# #——风格,eval = TRUE,呼应= FALSE,结果= "飞机 "------------------------ BiocStyle::乳胶()库(knitr)美元opts_chunk组(缓存= TRUE,整洁= FALSE) # #——预赛,消息= FALSE ----------------------------------------- 库(Biostrings)库(ShortRead) # #——help1 --------------------------------------------------------------- showMethods(补)# #——介绍 --------------------------------------------------------------- < - b型(“我存储任何的字符集!”)d <- DNAString("GCATAT-TAC") #创建DNAString对象。r <- RNAString("GCAUAU-UAC") #创建RNAString对象。r <- RNAString(d) #将d转换为RNAString对象。p < AAString(“HCWYHH ") ## ---- fileaccess ---------------------------------------------------------- fls的< - list.files(系统。file("extdata"， package="BiocIntro")， pattern =".txt"，full=TRUE) fls ## ----data---------------------------------------------------------------- #方法- 1 #读取FATSA文件seq <- readFasta(fls) ##让我们创建一个DNAStringSet，这是一个容器，用于存储一组DNAString dna <- sread(seq) #方法-2 dna <- readnastringset (fls) #让我们看看第一个DNAString，这个[[]]操作将DNAStringSet转换为DNAString brca1 <- dna[[1]] brca2 <- dna[[2]] #，使输出更容易理解。FASTA格式的序列表示为一系列行，每行通常不超过80个字符。successiveViews (brca1、宽度=代表(50、长度(dna [[1]]) / 50 + 1 )) ## ---- successiveViewall eval = FALSE --------------------------------------- ## 选项(showHeadLines =正)# # successiveViews (brca1,宽度=代表(50、长度(dna [[1]]) / 50 + 1 )) ## ---- 反向 ------------------------------------------------------------- 反向(brca1)补(brca1) reverseComplement (brca1 ) ## ------------------------------------------------------------------------ 翻译》(brca1) # #——预定义 -------------------------------------------------------------- DNA_BASES DNA_ALPHABET IUPAC_CODE_MAP # #——frequeny ------------------------------------------------------------ # 独特的字母是什么? uniqueLetters(brca2) alphabetFrequency(brca2) alphabetFrequency(brca2, baseOnly=TRUE) dinucleotideFrequency(brca2) trinucleotideFrequency(brca2) ## ----sol-gc-------------------------------------------------------------- gcContent <- function(x) { alf <- alphabetFrequency(x, as.prob=TRUE) sum(alf[c("G","C")]) } gcContent(brca1) gcContent(brca2) ## ----homosap-ex, message=FALSE------------------------------------------- library(BSgenome.Hsapiens.UCSC.hg19) ## ----homosap-gc-ex, message=FALSE---------------------------------------- gcContent(Hsapiens[["chr17"]]) gcContent(Hsapiens[["chr13"]]) ## ----hist-gc-ex---------------------------------------------------------- chrs <- paste0("chr", c(1:22,"X","Y")) data <- sapply(chrs, function(x) gcContent(Hsapiens[[x]])) names(data) <- chrs plot(data, xlab="chromosomes",ylab="gc Frequencies", xlim=c(1,24), col="blue") abline(h=gcContent(Hsapiens[["chr17"]]),col="red") abline(h=gcContent(Hsapiens[["chr13"]]),col="orange") title(main="gc Frequecies across Human Chromosomes", col.main="blue", font.main=4) legend("topleft",c("chromsomes","brca1","brca2"), cex=0.8, col=c("blue","red","orange"), pch=21:22, lty=1:2) ## ----sessionInfo--------------------------------------------------------- sessionInfo()