2021-06-28 Rstdio中DESeq2相关软件的安装

#首先升级R

install.packages("installr")

library(installr)

updateR()

library("BiocManager")

#Bioconductor version 3.12 (BiocManager 1.30.15), R 4.0.5 (2021-03-31) Bioconductor version '3.12' is out-of-date; the current release version '3.13' is available with R version '4.1'; see https://bioconductor.org/install

#重新更新Bioconductor

if (!requireNamespace("BiocManager", quietly = TRUE))

  install.packages("BiocManager")

BiocManager::install(version = "3.13")

#更新成功

library("BiocManager")

#通过BiocManager安装我们常用的R包

BiocManager::install("ggplot2")

BiocManager::install(c("ggplot2","ggtree","DESeq2"))

#一次安装多个包

BiocManager::install("DESeq2")

#错误: 无法载入程辑包‘GenomeInfoDb’

BiocManager::install("GenomeInfoDbData")

#测试软件DESeq2

library("DESeq2")

#开始，DESeq2包分析差异表达基因简单来说只有三步：构建dds矩阵，标准化，以及进行差异分析。

library(DESeq2)  #加载包

library(apeglm)

#Error in library(apeglm) : 不存在叫‘apeglm’这个名字的程辑包

BiocManager::install("apeglm")

####测试

library(DESeq2)  #加载包

library(apeglm)

安装成功。

以下为差异基因表达分析的相关脚本：

pvalue(pval): 统计学差异显著性检验指标。

qvalue(p-adjusted): 校正后的p值（qvalue=padj=FDR=Corrected p-Value=p-adjusted），是对p值进行了多重假设检验，能更好地控制假阳性率。

校正后的p值不同的几种表现形式，都是基于BH的方法进行多重假设检验得到的。校正后的p值不同的展现形式是因为不同的分析软件产生的。

作者：村长吃火锅

链接：https://www.jianshu.com/p/b1f6b50fde0e

来源：简书 著作权归作者所有。商业转载请联系作者获得授权，非商业转载请注明出处。

E:/SolPanTP/RawData/诺禾转录组测序（310）/05 数据分析/DESeq2/log2FC+p value/pi/pi_24 vs 0/

E:/SolPanTP/RawData/诺禾转录组测序（310）/05 数据分析/DESeq2/log2FC+p value/pi/pi_48 vs 0/

E:/SolPanTP/RawData/诺禾转录组测序（310）/05 数据分析/DESeq2/log2FC+p value/pi/pi_48 vs 24/

致病疫霉

###############################################################################################

library(DESeq2)  #加载包

library(apeglm)

data.pi_Sae24 = read.table("E:/SolPanTP/RawData/诺禾转录组测序（310）/05 数据分析/DESeq2/log2FC+p value/pi/pi_24 vs 0/pi_Sae24_count.csv",sep = ',',header = T,row.names = 1)

data.pi_Sly24 = read.table("E:/SolPanTP/RawData/诺禾转录组测序（310）/05 数据分析/DESeq2/log2FC+p value/pi/pi_24 vs 0/pi_Sly24_count.csv",sep = ',',header = T,row.names = 1)

data.pi_Sme24 = read.table("E:/SolPanTP/RawData/诺禾转录组测序（310）/05 数据分析/DESeq2/log2FC+p value/pi/pi_24 vs 0/pi_Sme24_count.csv",sep = ',',header = T,row.names = 1)

data.pi_Stu24 = read.table("E:/SolPanTP/RawData/诺禾转录组测序（310）/05 数据分析/DESeq2/log2FC+p value/pi/pi_24 vs 0/pi_Stu24_count2.csv",sep = ',',header = T,row.names = 1)

condition.pi_Sae24 <- factor(c(rep('0',3),rep('24',5)),levels = c("0","24"))

condition.pi_Sly24 <- factor(c(rep('0',3),rep('24',5)),levels = c("0","24"))

condition.pi_Sme24 <- factor(c(rep('0',3),rep('24',5)),levels = c("0","24"))

condition.pi_Stu24 <- factor(c(rep('0',3),rep('24',5)),levels = c("0","24"))

colData.pi_Sae24 = data.frame(row.names= colnames(data.pi_Sae24),condition.pi_Sae24)

colData.pi_Sly24 = data.frame(row.names= colnames(data.pi_Sly24),condition.pi_Sly24)

