之前写过一些微生物多样性的后续可视化的文档，感觉当时水平有限写的一般般没什么新意，今天重新来进行一下数据可视化分析，绘制一张更加富有美感的物种组成图，喜欢的小伙伴可以加入的我交流群获取文档数据及代码
library(tidyverse)
library(scales)
library(ggh4x)
library(patchwork)
library(magrittr)
computed_persent <- function(path) {
data <- path %>%
read.delim(check.names = F,sep="\t",row.names = 1) %>%
t() %>% as.data.frame()
data2 <- data %>%
mutate(sum = rowSums(.), persent = sum / sum(sum) * 100,
sum = NULL,) %>%
rbind(filter(., persent < 0.1) %>% colSums()) %>%
mutate(Taxa = c(data %>% rownames(), "others"))
filter(data2[1:(nrow(data2) - 1),], persent > 0.1) %>%
rbind(data2[nrow(data2),]) %>%
select(ncol(.), 1:(ncol(.) - 2)) %>%
set_rownames(seq_len(nrow(.))) %>%
return()
}
otu_taxa <- computed_persent("otu.xls") %>%
pivot_longer(cols = !Taxa,names_to = "Samples",
values_to = "number") %>% arrange(desc(number))
meta_taxa <- read.delim("taxa.xls",check.names = F,sep="\t") %>%
inner_join(.,otu_taxa,,by="Samples")
meta_taxa$Taxa <- factor(meta_taxa$Taxa,levels = unique(meta_taxa$Taxa))
palette <-c("#00545b","#ff856d","#640025","#3ddda5","#cdffaa","#150e00","#bae278",
"#007a98","#ffe093","#00533f","#90f0ff","#6d3c00","#004f17")
p1 <- ggplot(meta_taxa,aes(Samples,ReadCount,fill=Group))+
geom_col(width = 0.9)+theme_grey()+
labs(y="Read Abundance", x=NULL)+
scale_fill_manual(values=c("light blue", "dark red"))+
facet_nested(.~Type,drop=TRUE,scale="free",space="free")+
scale_y_continuous(expand = c(0,0),
labels=scales::scientific_format(digits=1))+
theme(strip.text = element_blank(),
axis.ticks.x = element_blank(),
panel.background = element_rect(fill='white'),
panel.spacing = unit(0.01,"lines"),
axis.text.y=element_text(size=12),
axis.title.y = element_text(size=12,color="black"),
axis.text.x = element_blank())
image
p2 <- ggplot(meta_taxa,aes(Samples,number,fill=Taxa))+
geom_col(position="stack") +
facet_nested(.~Type+Trial+Day,drop=T,
scale="free",space="free",switch="x")+
scale_fill_manual(values=palette)+
labs(x=NULL, y="Percent Phyla Abundance")+
scale_y_continuous(expand = c(0,0),labels=scales::percent)+
theme(strip.background = element_rect(fill="white",color="black"),
panel.spacing = unit(0,"lines"),
strip.text.x = element_text(size=12,color="black"),
axis.text.y=element_text(size=12),
axis.title.y = element_text(size=12,color="black"),
axis.text.x = element_blank(),
axis.ticks.x = element_blank())+
labs(fill="Phylum")
image
g <- ggplot_gtable(ggplot_build(p2))
strips <- which(grepl('strip-', g$layout$name))
pal <- c("#E64B35FF","#4DBBD5FF","#00A087FF","#3C5488FF","#F39B7FFF","#8491B4FF","#91D1C2FF",
"#FF0000","#4DBBD5FF","#00A087FF","#3C5488FF","#F39B7FFF","#8491B4FF","#91D1C2FF",
"#F8AFA8","#4DBBD5FF","#B09C85FF","#3C5488FF","#F39B7FFF","#B09C85FF","#91D1C2FF",
"#D3DDDC","#00A087FF","#E6A0C4","#3C5488FF")
for (i in seq_along(strips)) {
k <- which(grepl('rect', g$grobs[[strips[i]]]$grobs[[1]]$childrenOrder))
l <- which(grepl('titleGrob', g$grobs[[strips[i]]]$grobs[[1]]$childrenOrder))
g$grobs[[strips[i]]]$grobs[[1]]$children[[k]]$gp$fill <- pal[i]
# g$grobs[[strips[i]]]$grobs[[1]]$children[[l]]$children[[1]]$gp$col <- pal[i] #设置字体颜色
}
plot(g)
image
图片拼接
image
由于一些个人无法解决的问题，此处用了AI进行拼图
