TCGA 02 不同数据DEG结果取交集火山图及韦恩图展示

1. 三个数据集差异基因火山图（每10个肿瘤和正常组织样本）

导入表达矩阵，选择NT组的前10和TP组的前10个样本进行差异分析

library(TCGAbiolinks)
# 导入dataFilt表达矩阵
load("dataFilt.RData")

# selection of normal samples "NT"
samplesNT <- TCGAquery_SampleTypes(barcode = colnames(dataFilt),
                                   typesample = c("NT"))
# selection of tumor samples "TP"
samplesTP <- TCGAquery_SampleTypes(barcode = colnames(dataFilt), 
                                   typesample = c("TP"))
# Diff.expr.analysis (DEA)
DEG.LUAD.edgeR <- TCGAanalyze_DEA(mat1 = dataFilt[,samplesNT[1:10]],
                                  mat2 = dataFilt[,samplesTP[1:10]],
                                  pipeline="edgeR",
                                  batch.factors = c("TSS"),
                                  Cond1type = "Normal",
                                  Cond2type = "Tumor",
                                  voom =FALSE, 
                                  method = "glmLRT",
                                  # fdr.cut = 0.01,  #保留FDR<0.01的基因
                                  # logFC.cut = 1 #保留logFC＞1的基因
)
# ----------------------- DEA -------------------------------
#   there are Cond1 type Normal in  10 samples
# there are Cond2 type Tumor in  10 samples
# there are  12980 features as miRNA or genes 
# I Need about  8.7 seconds for this DEA. [Processing 30k elements /s]  
# ----------------------- END DEA -------------------------------

绘制第一个火山图

valcano_data <- data.frame(genes=rownames(DEG.LUAD.edgeR), 
                           logFC=DEG.LUAD.edgeR$logFC, 
                           FDR=DEG.LUAD.edgeR$FDR,
                           group=rep("NotSignificant", 
                                     nrow(DEG.LUAD.edgeR)),
                           stringsAsFactors = F)

valcano_data[which(valcano_data['FDR'] < 0.05 & 
                     valcano_data['logFC'] > 1.5),"group"] <- "Increased"
valcano_data[which(valcano_data['FDR'] < 0.05 &
                     valcano_data['logFC'] < -1.5),"group"] <- "Decreased"

cols = c("darkgrey","#00B2FF","orange")
names(cols) = c("NotSignificant","Increased","Decreased")

library(ggplot2)
vol1 <- ggplot(valcano_data, aes(x = logFC, y = -log10(FDR), color = group))+
  scale_colour_manual(values = cols) +
  ggtitle(label = "Volcano Plot 1", subtitle = "LUAD 1-10 samples volcano plot") +
  geom_point(size = 2.5, alpha = 1, na.rm = T) +
  theme_bw(base_size = 14) + 
  theme(legend.position = "right") + 
  xlab(expression(log[2]("logFC"))) + 
  ylab(expression(-log[10]("FDR"))) +
  geom_hline(yintercept = 1.30102, colour="#990000", linetype="dashed") + 
  geom_vline(xintercept = 1.5849, colour="#990000", linetype="dashed") + 
  geom_vline(xintercept = -1.5849, colour="#990000", linetype="dashed")+ 
  scale_y_continuous(trans = "log1p")

选择NT组的11-20和TP组的11-20样本进行差异分析

# Diff.expr.analysis (DEA)
DEG.LUAD.edgeR2 <- TCGAanalyze_DEA(mat1 = dataFilt[,samplesNT[11:20]],
                                  mat2 = dataFilt[,samplesTP[11:20]],
                                  pipeline="edgeR",
                                  batch.factors = c("TSS"),
                                  Cond1type = "Normal",
                                  Cond2type = "Tumor",
                                  voom =FALSE, 
                                  method = "glmLRT",
                                  # fdr.cut = 0.01,  #保留FDR<0.01的基因
                                  # logFC.cut = 1 #保留logFC＞1的基因
)
# ----------------------- DEA -------------------------------
#   there are Cond1 type Normal in  10 samples
# there are Cond2 type Tumor in  10 samples
# there are  12980 features as miRNA or genes 
# I Need about  8.7 seconds for this DEA. [Processing 30k elements /s]  
# ----------------------- END DEA -------------------------------

