论文是
A giant NLR gene confers broad-spectrum resistance to Phytophthora sojae in soybean
image.png
论文里公布了大部分柱形图和箱线图的原始数据，今天的推文试着用论文中的数据模仿一下论文中的 Figure 2b c
image.png
Figure 2b 的数据
image.png
类似的图之前录制过视频进行介绍，如果习惯看视频的话可以关注下我的B站账号 小明的数据分析笔记本
image.png
首先读取数据
dfb<-read.csv("figure2b.csv",header=F)
dfb
宽格式数据转换为长格式
dfb %>%
pivot_longer(!V1) %>%
select(V1,value) %>%
na.omit() -> dfb.1
最基本的柱形图
library(ggplot2)
ggplot(data=dfb.1,aes(x=V1,y=value))+
stat_summary(geom = "bar",
fun = mean,
fill="#c6c3c3")
image.png
添加误差线
这里误差线采用的是mean+-sem
library(ggplot2)
ebtop<-function(x){
return(mean(x)+sd(x)/sqrt(length(x)))
}
ebbottom<-function(x){
return(mean(x)-sd(x)/sqrt(length(x)))
}
ggplot(data=dfb.1,aes(x=V1,y=value))+
stat_summary(geom = "bar",
fun = mean,
fill="#c6c3c3")+
stat_summary(geom = "errorbar",
fun.min = ebbottom,
fun.max = ebtop,
width=0.2)
image.png
添加图上的散点
library(ggplot2)
ebtop<-function(x){
return(mean(x)+sd(x))
}
ebbottom<-function(x){
return(mean(x)-sd(x))
}
ggplot(data=dfb.1,aes(x=V1,y=value))+
stat_summary(geom = "bar",
fun = mean,
fill="#c6c3c3")+
stat_summary(geom = "errorbar",
fun.min = ebbottom,
fun.max = ebtop,
width=0.2)+
geom_jitter(width = 0.3)
image.png
添加显著性p值
ggplot(data=dfb.1,aes(x=V1,y=value))+
stat_summary(geom = "bar",
fun = mean,
fill="#c6c3c3")+
stat_summary(geom = "errorbar",
fun.min = ebbottom,
fun.max = ebtop,
width=0.2)+
geom_jitter(width = 0.3)+
geom_signif(comparisons = list(c("Control","F5"),
c("Control","pAtUbi3:CDS-Rps11-1"),
c("Control","pAtUbi3:CDS-Rps11-2")),
test = t.test,
test.args = list(var.equal=T,
alternative="two.side"),
y_position = c(1.1,1.3,1.5),
#annotations = c(""),
parse = T)
image.png
如何在geom_signif()函数里调整P值的文字格式暂时想不到办法了，使用annotate()函数吧
ggplot(data=dfb.1,aes(x=V1,y=value))+
stat_summary(geom = "bar",
fun = mean,
fill="#c6c3c3")+
stat_summary(geom = "errorbar",
fun.min = ebbottom,
fun.max = ebtop,
width=0.2)+
geom_jitter(width = 0.3)+
geom_signif(comparisons = list(c("Control","F5"),
c("Control","pAtUbi3:CDS-Rps11-1"),
c("Control","pAtUbi3:CDS-Rps11-2")),
test = t.test,
test.args = list(var.equal=T,
alternative="two.side"),
y_position = c(1.1,1.3,1.5),
annotations = c(""),
parse = T)+
annotate(geom = "text",
x=1.5,y=1.15,
label=expression(italic(P)~'='~1.83%*%10^-6))+
annotate(geom = "text",
x=2,y=1.35,
label=expression(italic(P)~'='~2.71%*%10^-5))+
annotate(geom = "text",
x=2.5,y=1.55,
label=expression(italic(P)~'='~5.75%*%10^-8))
image.png
这里遇到的警告信息暂时搞不懂是什么意思了
image.png
接下来是细节的调整
ggplot(data=dfb.1,aes(x=V1,y=value))+
stat_summary(geom = "bar",
fun = mean,
fill="#c6c3c3")+
stat_summary(geom = "errorbar",
fun.min = ebbottom,
fun.max = ebtop,
width=0.2)+
geom_jitter(width = 0.3)+
geom_signif(comparisons = list(c("Control","F5"),
c("Control","pAtUbi3:CDS-Rps11-1"),
c("Control","pAtUbi3:CDS-Rps11-2")),
test = t.test,
test.args = list(var.equal=T,
alternative="two.side"),
y_position = c(1.1,1.3,1.5),
annotations = c(""),
parse = T)+
annotate(geom = "text",
x=1.5,y=1.15,
label=expression(italic(P)~'='~1.83%*%10^-6))+
annotate(geom = "text",
x=2,y=1.35,
label=expression(italic(P)~'='~2.71%*%10^-5))+
annotate(geom = "text",
x=2.5,y=1.55,
label=expression(italic(P)~'='~5.75%*%10^-8))+
scale_y_continuous(expand = c(0,0),
limits = c(0,1.6),
breaks = seq(0,1,0.2))+
theme_minimal()+
theme(panel.grid = element_blank(),
axis.line.y = element_line(),
axis.ticks.y = element_line(),
axis.title.y = element_text(hjust=0.25,
size=15),
axis.text.x = element_text(angle = 30,
hjust = 1,
size=10))+
guides(y=guide_axis_truncated(trunc_lower = 0,
trunc_upper = 1))+
labs(x=NULL,y="Survival Rate")
image.png
Figure 2c 的数据也有，大家可以试着用以上代码试着复现一下figure2c的数据
如果需要推文的示例数据和代码的话，直接给推文打赏1元。如果没有收到我回复的数据代码下载链接，可以加我的微信催我 ，我的微信是
mingyan24
欢迎大家关注我的公众号
小明的数据分析笔记本
小明的数据分析笔记本 公众号 主要分享：1、R语言和python做数据分析和数据可视化的简单小例子；2、园艺植物相关转录组学、基因组学、群体遗传学文献阅读笔记；3、生物信息学入门学习资料及自己的学习笔记！