任务目标：批量绘制每个RNA文库reads比对情况的饼图；
任务流程: 数据预处理 和 图样式处理 + 循环出图
library(RColorBrewer);library(ggforce);set.seed(123);;library(ggplot2);library(dplyr);library(tidyverse)
数据集概况
加载进来的的数据集是按行记录了每个文库的reads比对信息，其中比对类别存在列向量，绘图注意数据格式转换，绘制一个文库的饼图需要提取数据集的一行来进行处理。
数据处理脚本
- 第一步，绘图数据格式转换
data.set <- read.table("*.tsv") #加载数据集
df <- data.set[1,] #提取数据集的一行进行脚本测试
df %>% data.frame() %>% t() %>% data.frame() %>% tibble::rownames_to_column(var = "group") %>% filter_all( any_vars(grepl("Reads", .)) ) %>%
dplyr::rename(labels_1 = 2) %>% filter(!grepl("Mapped.to.Genome", group)) %>%
mutate(perc = as.numeric(sub("%", "", labels_1))/100) %>%
mutate(labels = scales::percent(perc),labels = paste( gsub("\\."," ",x = group) ,labels,sep = "-")) -> t
> t
group labels_1 perc labels
1 Reads.Mapped.to.Exonic.Regions 42.90% 0.429 Reads Mapped to Exonic Regions-42.9%
2 Reads.Mapped.to.Intronic.Regions 25.70% 0.257 Reads Mapped to Intronic Regions-25.7%
3 Reads.Mapped.to.both.Exonic.and.Intronic.Regions 1.80% 0.018 Reads Mapped to both Exonic and Intronic Regions-1.8%
4 Reads.Mapped.Antisense.to.Gene 12.50% 0.125 Reads Mapped Antisense to Gene-12.5%
5 Reads.Mapped.to.Intergenic.Regions 16.70% 0.167 Reads Mapped to Intergenic Regions-16.7%
6 Reads.Mapped.to.Gene.but.Failed.to.Interpret.Type 0.40% 0.004 Reads Mapped to Gene but Failed to Interpret Type-0.4%
- 第二步，定义饼图分组变量绘图顺序
t$group <- factor(t$group,levels = t$group[6:1]) #取分组排列的倒序
- 第三步，计算绘图的极坐标数据
#计算文本标签的极坐标
t %>% mutate(
end = 2 * pi * cumsum(perc)/sum(perc),
start = lag(end, default = 0),
middle = 0.5 * (start + end),
hjust = ifelse(middle > pi, 1, 0),
vjust = ifelse(middle < pi/2 | middle > 3 * pi/2, 0, 1)) ->t
图样式脚本
- 样式一
ggplot(t) +
geom_arc_bar(aes(x0 = 0, y0 = 0, r0 = 0, r = 1,start = start, end = end, fill = group)) +
geom_text(aes(x = 1.05 * sin(middle_n), y = 1.05 * cos(middle_n),
label = stringr::str_wrap(labels, width = 40), #每行最大文本长度为40,超过文本长度进行折叠
hjust = hjust, vjust = vjust),
size=4.5, fontface="italic",color="grey20") + #绘图标签文本样式
coord_fixed(ratio = 1) + #固定绘图显示比例
#调整比例防止标签截断
scale_x_continuous(limits = c(-2.5, 2.5), name = "", breaks = NULL, labels = NULL) +
scale_y_continuous(limits = c(-1.2, 1.2), name = "", breaks = NULL, labels = NULL) +
scale_fill_manual(values = brewer.pal(6,"Dark2"), #填充色修改
labels = function(x) str_replace(x, "(.{100})", "\\1\n") #图例文本折叠
) +
guides(fill=guide_legend(ncol=2,title.position = "top"))+ #图例标签折叠
theme_void() +
###绘图注释
labs(
title = df[1],#添加标题头
caption = paste0("Reads.Mapped.to.Genome ",df[2])#添加注释文本
)+
theme(
legend.position = "bottom",
legend.text = element_text(size=12),
legend.title = element_text(size = 15),
legend.title.align = 0,
legend.margin= margin(t = 2, unit='cm'),
text = element_text(size = 18, face = "bold"),
plot.title = element_text(size = 23, face = "bold",hjust = 0.5,vjust = 5),
plot.caption = element_text(size = 22, face = "bold",hjust = 0.1,vjust = 30,colour = "#56b1cf"), #引用字样式
plot.caption.position = "panel"
)
- 样式二
ggplot(t, aes(x = "", y = perc, fill = labels)) +
geom_col() +
geom_label(aes(label = labels_1),color=c("white","white","white","white","white","red"),size=10,position = position_stack(vjust = 0.5),show.legend = FALSE) +
scale_fill_manual(values = viridis::viridis(6), #填充色修改
labels = function(x) stringr::str_wrap(x, width = 30) #图例文本折叠
)+
coord_polar(theta = "y")+
theme_void() +
###绘图注释
labs(
title = paste0("Reads.Mapped.to.Genome ",df[2]),
caption = df[1] )+
theme(text = element_text(size = 18, face = "bold"),
plot.title = element_text(size = 22, face = "bold",vjust = -115,hjust = 0.1,color = "skyblue"),
plot.caption = element_text(size = 22, face = "bold",hjust = 0.5,vjust = 115),
plot.caption.position = "panel",
legend.margin= margin(l = -1.5, unit='cm'), #图例距离绘图的距离
legend.text = element_text( size = 11,margin = margin(l = 5, unit = "pt")), #图例文本
legend.key.size = unit(30, "pt"), #图例大小
)
批量出图
将上面步骤的处理和出图脚本封装到函数f，使用 apply循环体遍历数据集的行，调用出图函数f出图
f <- function(x) { ... ; ggsave(plot = . ,filename = paste0(file_name,".jpg"),dpi = 300)}
apply(df, 1, FUN = function(x) f(x) )
网友评论