❞过节前依然在更新。最近好几个小伙伴都在用我们之前的一个bulk RNA多组差异分析函数(重启之普通R转录组分析(3)：写一个通用的Deseq2多组差异分析函数)，有些小问题，或者说一些功能不完善。所以我们这次进行了升级和优化。首先将bulk差异分析3大包DEseq2  edgeR  limma都纳入进来了。第二，让您的分析更加简单，不用担心复杂的代码和分组设置(很多时候还搞错谁vs谁)。第三, 不论你的两组样本重复数是否相同，都可以进行(无重复样本分析没有，主要是我认为你算法再优化，也清除不了个体差异随机性)。第四，多组样本的分析！轻松化解！  相信随着目前bulk的普及和便宜化，我们这个函数还是很有用的！完整版函数及数据已发布微信VIP，请自行下载！视频链接如下（复制到浏览器打开）：https://www.bilibili.com/video/BV1n2421A7oJ/?spm_id_from=333.999.0.0&vd_source=05b5479545ba945a8f5d7b2e7160ea34首先我们看一下函数的参数，也是很简洁：

图片

然后我们测试一下：首先是两组等重复样本，很简单！

setwd('D:\\KS项目\\公众号文章\\Bulk多组差异基因分析函数')#一、两组分析（样本数相等）-------------------------------------------------------------------df1 <- read.csv("Two_group.csv", header = T, row.names = 1)colnames(df1)# [1] "Cancer1" "Cancer2" "Cancer3" "Health1" "Health2" "Health3"meta1 <- data.frame(Cancer=c("Cancer1" ,"Cancer2" ,"Cancer3"),                    Health=c("Health1", "Health2", "Health3"))deg1_Deseq2 <- KS_bulkRNA_MultiGroup_DEGs(exprSet = df1,                                          meta = meta1,                                          methods = "DESeq2",                                          test = "Cancer",                                          control = "Health",                                          repNum1 = 3,                                          repNum2 = 3)deg1_edgeR <- KS_bulkRNA_MultiGroup_DEGs(exprSet = df1,                                          meta = meta1,                                          methods = "edgeR",                                          test = "Cancer",                                          control = "Health",                                          repNum1 = 3,                                          repNum2 = 3)deg1_limma <- KS_bulkRNA_MultiGroup_DEGs(exprSet = df1,                                         meta = meta1,                                         methods = "limma",                                         test = "Cancer",                                         control = "Health",                                         repNum1 = 3,                                         repNum2 = 3)

重复数不等的两组样本分析也是如此，只要设置好test和control即可：

#二、两组分析（样本数不同）-------------------------------------------------------------------df4 <- read.csv("two_diff_group.csv", header = T, row.names = 1)colnames(df4)# [1] "HC_1"  "HC_2"  "HC_3"  "HC_4"  "PPC_1" "PPC_2" "PPC_3" "PPC_4" "PPC_5" "PPC_6"meta4 <- data.frame(HC=c("HC_1","HC_2","HC_3","HC_4","",""),                    PPC=c("PPC_1","PPC_2","PPC_3","PPC_4","PPC_5","PPC_6"))deg4_Deseq2 <- KS_bulkRNA_MultiGroup_DEGs(exprSet = df4,                                          meta = meta4,                                          methods = "DESeq2",                                          test = "PPC",                                          control = "HC",                                          repNum1 = 6,                                          repNum2 = 4)deg4_edgeR <- KS_bulkRNA_MultiGroup_DEGs(exprSet = df4,                                          meta = meta4,                                          methods = "edgeR",                                          test = "PPC",                                          control = "HC",                                          repNum1 = 6,                                          repNum2 = 4)deg4_limma <- KS_bulkRNA_MultiGroup_DEGs(exprSet = df4,                                         meta = meta4,                                         methods = "limma",                                         test = "PPC",                                         control = "HC",                                         repNum1 = 6,                                         repNum2 = 4)

我们可以对比下三种方法差异基因结果，发现肯定不是完全一样，那是因为算法不一样，不用纠结。在我们这个数据里面可以看出，DEseq2和edgeR的结果重合还是挺多的。

#韦恩图deg4_Deseq2_sig <- deg4_Deseq2[which(abs(deg4_Deseq2$log2FoldChange)>0 & deg4_Deseq2$pvalue <=0.05),]deg4_edgeR_sig <- deg4_edgeR[which(abs(deg4_edgeR$logFC)>0 & deg4_edgeR$PValue <=0.05),]deg4_limma_sig <- deg4_limma[which(abs(deg4_limma$logFC)>0 & deg4_limma$P.Value <=0.05),]library(ggvenn)library(tidyverse)Venn_list <- list(deg4_Deseq2_sig=rownames(deg4_Deseq2_sig),                  deg4_edgeR_sig=rownames(deg4_edgeR_sig),                  deg4_limma_sig=rownames(deg4_limma_sig))#使用list_to_data_frame将list转化为data.framedata_veen = list_to_data_frame(Venn_list)ggvenn(Venn_list,       show_percentage = T,       show_elements = F,       text_size=3,       digits = 1,       set_name_size=4,       stroke_color = "grey30",       fill_color = c("#FF8C00","#4DAF4A","#B64E89"),       set_name_color = c("#FF8C00","#4DAF4A","#B64E89"))

图片

多组样本的分析就更简单了：大多设置都设置好了。这里需要强调一点，那就是对于多组样本，在进行meta设置的时候，test组靠前，control靠后！

#四、多组test------------------------------------------------------------------df3 <- read.csv("count_gene.csv", header = T, row.names = 1, check.names = F)colnames(df3)# [1] "Fbrain 1" "Fbrain 2" "Fbrain 3" "Fbrain 4" "Fhom 1"   "Fhom 2"   "Fhom 3"  # [8] "Mbrain 1" "Mbrain 2" "Mbrain 3" "Mbrain 4" "Mbrain 5" "Mhom 1"   "Mhom 2"  # [15] "Mhom 3"   "Mhom 4" meta3 <- data.frame(Mhom = c("Mhom 1","Mhom 2", "Mhom 3","Mhom 4",""),                    Fhom  = c("Fhom 1","Fhom 2","Fhom 3","",""),                    Mbrain=c("Mbrain 1","Mbrain 2","Mbrain 3","Mbrain 4","Mbrain 5"),                    Fbrain=c("Fbrain 1","Fbrain 2","Fbrain 3","Fbrain 4",""))deg3_Deseq2 <- KS_bulkRNA_MultiGroup_DEGs(exprSet = df3,                                          meta = meta3,                                          methods = "DESeq2",                                          separator=" ")deg3_edgeR <- KS_bulkRNA_MultiGroup_DEGs(exprSet = df3,                                         meta = meta3,                                         methods = "edgeR",                                         separator=" ")deg3_limma <- KS_bulkRNA_MultiGroup_DEGs(exprSet = df3,                                         meta = meta3,                                         methods = "limma",                                         separator=" ")

图片

本站仅提供存储服务，所有内容均由用户发布，如发现有害或侵权内容，请点击举报。