require(TxDb.Hsapiens.UCSC.hg19.knownGene) exByGn <- exonsBy(TxDb.Hsapiens.UCSC.hg19. ucsc.hg19 .knownGene) exByGnknownGene,“基因”)# #只有14号染色体seqlevels (exByGn,力= TRUE) =“chr14”# #——summarizeOverlaps-bam消息= FALSE -------------------------------- 需要(RNAseqData.HNRNPC.bam.chr14)长度(RNAseqData.HNRNPC.bam.chr14_BAMFILES) # #——summarizeOverlaps --------------------------------------------------- ## 下一个2线可选;非windows库(BiocParallel)注册(MulticoreParam(工人= detectCores ())) olap < - summarizeOverlaps (exByGn RNAseqData.HNRNPC.bam.chr14_BAMFILES) # #——summarizeOverlaps-explore ------------------------------------------- olap(分析(olap)) colSums(分析(olap)) #库大小的情节(总和(宽度(olap)), rowMeans(分析(olap)),日志= " xy ") ## ---- summarizeOverlaps-gc ------------------------------------------------ 需要< getSeq (BSgenome.Hsapiens.UCSC (BSgenome.Hsapiens.UCSC.hg19)序列。hg19, rowData(olaps)) gcPerExon <- letterFrequency(unlist(sequences), "GC") gc <- relist(as.vector(gcPerExon), sequences) gc_percent <- sum(gc) / sum(width(olaps)) plot(gc_percent, rowMeans(assay(olaps)), log="y")