论文
Graph pangenome captures missing heritability and empowers tomato breeding
https://www.nature.com/articles/s41586-022-04808-9#MOESM8
没有找到论文里的作图的代码，但是找到了部分组图数据，我们可以用论文中提供的原始数据模仿出论文中的图
今天的推文重复一下论文中的Figure1c
image.png
今天主要的知识点是多个图例的时候如何分开放，目前想到的办法是使用ggpubr这个R包把图例单独挑出来，然后使用annotation_custom()函数再把图例加回去。不知道有没有更方便的办法
部分示例数据截图
image.png
读取数据
dat01<-read.delim("data/20220719/Fig1c.txt",
sep = "\t",
header = TRUE,
check.names = FALSE)
dat01
转换成作图数据
library(tidyverse)
library(stringr)
#str_pad('1',2,side = "left",pad = "0")
dat01 %>% filter(`Reference genome`!="p value") %>%
mutate(variants=rep(rep(c("SNP","InDel","SV"),each=2),times=3)) %>%
pivot_longer(-c(`Reference genome`,variants)) %>%
mutate(name=as.numeric(str_replace(name,'x',''))) %>%
group_by(`Reference genome`,variants,name) %>%
summarise(mean_value=mean(value)) %>%
ungroup() -> new.data
最基本的图
library(ggplot2)
ggplot(data=new.data,aes(x=name,y=mean_value))+
geom_line(aes(color=variants,lty=`Reference genome`))+
geom_point(aes(color=variants))
image.png
细节调整
ggplot(data=new.data,aes(x=name,y=mean_value))+
geom_line(aes(color=variants,lty=`Reference genome`))+
geom_point(aes(color=variants),size=5)+
scale_color_manual(values = c("InDel"="#a4d6c1",
"SNP"="#b6e0f0",
"SV"="#ea6743"))+
labs(y=TeX(r"(\textit{F}${_1}$ score)"),
x="Sequencing depth")+
theme_classic()+
scale_y_continuous(limits = c(0.4,1),
breaks = c(0.4,0.6,0.8,1.0),
expand = expansion(mult = c(0.1,0)))
image.png
图例位置
library(ggpubr)
ggplot(data=new.data,aes(x=name,y=mean_value))+
geom_line(aes(color=variants,lty=`Reference genome`),
show.legend = FALSE)+
geom_point(aes(color=variants),size=5)+
scale_color_manual(values = c("InDel"="#a4d6c1",
"SNP"="#b6e0f0",
"SV"="#ea6743"),
name="")+
labs(y=TeX(r"(\textit{F}${_1}$ score)"),
x="Sequencing depth")+
theme_classic()+
scale_y_continuous(limits = c(0.4,1),
breaks = c(0.4,0.6,0.8,1.0),
expand = expansion(mult = c(0.1,0))) -> p1
as_ggplot(get_legend(p1)) -> legend.01
ggplot(data=new.data,aes(x=name,y=mean_value))+
geom_line(aes(color=variants,lty=`Reference genome`))+
geom_point(aes(color=variants),size=5)+
scale_color_manual(values = c("InDel"="#a4d6c1",
"SNP"="#b6e0f0",
"SV"="#ea6743"),
name="")+
labs(y=TeX(r"(\textit{F}${_1}$ score)"),
x="Sequencing depth")+
theme_classic()+
scale_y_continuous(limits = c(0.4,1),
breaks = c(0.4,0.6,0.8,1.0),
expand = expansion(mult = c(0.1,0)))+
guides(color="none")+
theme(legend.position = "top",
legend.title = element_blank()) -> p2
as_ggplot(get_legend(p2)) -> legend.02
ggplot(data=new.data,aes(x=name,y=mean_value))+
geom_line(aes(color=variants,lty=`Reference genome`))+
geom_point(aes(color=variants),size=5)+
scale_color_manual(values = c("InDel"="#a4d6c1",
"SNP"="#b6e0f0",
"SV"="#ea6743"))+
labs(y=TeX(r"(\textit{F}${_1}$ score)"),
x="Sequencing depth")+
theme_classic()+
scale_y_continuous(limits = c(0.4,1),
breaks = c(0.4,0.6,0.8,1.0),
expand = expansion(mult = c(0.1,0))) -> p
p
p + theme(plot.margin = unit(c(1,0.1,0.1,0.1),'cm'),
legend.position = "none")+
coord_cartesian(clip = "off")+
annotation_custom(grob = ggplotGrob(legend.01),
xmin = 22,xmax = 22,
ymin=0.5,ymax = 0.5)+
annotation_custom(grob = ggplotGrob(legend.02),
xmin = 15,xmax = 15,
ymin=1.05,ymax = 1.05)
最终结果
image.png
封面图
library(patchwork)
pdf(file = "abc.pdf",
width = 9.4,height = 4)
pp + pp
dev.off()
image.png
示例数据和代码可以自己到论文中获取，或者给本篇推文点赞，点击在看，然后留言获取
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！