R基本语法
获取帮助文档，查看命令或函数的使用方法、事例或适用范围
>>> ?command>>> ??command #深度搜索或模糊搜索此命令>>> example(command) #得到命令的例子
R中的变量
> # 数字变量> a a[1] 10> > # 字符串变量> a a[1] “abc”> > # 逻辑变量> a > a[1] TRUE> > b > b[1] TRUE> > d > d[1] FALSE> # 向量> > a a[1] FALSE FALSE FALSE FALSE FALSE> > a is.vector(a)[1] TRUE> > # 矩阵> > a a [,1] [,2] [,3] [,4][1,] 1 2 3 4[2,] 5 6 7 8[3,] 9 10 11 12[4,] 13 14 15 16[5,] 17 18 19 20> > is.matrix(a)[1] TRUE> > dim(a) #查看或设置数组的维度向量[1] 5 4> > # 错误的用法> dim(a) # 正确的用法> a dim(a) a [,1] [,2] [,3] [,4][1,] 1 6 11 16[2,] 2 7 12 17[3,] 3 8 13 18[4,] 4 9 14 19[5,] 5 10 15 20> > print(paste(“矩阵a的行数”, nrow(a)))[1] “矩阵a的行数 5”> print(paste(“矩阵a的列数”, ncol(a)))[1] “矩阵a的列数 4”> > #查看或设置行列名> rownames(a)NULL> rownames(a) a [,1] [,2] [,3] [,4]a 1 6 11 16b 2 7 12 17c 3 8 13 18d 4 9 14 19e 5 10 15 20# R中获取一系列的字母> letters[1:4][1] “a” “b” “c” “d”> colnames(a) a a b c da 1 6 11 16b 2 7 12 17c 3 8 13 18d 4 9 14 19e 5 10 15 20> # is系列和as系列函数用来判断变量的属性和转换变量的属性# 矩阵转换为data.frame> is.character(a)[1] FALSE> is.numeric(a)[1] TRUE> is.matrix(a)[1] TRUE> is.data.frame(a)[1] FALSE> is.data.frame(as.data.frame(a))[1] TRUE
R中矩阵运算
# 数据产生# rnorm(n, mean = 0, sd = 1) 正态分布的随机数# runif(n, min = 0, max = 1) 平均分布的随机数# rep(1,5) 把1重复5次# scale(1:5) 标准化数据> a a [1] -0.41253556 0.12192929 -0.47635888 -0.97171653 1.09162243 1.87789657 [7] -0.11717937 2.92953522 1.33836620 -0.03269026 0.87540920 0.13005744[13] 0.11900686 0.76663940 0.28407356 -0.91251181 0.17997973 0.50452258[19] 0.25961316 -0.58052230 1.00000000 2.00000000 3.00000000 4.00000000[25] 5.00000000 0.00000000 0.00000000 0.00000000 0.00000000 0.00000000[31] 2.00000000 10.00000000 11.00000000 13.00000000 4.00000000 -1.26491106[37] -0.63245553 0.00000000 0.63245553 1.26491106> a a [,1] [,2] [,3] [,4] [,5][1,] -0.4125356 0.1219293 -0.4763589 -0.9717165 1.09162243[2,] 1.8778966 -0.1171794 2.9295352 1.3383662 -0.03269026[3,] 0.8754092 0.1300574 0.1190069 0.7666394 0.28407356[4,] -0.9125118 0.1799797 0.5045226 0.2596132 -0.58052230[5,] 1.0000000 2.0000000 3.0000000 4.0000000 5.00000000[6,] 0.0000000 0.0000000 0.0000000 0.0000000 0.00000000[7,] 2.0000000 10.0000000 11.0000000 13.0000000 4.00000000[8,] -1.2649111 -0.6324555 0.0000000 0.6324555 1.26491106# 求行的加和> rowSums(a)[1] -0.6470593 5.9959284 2.1751865 -0.5489186 15.0000000 0.0000000 40.0000000[8] 0.0000000## 注意检查括号的配对> a a * 2 [,1] [,2] [,3] [,4] [,5][1,] -0.8250711 0.2438586 -0.9527178 -1.9434331 2.18324487[2,] 3.7557931 -0.2343587 5.8590704 2.6767324 -0.06538051[3,] 1.7508184 0.2601149 0.2380137 1.5332788 