colData.pi_Sme24 = data.frame(row.names= colnames(data.pi_Sme24),condition.pi_Sme24)

colData.pi_Stu24 = data.frame(row.names= colnames(data.pi_Stu24),condition.pi_Stu24)

dds.pi_Sae24 <- DESeqDataSetFromMatrix(data.pi_Sae24,colData.pi_Sae24,design = ~ condition.pi_Sae24)

dds.pi_Sly24 <- DESeqDataSetFromMatrix(data.pi_Sly24,colData.pi_Sly24,design = ~ condition.pi_Sly24)

dds.pi_Sme24 <- DESeqDataSetFromMatrix(data.pi_Sme24,colData.pi_Sme24,design = ~ condition.pi_Sme24)

dds.pi_Stu24 <- DESeqDataSetFromMatrix(data.pi_Stu24,colData.pi_Stu24,design = ~ condition.pi_Stu24)

dds.pi_Sae24 <-DESeq(dds.pi_Sae24)

resultsNames(dds.pi_Sae24)

dds.pi_Sly24 <-DESeq(dds.pi_Sly24)

resultsNames(dds.pi_Sly24)

dds.pi_Sme24 <-DESeq(dds.pi_Sme24)

resultsNames(dds.pi_Sme24)

dds.pi_Stu24 <-DESeq(dds.pi_Stu24)

resultsNames(dds.pi_Stu24)

res.pi_Sae24.24.0 = results(dds.pi_Sae24,contrast=c("condition.pi_Sae24","24","0"))

res.pi_Sly24.24.0 = results(dds.pi_Sly24,contrast=c("condition.pi_Sly24","24","0"))

res.pi_Sme24.24.0 = results(dds.pi_Sme24,contrast=c("condition.pi_Sme24","24","0"))

res.pi_Stu24.24.0 = results(dds.pi_Stu24,contrast=c("condition.pi_Stu24","24","0"))

order.res.pi_Sae24.24.0 <- res.pi_Sae24.24.0[order(res.pi_Sae24.24.0$pvalue),]

order.res.pi_Sly24.24.0 <- res.pi_Sly24.24.0[order(res.pi_Sly24.24.0$pvalue),]

order.res.pi_Sme24.24.0 <- res.pi_Sme24.24.0[order(res.pi_Sme24.24.0$pvalue),]

order.res.pi_Stu24.24.0 <- res.pi_Stu24.24.0[order(res.pi_Stu24.24.0$pvalue),]

setwd("E:/SolPanTP/RawData/诺禾转录组测序（310）/05 数据分析/DESeq2/log2FC+p value/pi/pi_24 vs 0")

write.csv(order.res.pi_Sae24.24.0,file = "order.res.pi_Sae24.24.0.csv",quote = F)

write.csv(order.res.pi_Sly24.24.0,file = "order.res.pi_Sly24.24.0.csv",quote = F)

write.csv(order.res.pi_Sme24.24.0,file = "order.res.pi_Sme24.24.0.csv",quote = F)

write.csv(order.res.pi_Stu24.24.0,file = "order.res.pi_Stu24.24.0.csv",quote = F)

diffgene_pi_Sae24.24.0_deseq2 <- subset(order.res.pi_Sae24.24.0,padj < 0.01 & abs(log2FoldChange) >2)

diffgene_pi_Sly24.24.0_deseq2 <- subset(order.res.pi_Sly24.24.0,padj < 0.01 & abs(log2FoldChange) >2)

diffgene_pi_Sme24.24.0_deseq2 <- subset(order.res.pi_Sme24.24.0,padj < 0.01 & abs(log2FoldChange) >2)

diffgene_pi_Stu24.24.0_deseq2 <- subset(order.res.pi_Stu24.24.0,padj < 0.01 & abs(log2FoldChange) >2)

write.csv(diffgene_pi_Sae24.24.0_deseq2,file = "diffgene_pi_Sae24.24.0_deseq2.csv",quote = F)

write.csv(diffgene_pi_Sly24.24.0_deseq2,file = "diffgene_pi_Sly24.24.0_deseq2.csv",quote = F)

write.csv(diffgene_pi_Sme24.24.0_deseq2,file = "diffgene_pi_Sme24.24.0_deseq2.csv",quote = F)

write.csv(diffgene_pi_Stu24.24.0_deseq2,file = "diffgene_pi_Stu24.24.0_deseq2.csv",quote = F)