森林图在论文中很常见,多用于表示多因素分析中的变量与结果变量的比值效应,可以用图示的方法比较直观的绘制出来。既往我们在文章《R语言快速绘制多因素回归分析森林图(1)》已经介绍了怎么绘制森林图,但是绘图比较简单,不够美观,不能绘制相对复杂的森林图。今天我们来介绍一下forestploter包,它等于是在forestplot包的基础上进一步强化功能,制作方法也相对简单一点,而且加强了对图形的精细控制,而且可以绘制单组和多组森林图。
R语言使用forestploter包绘制单组及双组森林图
代码:
library(grid)
library(forestploter)
dt<-read.csv("E:/r/test/forest2.csv",sep=',',header=TRUE)
# 公众号回复:森林图数据2,可以获得数据dt <- dt[,1:6]#缩进一格
dt$Subgroup <- ifelse(is.na(dt$Placebo), dt$Subgroup,paste0(" ", dt$Subgroup))#把治疗组和对照组NA(有缺失)的地方变成一个空格
dt$Treatment <- ifelse(is.na(dt$Treatment), "", dt$Treatment)
dt$Placebo <- ifelse(is.na(dt$Placebo), "", dt$Placebo)#生成一个变量se,它在绘图的时候表示正方形的大小
dt$se <- (log(dt$hi) - log(dt$est))/1.96#生成一个绘图区间,等下用来绘图
dt$` ` <- paste(rep(" ", 20), collapse = " ")#生成HR和可信区间
dt$`HR (95% CI)` <- ifelse(is.na(dt$se), "",sprintf("%.2f (%.2f to %.2f)",dt$est, dt$low, dt$hi))#sprintF返回字符和可变量组合
#单组绘图
p <- forest(dt[,c(1:3, 8:9)],est = dt$est, #效应值lower = dt$low, #可信区间下限upper = dt$hi, #可信区间上限sizes = dt$se, #黑框的大小ci_column = 4, #在那一列画森林图,要选空的那一列ref_line = 1,arrow_lab = c("Placebo Better", "Treatment Better"),xlim = c(0, 4),ticks_at = c(0.5, 1, 2, 3),footnote = "This is the demo data. Please feel free to change\nanything you want.")
p#没有P值怎么办,我们可以给它加上去
dt$p <- paste(rep("<0.05", 22))p <- forest(dt[,c(1:3, 8:10)],est = dt$est, #效应值lower = dt$low, #可信区间下限upper = dt$hi, #可信区间上限sizes = dt$se, #黑框的大小ci_column = 4, #在那一列画森林图,要选空的那一列ref_line = 1,arrow_lab = c("Placebo Better", "Treatment Better"),xlim = c(0, 4),ticks_at = c(0.5, 1, 2, 3),footnote = "This is the demo data. Please feel free to change\nanything you want.")
p#图形进行细节调整
dt_tmp <- rbind(dt[-1, ], dt[1, ])
dt_tmp[nrow(dt_tmp), 1] <- "Overall"
dt_tmp <- dt_tmp[1:11, ]
tm <- forest_theme(base_size = 10, #文本的大小# Confidence interval point shape, line type/color/widthci_pch = 15, #可信区间点的形状ci_col = "#762a83", #CI的颜色ci_fill = "blue", #ci颜色填充ci_alpha = 0.8, #ci透明度ci_lty = 1, #CI的线型ci_lwd = 1.5, #CI的线宽ci_Theight = 0.2, # Set an T end at the end of CI ci的高度,默认是NULL# Reference line width/type/color 参考线默认的参数,中间的竖的虚线refline_lwd = 1, #中间的竖的虚线refline_lty = "dashed",refline_col = "grey20",# Vertical line width/type/color 垂直线宽/类型/颜色 可以添加一条额外的垂直线,如果没有就不显示vertline_lwd = 1, #可以添加一条额外的垂直线,如果没有就不显示vertline_lty = "dashed",vertline_col = "grey20",# Change summary color for filling and borders 更改填充和边框的摘要颜色summary_fill = "yellow", #汇总部分大菱形的颜色summary_col = "#4575b4",# Footnote font size/face/color 脚注字体大小/字体/颜色footnote_cex = 0.6,footnote_fontface = "italic",footnote_col = "red")
pt <- forest(dt_tmp[,c(1:3, 8:9)],est = dt_tmp$est,lower = dt_tmp$low, upper = dt_tmp$hi,sizes = dt_tmp$se,is_summary = c(rep(FALSE, nrow(dt_tmp)-1), TRUE),ci_column = 4,ref_line = 1,arrow_lab = c("Placebo Better", "Treatment Better"),xlim = c(0, 4),ticks_at = c(0.5, 1, 2, 3),footnote = "This is the demo data. Please feel free to change\nanything you want.",theme = tm)pt#多组的森林图
dt<-read.csv("E:/r/test/forest2.csv",sep=',',header=TRUE)dt$Subgroup <- ifelse(is.na(dt$Placebo), dt$Subgroup,paste0(" ", dt$Subgroup))#######如果变量没有缺失,就缩进一格,也就是前进一格#因为是双组变量,所以要设置2个n,这步和前面基本一样
dt$n1 <- ifelse(is.na(dt$Treatment), "", dt$Treatment)###将缺失的部分变为空格
dt$n2 <- ifelse(is.na(dt$Placebo), "", dt$Placebo)#因为是要画两个森林图,所以要增加两个空地方来画图
dt$`CVD outcome` <- paste(rep(" ", 20), collapse = " ")
dt$`COPD outcome` <- paste(rep(" ", 20), collapse = " ")#设置一些森林图的基本参数,这步和前面是一样的
tm <- forest_theme(base_size = 10,refline_lty = "solid", #参考线类型ci_pch = c(15, 18),ci_col = c("#377eb8", "#4daf4a"),footnote_col = "blue",legend_name = "Group", #设置标题名字legend_value = c("Trt 1", "Trt 2"), #设置分组名字vertline_lty = c("dashed", "dotted"),vertline_col = c("#d6604d", "#bababa"))
#最后绘图 ci_column = c(3, 5)是指在第3和5列绘图,est_gp1和est_gp2为一组,est_gp3和est_gp4为一组,其他的依次类推p <- forest(dt[,c(1, 19, 21, 20, 22)],est = list(dt$est_gp1,dt$est_gp2,dt$est_gp3,dt$est_gp4),lower = list(dt$low_gp1,dt$low_gp2,dt$low_gp3,dt$low_gp4), upper = list(dt$hi_gp1,dt$hi_gp2,dt$hi_gp3,dt$hi_gp4),ci_column = c(3, 5),ref_line = 1,vert_line = c(0.5, 2),nudge_y = 0.2,theme = tm)p