0.56814712[4,] -1.8250236 0.3599595 1.0090452 0.5192263 -1.16104460[5,] 2.0000000 4.0000000 6.0000000 8.0000000 10.00000000[6,] 4.0000000 20.0000000 22.0000000 26.0000000 8.00000000[7,] -2.5298221 -1.2649111 0.0000000 1.2649111 2.52982213# 所有值取绝对值，再取对数 （取对数前一般加一个数避免对0或负值取对数）> log2(abs(a)+1) [,1] [,2] [,3] [,4] [,5][1,] 0.4982872 0.1659818 0.5620435 0.9794522 1.0646224[2,] 1.5250147 0.1598608 1.9743587 1.2255009 0.0464076[3,] 0.9072054 0.1763961 0.1622189 0.8210076 0.3607278[4,] 0.9354687 0.2387621 0.5893058 0.3329807 0.6604014[5,] 1.0000000 1.5849625 2.0000000 2.3219281 2.5849625[6,] 1.5849625 3.4594316 3.5849625 3.8073549 2.3219281[7,] 1.1794544 0.7070437 0.0000000 0.7070437 1.1794544# 取出最大值、最小值、行数、列数> max(a)[1] 13> min(a)[1] -1.264911> nrow(a)[1] 7> ncol(a)[1] 5# 增加一列或一行# cbind: column bind> cbind(a, 1:7) [,1] [,2] [,3] [,4] [,5] [,6][1,] -0.4125356 0.1219293 -0.4763589 -0.9717165 1.09162243 1[2,] 1.8778966 -0.1171794 2.9295352 1.3383662 -0.03269026 2[3,] 0.8754092 0.1300574 0.1190069 0.7666394 0.28407356 3[4,] -0.9125118 0.1799797 0.5045226 0.2596132 -0.58052230 4[5,] 1.0000000 2.0000000 3.0000000 4.0000000 5.00000000 5[6,] 2.0000000 10.0000000 11.0000000 13.0000000 4.00000000 6[7,] -1.2649111 -0.6324555 0.0000000 0.6324555 1.26491106 7> cbind(a, seven=1:7) seven[1,] -0.4125356 0.1219293 -0.4763589 -0.9717165 1.09162243 1[2,] 1.8778966 -0.1171794 2.9295352 1.3383662 -0.03269026 2[3,] 0.8754092 0.1300574 0.1190069 0.7666394 0.28407356 3[4,] -0.9125118 0.1799797 0.5045226 0.2596132 -0.58052230 4[5,] 1.0000000 2.0000000 3.0000000 4.0000000 5.00000000 5[6,] 2.0000000 10.0000000 11.0000000 13.0000000 4.00000000 6[7,] -1.2649111 -0.6324555 0.0000000 0.6324555 1.26491106 7# rbind: row bind> rbind(a,1:5) [,1] [,2] [,3] [,4] [,5][1,] -0.4125356 0.1219293 -0.4763589 -0.9717165 1.09162243[2,] 1.8778966 -0.1171794 2.9295352 1.3383662 -0.03269026[3,] 0.8754092 0.1300574 0.1190069 0.7666394 0.28407356[4,] -0.9125118 0.1799797 0.5045226 0.2596132 -0.58052230[5,] 1.0000000 2.0000000 3.0000000 4.0000000 5.00000000[6,] 2.0000000 10.0000000 11.0000000 13.0000000 4.00000000[7,] -1.2649111 -0.6324555 0.0000000 0.6324555 1.26491106[8,] 1.0000000 2.0000000 3.0000000 4.0000000 5.00000000# 计算每一行的mad (中值绝对偏差，一般认为比方差的鲁棒性更强，更少受异常值的影响，更能反映数据间的差异)> apply(a,1,mad)[1] 0.7923976 2.0327283 0.2447279 0.4811672 1.4826000 4.4478000 0.9376786# 计算每一行的var (方差)# apply表示对数据（第一个参数）的每一行 (第二个参数赋值为1) 或每一列 (2)操作# 最后返回一个列表> apply(a,1,var)[1] 0.6160264 1.6811161 0.1298913 0.3659391 2.5000000 22.5000000 1.0000000# 