绘制第2个火山图

valcano_data2 <- data.frame(genes=rownames(DEG.LUAD.edgeR2), 
                           logFC=DEG.LUAD.edgeR2$logFC, 
                           FDR=DEG.LUAD.edgeR2$FDR,
                           group=rep("NotSignificant", 
                                     nrow(DEG.LUAD.edgeR2)),
                           stringsAsFactors = F)

valcano_data2[which(valcano_data2['FDR'] < 0.05 & 
                     valcano_data2['logFC'] > 1.5),"group"] <- "Increased"
valcano_data2[which(valcano_data2['FDR'] < 0.05 &
                     valcano_data2['logFC'] < -1.5),"group"] <- "Decreased"

cols = c("darkgrey","#00B2FF","orange")
names(cols) = c("NotSignificant","Increased","Decreased")

library(ggplot2)
vol2 <- ggplot(valcano_data2, aes(x = logFC, y = -log10(FDR), color = group))+
  scale_colour_manual(values = cols) +
  ggtitle(label = "Volcano Plot 2", subtitle = "LUAD 11-20 volcano plot") +
  geom_point(size = 2.5, alpha = 1, na.rm = T) +
  theme_bw(base_size = 14) + 
  theme(legend.position = "right") + 
  xlab(expression(log[2]("logFC"))) + 
  ylab(expression(-log[10]("FDR"))) +
  geom_hline(yintercept = 1.30102, colour="#990000", linetype="dashed") + 
  geom_vline(xintercept = 1.5849, colour="#990000", linetype="dashed") + 
  geom_vline(xintercept = -1.5849, colour="#990000", linetype="dashed")+ 
  scale_y_continuous(trans = "log1p")

选择NT组的21-30和TP组的21-30样本进行差异分析

# Diff.expr.analysis (DEA)
DEG.LUAD.edgeR3 <- TCGAanalyze_DEA(mat1 = dataFilt[,samplesNT[21:30]],
                                  mat2 = dataFilt[,samplesTP[21:30]],
                                  pipeline="edgeR",
                                  batch.factors = c("TSS"),
                                  Cond1type = "Normal",
                                  Cond2type = "Tumor",
                                  voom =FALSE, 
                                  method = "glmLRT",
                                  # fdr.cut = 0.01,  #保留FDR<0.01的基因
                                  # logFC.cut = 1 #保留logFC＞1的基因
)
# ----------------------- DEA -------------------------------
#   there are Cond1 type Normal in  10 samples
# there are Cond2 type Tumor in  10 samples
# there are  12980 features as miRNA or genes 
# I Need about  8.7 seconds for this DEA. [Processing 30k elements /s]  
# ----------------------- END DEA -------------------------------

绘制第3个火山图

valcano_data3 <- data.frame(genes=rownames(DEG.LUAD.edgeR3), 
                            logFC=DEG.LUAD.edgeR3$logFC, 
                            FDR=DEG.LUAD.edgeR3$FDR,
                            group=rep("NotSignificant", 
                                      nrow(DEG.LUAD.edgeR3)),
                            stringsAsFactors = F)

valcano_data3[which(valcano_data3['FDR'] < 0.05 & 
                     valcano_data3['logFC'] > 1.5),"group"] <- "Increased"
valcano_data3[which(valcano_data3['FDR'] < 0.05 &
                     valcano_data3['logFC'] < -1.5),"group"] <- "Decreased"

cols = c("darkgrey","#00B2FF","orange")
names(cols) = c("NotSignificant","Increased","Decreased")

library(ggplot2)
vol3 <- ggplot(valcano_data3, aes(x = logFC, y = -log10(FDR), color = group))+
  scale_colour_manual(values = cols) +
  ggtitle(label = "Volcano Plot 3", subtitle = "LUAD 21-30 volcano plot") +
  geom_point(size = 2.5, alpha = 1, na.rm = T) +
  theme_bw(base_size = 14) + 
  theme(legend.position = "right") + 
  xlab(expression(log[2]("logFC"))) + 
  ylab(expression(-log[10]("FDR"))) +
  geom_hline(yintercept = 1.30102, colour="#990000", linetype="dashed") + 
  geom_vline(xintercept = 1.5849, colour="#990000", linetype="dashed") + 
  geom_vline(xintercept = -1.5849, colour="#990000", linetype="dashed")+ 
  scale_y_continuous(trans = "log1p")
library(cowplot)
library(patchwork)
vol1+vol2+vol3
3个火山图合并

2. upset图和韦恩图分析

提取3个数据的差异基因列表

DEG1_up <- valcano_data[valcano_data$group=="Increased", "genes"]
DEG1_down <- valcano_data[valcano_data$group=="Decreased", "genes"]

