跟着Nature Plants学作图：R语言ggplot2画分组折线图和置信区间

用户7010445

发布于 2022-05-23 07:58:14

1.5K00

代码可运行

文章被收录于专栏：小明的数据分析笔记本小明的数据分析笔记本

运行总次数：0

代码可运行

论文

The flying spider-monkey tree fern genome provides insights into fern evolution and arborescence

https://www.nature.com/articles/s41477-022-01146-6#Sec44

数据下载链接

https://doi.org/10.6084/m9.figshare.19125641

今天的推文重复一下论文中的Figure1d中左下角的小图

image.png

论文中提供的原始数据集如下

image.png

需要将其整理成3个单独的数据集

image.png

首先是做数据整理的代码

library(readxl)
library(ggplot2)
library(tidyverse)

dat01<-read_excel("data/20220518/dat01.xlsx")
dat01

dat01 %>% 
  mutate(x=8:2,
         mean_value=`Duplication Per`,
         lower95=`Duplication Per`,
         upper95=`Duplication Per`,
         group="Experimental") %>% 
  select(x,mean_value,lower95,upper95,group)-> dat01

dat02<-read_excel("data/20220518/dat02.xlsx")
head(dat02)
dat02 %>% 
  group_by(MRCA) %>% 
  summarise(mean_value = mean(`Duplication Per`),
            lower95 = Rmisc::CI(`Duplication Per`)[3],
            upper95 = Rmisc::CI(`Duplication Per`)[1]) %>% 
  mutate(x=8:2,
         group="Null simulation") %>% 
  select(x,mean_value,lower95,upper95,group) -> dat02

dat03<-read_excel("data/20220518/dat03.xlsx")
head(dat03)
dat03 %>% 
  group_by(MRCA) %>% 
  summarise(mean_value = mean(`Duplication Per`),
            lower95 = Rmisc::CI(`Duplication Per`)[3],
            upper95 = Rmisc::CI(`Duplication Per`)[1]) %>% 
  mutate(x=8:2,
         group="Positive simulation") %>% 
  select(x,mean_value,lower95,upper95,group) -> dat03

dat<-bind_rows(dat01,dat02,dat03)
dat %>% 
  mutate(group=fct_rev(group)) -> dat

作图代码

ggplot(data = dat,aes(x=x,y=mean_value))+
  geom_line(aes(color=group),size=1.5)+
  geom_ribbon(aes(ymin=lower95-1,ymax=upper95+1,
                  fill=group),
              alpha=0.5,
              show.legend = FALSE)+
  theme_minimal()+
  theme(panel.grid = element_blank(),
        axis.line = element_line(),
        axis.ticks = element_line(),
        legend.title = element_blank())+
  scale_x_continuous(breaks = 2:8,
                     labels = paste0("N",8:2))+
  scale_y_continuous(breaks = c(0,25))+
  labs(x="Subtree node",y="Percent subtree")