计算每一列的平均值> apply(a,2,mean)[1] 0.4519068 1.6689045 2.4395294 2.7179083 1.5753421# 取出中值绝对偏差大于0.5的行> b = a[apply(a,1,mad)>0.5,]> b [,1] [,2] [,3] [,4] [,5][1,] -0.4125356 0.1219293 -0.4763589 -0.9717165 1.09162243[2,] 1.8778966 -0.1171794 2.9295352 1.3383662 -0.03269026[3,] 1.0000000 2.0000000 3.0000000 4.0000000 5.00000000[4,] 2.0000000 10.0000000 11.0000000 13.0000000 4.00000000[5,] -1.2649111 -0.6324555 0.0000000 0.6324555 1.26491106# 矩阵按照mad的大小降序排列> c = b[order(apply(b,1,mad), decreasing=T),]> c [,1] [,2] [,3] [,4] [,5][1,] 2.0000000 10.0000000 11.0000000 13.0000000 4.00000000[2,] 1.8778966 -0.1171794 2.9295352 1.3383662 -0.03269026[3,] 1.0000000 2.0000000 3.0000000 4.0000000 5.00000000[4,] -1.2649111 -0.6324555 0.0000000 0.6324555 1.26491106[5,] -0.4125356 0.1219293 -0.4763589 -0.9717165 1.09162243> rownames(c) colnames(c) c A B C D EGene_a 2.0000000 10.0000000 11.0000000 13.0000000 4.00000000Gene_b 1.8778966 -0.1171794 2.9295352 1.3383662 -0.03269026Gene_c 1.0000000 2.0000000 3.0000000 4.0000000 5.00000000Gene_d -1.2649111 -0.6324555 0.0000000 0.6324555 1.26491106Gene_e -0.4125356 0.1219293 -0.4763589 -0.9717165 1.09162243# 矩阵转置> expr = t(c)> expr Gene_a Gene_b Gene_c Gene_d Gene_eA 2 1.87789657 1 -1.2649111 -0.4125356B 10 -0.11717937 2 -0.6324555 0.1219293C 11 2.92953522 3 0.0000000 -0.4763589D 13 1.33836620 4 0.6324555 -0.9717165E 4 -0.03269026 5 1.2649111 1.0916224# 矩阵值的替换> expr2 = expr> expr2[expr2 expr2 Gene_a Gene_b Gene_c Gene_d Gene_eA 2 1.877897 1 0.0000000 0.0000000B 10 0.000000 2 0.0000000 0.1219293C 11 2.929535 3 0.0000000 0.0000000D 13 1.338366 4 0.6324555 0.0000000E 4 0.000000 5 1.2649111 1.0916224# 矩阵中只针对某一列替换# expr2是个矩阵不是数据框，不能使用列名字索引> expr2[expr2$Gene_b expr2 str(expr2)’data.frame’: 5 obs. of 5 variables: $ Gene_a: num 2 10 11 13 4 $ Gene_b: num 1.88 1 2.93 1.34 1 $ Gene_c: num 1 2 3 4 5 $ Gene_d: num 0 0 0 0.632 1.265 $ Gene_e: num 0 0.122 0 0 1.092> expr2[expr2$Gene_b expr2 Gene_a Gene_b Gene_c Gene_d Gene_eA 2 1.877897 1 0.0000000 0.0000000B 10 1.000000 2 0.0000000 0.1219293C 11 2.929535 3 0.0000000 0.0000000D 13 1.338366 4 0.6324555 0.0000000E 4 1.000000 5 1.2649111 1.0916224
R中矩阵筛选合并
