听说你还不会绘制森林图(Forest Plot)！？超简单的绘制技巧都在这了

DataCharm

发布于 2022-05-24 16:05:08

6K0

发布于 2022-05-24 16:05:08

文章被收录于专栏：数据学术商业新闻数据学术商业新闻

今天这篇推文，小编就带大家了解一下森林图(Forest Plot) 的绘制方法，主要内容如下：

森林图(Forest Plot)的简单介绍
R-森林图(Forest Plot)绘制方法
Python-森林图(Forest Plot)绘制方法

森林图(Forest Plot)的简单介绍

森林图(Forest Plot) 常用于Meta分析结果展示使用。森林图(可以将观察到的效果、置信区间以及每个研究对象的权重等信息全部表示出来，是一种简单直观地展示单一研究和汇总研究的可视化图表。下面，小编再附上森林图各个绘图元素间关系的解释图：

Key Elements of the Forest plot

注：这里小编简单介绍一下，感兴趣的同学可以自行查阅资料哈。

下面小编就介绍下如何使用R和Python绘制森林图(Forest Plot),可视化结果可能会有所不同。

R-森林图(Forest Plot)绘制方法

使用R绘制森林图(Forest Plot)的方法比较多，这里重点介绍R-forestplot包和R-ggforestplot包绘制。

「注意」：安装R-ggforestplot包之前，确保broom包已安装，否则可能会安装出错。

R-forestplot包绘制

这一部分我们直接使用提供的数据进行绘制，重点在于展示forestplot包中一些绘图参数的设置。

「样例一」：

library(tidyverse)
library(forestplot)
library(meta)
# 构建数据集
cochrane_from_rmeta <- 
  structure(list(
    mean  = c(NA, NA, 0.578, 0.165, 0.246, 0.700, 0.348, 0.139, 1.017, NA, 0.531), 
    lower = c(NA, NA, 0.372, 0.018, 0.072, 0.333, 0.083, 0.016, 0.365, NA, 0.386),
    upper = c(NA, NA, 0.898, 1.517, 0.833, 1.474, 1.455, 1.209, 2.831, NA, 0.731)),
    .Names = c("mean", "lower", "upper"), 
    row.names = c(NA, -11L), 
    class = "data.frame")
# 可视化绘制
forestplot(tabletext, 
           graph.pos = 4,
           # 修改label，ticks 字体和大小
           txt_gp = fpTxtGp(label = gpar(fontfamily = "Roboto Condensed"),
                            ticks = gpar(fontfamily = "Roboto Condensed", cex = .8)),
           
           hrzl_lines = gpar(col = "#444444"),
           cochrane_from_rmeta,new_page = TRUE,
           is.summary = c(TRUE,TRUE,rep(FALSE,8),TRUE),
           clip = c(0.1,2.5), 
           xlog = TRUE, 
           col = fpColors(box = "#BC3C28",
                          line = "black",
                          summary = "#BC3C28"),
           vertices = TRUE,
           title = "The Example Of forestplot::forestplot()")

The Example Of forestplot::forestplot()

注意：这里设置了graph.pos=4 参数用于改变图表元素位置。

「样例二」：针对多个置信区间时

# 构建数据
data(HRQoL)
clrs <- fpColors(box = "royalblue",line = "darkblue", summary = "royalblue")
tabletext <- 
  list(c(NA, rownames(HRQoL$Sweden)),
       append(list(expression(beta)), sprintf("%.2f", HRQoL$Sweden[,"coef"])))

tabletext <- cbind(rownames(HRQoL$Sweden),
                   sprintf("%.2f", HRQoL$Sweden[,"coef"]))
tabletext02 <- tabletext[,1]
#可视化绘制
forestplot(tabletext02, 
           legend = c("Sweden", "Denmark"),
           fn.ci_norm = c(fpDrawNormalCI, fpDrawCircleCI),
           
           txt_gp = fpTxtGp(label = gpar(fontfamily = "Roboto Condensed"),
                            ticks = gpar(fontfamily = "Roboto Condensed", cex = .8),
                            xlab  = gpar(fontfamily = "Roboto Condensed", cex = 1)),
           