DEG2_up <- valcano_data[valcano_data2$group=="Increased", "genes"]
DEG2_down <- valcano_data[valcano_data2$group=="Decreased", "genes"]

DEG3_up <- valcano_data[valcano_data3$group=="Increased", "genes"]
DEG3_down <- valcano_data[valcano_data3$group=="Decreased", "genes"]

用Y叔开发的ggupset做Upset图

# devtools::install_github("GuangchuangYu/yyplot")
# devtools::install_github("GuangchuangYu/UpSetR")
# install.packages("venneuler")
# remove.packages("ggplot2")
# install.packages("ggimage")
# if (!requireNamespace("BiocManager", quietly = TRUE))
#     install.packages("BiocManager")
# BiocManager::install("ComplexHeatmap")

# 上调基因
lt_up = list(TCGA_1 = DEG1_up,
             TCGA_2 = DEG2_up,
             TCGA_3 = DEG3_up)
dat_up<- ComplexHeatmap::list_to_matrix(lt_up)
dat_plot_up <-  data.frame(dat_up)

require(UpSetR)
p1 <- upset(dat_plot_up, sets=c("TCGA_3", "TCGA_2", "TCGA_1"),
  keep.order = TRUE)
require(ggplotify)
g1 <- as.ggplot(p1) + ggtitle("Up regulated")


# 下调基因
lt_down = list(TCGA_1 = DEG1_down,
               TCGA_2 = DEG2_down,
               TCGA_3 = DEG3_down)
dat_down<- ComplexHeatmap::list_to_matrix(lt_down)
dat_plot_down <-  data.frame(dat_down)

require(UpSetR)
p2 <- upset(dat_plot_down, , sets=c("TCGA_3", "TCGA_2", "TCGA_1"),
            keep.order = TRUE)
require(ggplotify)
g2 <- as.ggplot(p2) + ggtitle("Down regulated")

# 拼图
library(cowplot)
library(patchwork)
g1+g2
upset图合并

做韦恩图

require(yyplot)
library("ggsci")
g3 <- ggvenn(dat_plot_up) + theme_void() +  
  scale_fill_jco() + ggtitle("Up regulated genes")
g4 <- ggvenn(dat_plot_down) + theme_void() +  
  scale_fill_jco() + ggtitle("Down regulated genes")
g3 + g4
韦恩图合并

upset和韦恩图拼接

require(ggimage)
g1_3 <- g1 + geom_subview(subview=g3+theme_void(), x=.78, y=.8, w=.5, h=.5)
g2_4 <- g2 + geom_subview(subview=g4+theme_void(), x=.78, y=.8, w=.5, h=.5)