# 读入样品信息> sampleInfo = “Samp;Group;Genotype+ A;Control;WT+ B;Control;WT+ D;Treatment;Mutant+ C;Treatment;Mutant+ E;Treatment;WT+ F;Treatment;WT”> phenoData = read.table(text=sampleInfo,sep=”;”, header=T, row.names=1, quote=””)> phenoData Group GenotypeA Control WTB Control WTD Treatment MutantC Treatment MutantE Treatment WTF Treatment WT# 把样品信息按照基因表达矩阵中的样品信息排序，并只保留有基因表达信息的样品# match() returns a vector of the positions of (first) matches of its first argument in its second.> phenoData[match(rownames(expr), rownames(phenoData)),] Group GenotypeA Control WTB Control WTC Treatment MutantD Treatment MutantE Treatment WT# ‘%in%’ is a more intuitive interface as a binary operator, which returns a logical vector indicating if there is a match or not for its left operand.# 注意顺序，%in%比match更好理解一些> phenoData = phenoData[rownames(phenoData) %in% rownames(expr),]> phenoData Group GenotypeA Control WTB Control WTC Treatment MutantD Treatment MutantE Treatment WT# 合并矩阵# by=0 表示按照行的名字排序# by=columnname 表示按照共有的某一列排序# 合并后多出了新的一列Row.names> merge_data = merge(expr, phenoData, by=0, all.x=T)> merge_data Row.names Gene_a Gene_b Gene_c Gene_d Gene_e Group Genotype1 A 2 1.87789657 1 -1.2649111 -0.4125356 Control WT2 B 10 -0.11717937 2 -0.6324555 0.1219293 Control WT3 C 11 2.92953522 3 0.0000000 -0.4763589 Treatment Mutant4 D 13 1.33836620 4 0.6324555 -0.9717165 Treatment Mutant5 E 4 -0.03269026 5 1.2649111 1.0916224 Treatment WT> rownames(merge_data) merge_data Row.names Gene_a Gene_b Gene_c Gene_d Gene_e Group GenotypeA A 2 1.87789657 1 -1.2649111 -0.4125356 Control WTB B 10 -0.11717937 2 -0.6324555 0.1219293 Control WTC C 11 2.92953522 3 0.0000000 -0.4763589 Treatment MutantD D 13 1.33836620 4 0.6324555 -0.9717165 Treatment MutantE E 4 -0.03269026 5 1.2649111 1.0916224 Treatment WT# 去除一列；-1表示去除第一列> merge_data = merge_data[,-1]> merge_data Gene_a Gene_b Gene_c Gene_d Gene_e Group GenotypeA 2 1.87789657 1 -1.2649111 -0.4125356 Control WTB 10 -0.11717937 2 -0.6324555 0.1219293 Control WTC 11 2.92953522 3 0.0000000 -0.4763589 Treatment MutantD 13 1.33836620 4 0.6324555 -0.9717165 Treatment MutantE 4 -0.03269026 5 1.2649111 1.0916224 Treatment WT# 提取出所有的数值列> merge_data[sapply(merge_data, is.numeric)] Gene_a Gene_b Gene_c Gene_d Gene_eA 2 1.87789657 1 -1.2649111 -0.4125356B 10 -0.11717937 2 -0.6324555 0.1219293C 11 2.92953522 3 0.0000000 -0.4763589D 13 1.33836620 4 0.6324555 -0.9717165E 4 -0.03269026 5 1.2649111 1.0916224
str的应用
str: Compactly display the internal structure of an R object, a diagnostic function and an alternative to ‘summary (and to some extent, ‘dput’). Ideally, only one line for each ‘basic’ structure is displayed. It is especially well suited to compactly display the (abbreviated) contents of (possibly nested) lists. The idea is to give reasonable output for any R object. It calls ‘args’ for (non-primitive) function objects.