           boxsize = .25, # 设置box 大小
           line.margin = .1, # 设置该参数，避免拥挤
           mean = cbind(HRQoL$Sweden[, "coef"], HRQoL$Denmark[, "coef"]),
           lower = cbind(HRQoL$Sweden[, "lower"], HRQoL$Denmark[, "lower"]),
           upper = cbind(HRQoL$Sweden[, "upper"], HRQoL$Denmark[, "upper"]),
           clip = c(-.125, 0.075),
           xticks = c(-.1, -0.05, 0, .05),
           lty.ci = c(1, 2),
           col = fpColors(box = c("#BC3C28", "#0972B5")),
           xlab = "EQ-5D index",vertices = TRUE,
           title = "The Example02 Of forestplot::forestplot()")

The Example02 Of forestplot::forestplot()

以上就简单介绍了forestplot包绘制森林图(Forest Plot)，更多详细参数设置和例子，小伙伴们参考forestplot介绍[1]

R-ggforestplot包绘制

ggforestplot包符合ggplot2绘图语法，熟悉ggplot2的小伙伴可能更加适应一下，接下来，小编举几个例子具体介绍下~

「样例一：」 forestplot()函数绘制

library(ggforestplot)
library(tidyverse)
df_linear <-
  ggforestplot::df_linear_associations %>%
  dplyr::arrange(name) %>%
  dplyr::filter(dplyr::row_number() <= 30)

# 可视化绘制
ggforestplot::forestplot(
                         df = df_linear,
                         estimate = beta,
                         logodds = FALSE,
                         colour = trait,
                         title = "Associations to metabolic traits",
                         xlab = "1-SD increment in cardiometabolic trait
  per 1-SD increment in biomarker concentration"
)

The Example01 Of ggforestplot::forestplot()

「样例二」：geom_effect()绘制

这个方法和平时使用ggplot2绘制类似，也可以实现更加方便的定制化操作，如下：

df <-df_linear_associations %>%
  # 数据处理
  dplyr::arrange(name) %>%
  dplyr::mutate(
    xmin = beta - qnorm(1 - (1 - 0.95) / 2) * se,
    xmax = beta + qnorm(1 - (1 - 0.95) / 2) * se
  ) %>%

  dplyr::filter(dplyr::row_number() <= 30) %>%
  dplyr::mutate(filled = pvalue < 0.001)
  # 可视化绘制
  ggplot(data = df, aes(x = beta, y = name)) +
  geom_effect(
    ggplot2::aes(
      xmin = xmin,
      xmax = xmax,
      colour = trait,
      shape = trait,
      filled = filled
    ),
    size=1.2,
    position = ggstance::position_dodgev(height = 0.5)
  ) +
  scale_colour_nejm() +
  labs(
        title = "Example of <span style='color:#D20F26'>ggforestplot::geom_effect function</span>",
        subtitle = "processed charts with <span style='color:#1A73E8'>geom_effect()</span>",
        caption = "Visualization by <span style='color:#0057FF'>DataCharm</span>") +
  theme_forest() +
  # Add striped background
  geom_stripes() +
  # Add vertical line at null point
  geom_vline(
    xintercept = 0,
    linetype = "solid",
    size = 0.4,
    colour = "black"
  ) +
 theme(text = element_text(family = "Roboto Condensed"),
       plot.title = element_markdown(hjust = 0.5,vjust = .5,color = "black",face = 'bold',
                                  size = 20, margin = margin(t = 10, b = 12)),
       plot.subtitle = element_markdown(hjust = 0,vjust = .5,size=15),
       plot.caption = element_markdown(face = 'bold',size = 12))

The Example01 Of ggforestplot::geom_effect()

以上，小编就简单介绍了使用R-ggforestplot()绘制森林图(Forest Plot)的绘制方法，更多绘图函数和图形参数，小伙伴们可参考R-ggforestplot包介绍[2]。