g1_3+g2_4
upset和韦恩图合并

3. 火山图、upset图+韦恩图合并

(vol1|vol2|vol3)/
  (g1_3|g2_4)
火山图-韦恩图-upset图合并

挑选出三个数据集中共同上调或下调的基因

up_common <- Reduce(intersect, list(DEG1_up, DEG2_up, DEG3_up))
down_common <- Reduce(intersect, list(DEG1_down, DEG2_down, DEG3_down))
background_genes <- Reduce(union, list(DEG1_up, DEG2_up, DEG3_up,
                                       DEG1_down, DEG2_down, DEG3_down))
up_common_df <- data.frame(gene=up_common, 
                           logFC=valcano_data[valcano_data$genes %in% 
                                                up_common, 
                                              "logFC"])
down_common_df <- data.frame(gene=down_common, 
                             logFC=valcano_data[valcano_data$genes %in% 
                                                  down_common, 
                                                "logFC"])
background_genes_df <- data.frame(gene=background_genes, 
                              logFC=valcano_data[valcano_data$genes %in% 
                                                   background_genes, 
                                                 "logFC"], stringsAsFactors = F)
all_gene_df <- valcano_data[, c("genes", "logFC")]
save(list=c("up_common_df", "down_common_df", "background_genes_df", "all_gene_df"), 
     file="filtered_genes.RData")
最后编辑于 ：
©著作权归作者所有,转载或内容合作请联系作者
  • 人面猴
    序言：七十年代末，一起剥皮案震惊了整个滨河市，随后出现的几起案子，更是在滨河造成了极大的恐慌，老刑警刘岩，带你破解...
    沈念sama阅读 206,126评论 6赞 481
  • 死咒
    序言：滨河连续发生了三起死亡事件，死亡现场离奇诡异，居然都是意外死亡，警方通过查阅死者的电脑和手机，发现死者居然都...
    沈念sama阅读 88,254评论 2赞 382
  • 救了他两次的神仙让他今天三更去死
    文/潘晓璐 我一进店门，熙熙楼的掌柜王于贵愁眉苦脸地迎上来，“玉大人，你说我怎么就摊上这事。” “怎么了？”我有些...
    开封第一讲书人阅读 152,445评论 0赞 341
  • 道士缉凶录：失踪的卖姜人
    文/不坏的土叔 我叫张陵，是天一观的道长。 经常有香客问我，道长，这世上最难降的妖魔是什么？ 我笑而不...
    开封第一讲书人阅读 55,185评论 1赞 278
  • 港岛之恋（遗憾婚礼）
    正文 为了忘掉前任，我火速办了婚礼，结果婚礼上，老公的妹妹穿的比我还像新娘。我一直安慰自己，他们只是感情好，可当我...
    茶点故事阅读 64,178评论 5赞 371
  • 恶毒庶女顶嫁案：这布局不是一般人想出来的
    文/花漫 我一把揭开白布。 她就那样静静地躺着，像睡着了一般。 火红的嫁衣衬着肌肤如雪。 梳的纹丝不乱的头发上，一...
    开封第一讲书人阅读 48,970评论 1赞 284
  • 城市分裂传说
    那天，我揣着相机与录音，去河边找鬼。 笑死，一个胖子当着我的面吹牛，可吹牛的内容都是我干的。 我是一名探鬼主播，决...
    沈念sama阅读 38,276评论 3赞 399
  • 双鸳鸯连环套：你想象不到人心有多黑
    文/苍兰香墨 我猛地睁开眼，长吁一口气：“原来是场噩梦啊……” “哼！你这毒妇竟也来了？” 一声冷哼从身侧响起，我...
    开封第一讲书人阅读 36,927评论 0赞 259
  • 万荣杀人案实录
    序言：老挝万荣一对情侣失踪，失踪者是张志新（化名）和其女友刘颖，没想到半个月后，有当地人在树林里发现了一具尸体，经...
    沈念sama阅读 43,400评论 1赞 300
  • 护林员之死
    正文 独居荒郊野岭守林人离奇死亡，尸身上长有42处带血的脓包…… 初始之章·张勋 以下内容为张勋视角 年9月15日...
    茶点故事阅读 35,883评论 2赞 323
  • 白月光启示录
    正文 我和宋清朗相恋三年，在试婚纱的时候发现自己被绿了。 大学时的朋友给我发了我未婚夫和他白月光在一起吃饭的照片。...
    茶点故事阅读 37,997评论 1赞 333
  • 活死人
    序言：一个原本活蹦乱跳的男人离奇死亡，死状恐怖，灵堂内的尸体忽然破棺而出，到底是诈尸还是另有隐情，我是刑警宁泽，带...
    沈念sama阅读 33,646评论 4赞 322
  • 日本核电站爆炸内幕
    正文 年R本政府宣布，位于F岛的核电站，受9级特大地震影响，放射性物质发生泄漏。R本人自食恶果不足惜，却给世界环境...
    茶点故事阅读 39,213评论 3赞 307
  • 男人毒药：我在死后第九天来索命
    文/蒙蒙 一、第九天 我趴在偏房一处隐蔽的房顶上张望。 院中可真热闹，春花似锦、人声如沸。这庄子的主人今日做“春日...
    开封第一讲书人阅读 30,204评论 0赞 19
  • 一桩弑父案，背后竟有这般阴谋
    文/苍兰香墨 我抬头看了看天上的太阳。三九已至，却和暖如春，着一层夹袄步出监牢的瞬间，已是汗流浃背。 一阵脚步声响...
    开封第一讲书人阅读 31,423评论 1赞 260
  • 情欲美人皮
    我被黑心中介骗来泰国打工， 没想到刚下飞机就差点儿被人妖公主榨干…… 1. 我叫王不留，地道东北人。 一个月前我还...
    沈念sama阅读 45,423评论 2赞 352
  • 代替公主和亲
    正文 我出身青楼，却偏偏与公主长得像，于是被迫代替她去往敌国和亲。 传闻我的和亲对象是个残疾皇子，可洞房花烛夜当晚...
    茶点故事阅读 42,722评论 2赞 345