str用来告诉结果的构成方式，对于不少Bioconductor的包，或者复杂的R函数的输出，都是一堆列表的嵌套，str(complex_result)会输出每个列表的名字，方便提取对应的信息。
# str的一个应用例子> str(list(a = “A”, L = as.list(1:100)), list.len = 9)List of 2 $ a: chr “A” $ L:List of 100 ..$ : int 1 ..$ : int 2 ..$ : int 3 ..$ : int 4 ..$ : int 5 ..$ : int 6 ..$ : int 7 ..$ : int 8 ..$ : int 9 .. [list output truncated]# 利用str查看pca的结果，具体的PCA应用查看http://mp.weixin.qq.com/s/sRElBMkyR9rGa4TQp9KjNQ> pca_result pca_resultStandard deviations:[1] 4.769900e+00 1.790861e+00 1.072560e+00 1.578391e-01 2.752128e-16Rotation: PC1 PC2 PC3 PC4 PC5Gene_a 0.99422750 -0.02965529 0.078809521 0.01444655 0.06490461Gene_b 0.04824368 -0.44384942 -0.885305329 0.03127940 0.12619948Gene_c 0.08258192 0.81118590 -0.451360828 0.05440417 -0.35842886Gene_d -0.01936958 0.30237826 -0.079325524 -0.66399283 0.67897952Gene_e -0.04460135 0.22948437 -0.002097256 0.74496081 0.62480128> str(pca_result)List of 5 $ sdev : num [1:5] 4.77 1.79 1.07 1.58e-01 2.75e-16 $ rotation: num [1:5, 1:5] 0.9942 0.0482 0.0826 -0.0194 -0.0446 … ..- attr(*, “dimnames”)=List of 2 .. ..$ : chr [1:5] “Gene_a” “Gene_b” “Gene_c” “Gene_d” … .. ..$ : chr [1:5] “PC1” “PC2” “PC3” “PC4” … $ center : Named num [1:5] 8 1.229 3 0.379 0.243 ..- attr(*, “names”)= chr [1:5] “Gene_a” “Gene_b” “Gene_c” “Gene_d” … $ scale : logi FALSE $ x : num [1:5, 1:5] -6.08 1.86 3.08 5.06 -3.93 … ..- attr(*, “dimnames”)=List of 2 .. ..$ : chr [1:5] “A” “B” “C” “D” … .. ..$ : chr [1:5] “PC1” “PC2” “PC3” “PC4” … – attr(*, “class”)= chr “prcomp”# 取出每个主成分解释的差异> pca_result$sdev[1] 4.769900e+00 1.790861e+00 1.072560e+00 1.578391e-01 2.752128e-16
R的包管理
# 什么时候需要安装包> library(‘unExistedPackage’)Error in library(“unExistedPackage”) : 不存在叫‘unExistedPackage’这个名字的程辑包# 安装包> install.packages(“package_name”)# 指定安装来源> install.packages(“package_name”, repo=”http://cran.us.r-project.org”)# 安装Bioconductor的包> source(‘https://bioconductor.org/biocLite.R’)> biocLite(‘BiocInstaller’)> biocLite(c(“RUVSeq”,”pcaMethods”))# 安装Github的R包> install.packages(“devtools”)> devtools::install_github(“JustinaZ/pcaReduce”)# 手动安装, 首先下载包的源文件（压缩版就可），然后在终端运行下面的命令。ct@ehbio:~$ R CMD INSTALL package.tar.gz# 移除包>remove.packages(“package_name”)# 查看所有安装的包>library()# 查看特定安装包的版本> installed.packages()[c(“DESeq2”), c(“Package”, “Version”)] Package Version “DESeq2” “1.14.1” > # 查看默认安装包的位置>.libPaths()# 调用安装的包>library(package_name)#devtools::install_github(“hms-dbmi/scde”, build_vignettes = FALSE)#install.packages(c(“mvoutlier”,”ROCR”))#biocLite(c(“RUVSeq”,”pcaMethods”,”SC3″,”TSCAN”,”monocle”,”MultiAssayExperiment”,”SummarizedExperiment”))#devtools::install_github(“satijalab/seurat”)