R-survminer包绘制

最后，小编再介绍使用survminer::ggforest()函数绘制制森林图(Forest Plot)，详细如下：

「样例一」：

library(survminer)
library(survival)
model <- coxph( Surv(time, status) ~ sex + rx + adhere,
                data = colon )
plot01 <- ggforest(model) + 
     labs(
        title = "Example of <span style='color:#D20F26'>survival::ggforest function</span>",
        subtitle = "processed charts with <span style='color:#1A73E8'>ggforest()</span>",
        caption = "Visualization by <span style='color:#0057FF'>DataCharm</span>") +
     theme(text = element_text(family = "Roboto Condensed"),
       plot.title = element_markdown(hjust = 0.5,vjust = .5,color = "black",face = 'bold',
                                  size = 20, margin = margin(t = 10, b = 12)),
       plot.subtitle = element_markdown(hjust = 0.5,vjust = .5,size=15),
       plot.caption = element_markdown(hjust = 1,face = 'bold',size = 11,margin = margin(b = 5,r = 5)))

The Example01 Of survminer::ggforest()

「样例二」：

colon <- within(colon, {
  sex <- factor(sex, labels = c("female", "male"))
  differ <- factor(differ, labels = c("well", "moderate", "poor"))
  extent <- factor(extent, labels = c("submuc.", "muscle", "serosa", "contig."))
})
bigmodel <-
  coxph(Surv(time, status) ~ sex + rx + adhere + differ + extent + node4,
    data = colon )

plot02 <- ggforest(bigmodel) + 
     labs(
        title = "Example of <span style='color:#D20F26'>survival::ggforest function</span>",
        subtitle = "processed charts with <span style='color:#1A73E8'>ggforest()</span>",
        caption = "Visualization by <span style='color:#0057FF'>DataCharm</span>") +
     theme(text = element_text(family = "Roboto Condensed"),
       plot.title = element_markdown(hjust = 0.5,vjust = .5,color = "black",face = 'bold',
                                  size = 20, margin = margin(t = 10, b = 12)),
       plot.subtitle = element_markdown(hjust = 0.5,vjust = .5,size=15),
       plot.caption = element_markdown(hjust = 1,face = 'bold',size = 11,margin = margin(b = 5,r = 5)))

The Example02 Of survminer::ggforest()

更多详细例子可参考R-survminer[3]

Python-森林图(Forest Plot)绘制方法

Python在绘制森林图(Forest Plot)时可能没R这么方便，但小编也是找到一个可快速绘制的库-zepid。感兴趣的小伙伴可自行搜索，这里小编就接单介绍一下其EffectMeasurePlot()绘图函数，如下：

import matplotlib.image as mpimg
import numpy as np
import matplotlib.pyplot as plt
import zepid
from zepid.graphics import EffectMeasurePlot
plt.rcParams['font.family'] = ['Times New Roman']


labs = ["ACA(Isq=41.37% Tausq=0.146 pvalue=0.039 )",
        "ICA0(Isq=25.75% Tausq=0.092 pvalue=0.16 )",
        "ICA1(Isq=60.34% Tausq=0.121 pvalue=0.00 )",
        "ICAb(Isq=25.94% Tausq=0.083 pvalue=0.16 )",
        "ICAw(Isq=74.22% Tausq=0.465 pvalue=0.00 )"]
measure = [2.09,2.24,1.79,2.71,1.97]
lower = [1.49,1.63,1.33,2.00,1.25]
upper = [2.92,3.07,2.42,3.66,3.11]
p = EffectMeasurePlot(label=labs, effect_measure=measure, lcl=lower, ucl=upper)
p.labels(effectmeasure='RR')
p.colors(pointshape="D")
ax=p.plot(figsize=(8,4), t_adjuster=0.09, max_value=4, min_value=0.35)
plt.title("Random Effect Model(Risk Ratio)",loc="right",x=1, y=1.045)
plt.suptitle("Missing Data Imputation Method",x=-0.1,y=0.98)
ax.set_xlabel("Favours Control      Favours Haloperidol       ", fontsize=10)
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
ax.spines['bottom'].set_visible(True)
ax.spines['left'].set_visible(False)
plt.savefig(r"forest_plot02_python.png",width=8,height=6,
          dpi=900,bbox_inches='tight',facecolor='white')