ggplot2绘制凋亡/坏死实验堆叠柱状图添加统计检验报错求助

使用ggplot2绘制凋亡/坏死实验的堆叠柱状图，展示apop、nec、late三类数据的总和及各部分占比，尝试为每类数据添加配对t检验的显著性标记时，重复添加stat_compare_means层出现报错：

Error in `ggsignif::geom_signif()`:
! Problem while computing stat.
i Error occurred in the 3rd layer.
Caused by error in `compute_layer()`:
! `stat_signif()` requires the following missing aesthetics: y

数据 #

数据表格 #

数据框代码 #

the_data <- structure(list(condition = c("37_colo_control", "37_colo_control", "37_colo_control", "42_colo_control", "42_colo_control", "42_colo_control", "37_colo_mmc", "37_colo_mmc", "37_colo_mmc", "42_colo_mmc", "42_colo_mmc", "42_colo_mmc"), rep = c("rep1", "rep2", "rep3", "rep1", "rep2", "rep3", "rep1", "rep2", "rep3", "rep1", "rep2", "rep3"), nec = c(0.0209, 0.0013, 0.0076, 0.0147, 0.0233, 0.0176, 0.0121, 0.0086, 0.0076, 0.0087, 0.0122, 0.0087), late = c(0.0334, 0.0402, 0.0546, 0.0564, 0.0596, 0.0461, 0.0976, 0.109, 0.111, 0.112, 0.133, 0.112), apop = c(0.0405, 0.0541, 0.0707, 0.0616, 0.0762, 0.0507, 0.237, 0.241, 0.289, 0.302, 0.327, 0.302)), class = "data.frame", row.names = c(NA, 12L))

原绘图代码 #

library(ggpubr)
library(ggprism)
library(ggplot2)

the_data <- read.csv(**[[see table for data]]**)

factored_condition <- c("37_colo_control","37_colo_mmc","42_colo_control","42_colo_mmc")
comparisons <- list(c(factored_condition[1],factored_condition[2]),
                    c(factored_condition[1],factored_condition[3]),
                    c(factored_condition[1],factored_condition[4])
                    )


the_data %>%
  group_by(condition)

fig_bar <- ggplot(the_data, aes(x=factor(condition, levels=factored_condition)))+ 
  geom_bar(aes(y=apop+nec+late),position=position_dodge(), stat="summary", fun="mean", fill = "grey65") +
  stat_compare_means(mapping = aes(y=apop), 
                     comparisons = comparisons, paired = TRUE, method = "t.test", label="p.signif",
                     symnum.args = list(cutpoints = c(0, 0.0001, 0.001, 0.01, 0.05, Inf), 
                                        symbols = c("****","***", "**", "*", " "))) +

    geom_bar(aes(y=nec+late),position=position_dodge(), stat="summary", fun="mean", fill = "grey45") +
    stat_compare_means(mapping = aes(y=late), 
                     comparisons = comparisons, paired = TRUE, method = "t.test", label="p.signif",
                     symnum.args = list(cutpoints = c(0, 0.0001, 0.001, 0.01, 0.05, Inf), 
                                        symbols = c("****","***", "**", "*", " "))) +
  
    geom_bar(aes(y=nec),position=position_dodge(), stat="summary", fun="mean", fill = "grey 15") +
    stat_compare_means(mapping = aes(y=nec), 
                     comparisons = comparisons, paired = TRUE, method = "t.test", label="p.signif",
                     symnum.args = list(cutpoints = c(0, 0.0001, 0.001, 0.01, 0.05, Inf), 
                                        symbols = c("****","***", "**", "*", " "))) +
 
  labs(y="Percent of Cells", x="", fill = "") +
  ggtitle("Colo205") +
  scale_y_continuous(expand=c(0,0),limits = c(0,1.0), labels = scales::percent) +
  scale_x_discrete(labels=x.names) +
  theme_prism()

fig_bar

报错信息 #

Error in `ggsignif::geom_signif()`:
! Problem while computing stat.
i Error occurred in the 3rd layer.
Caused by error in `compute_layer()`:
! `stat_signif()` requires the following missing aesthetics: y
Backtrace:

错误原因 #

1. 原代码用多次geom_bar叠加模拟堆叠，这种方式不符合ggplot2的规范，且stat_compare_means的映射参数传递错误，导致无法识别y轴美学。
2. 配对t检验需要确保重复样本一一对应，原宽格式数据结构不利于分组检验和绘图。

修正后代码 #

library(ggpubr)
library(ggprism)
library(ggplot2)
library(tidyr)
library(dplyr)

# 转换为长格式数据，适配堆叠绘图和分组检验
long_data <- the_data %>%
  pivot_longer(cols = c(nec, late, apop), names_to = "type", values_to = "value") %>%
  mutate(
    condition = factor(condition, levels = c("37_colo_control","37_colo_mmc","42_colo_control","42_colo_mmc")),
    type = factor(type, levels = c("nec", "late", "apop"))
  )

# 定义比较组
comparisons <- list(c("37_colo_control","37_colo_mmc"),
                    c("37_colo_control","42_colo_control"),
                    c("37_colo_control","42_colo_mmc"))

# 计算各类型数据的最大均值，用于设置显著性标记的y轴位置（避免重叠）
mean_pos <- long_data %>%
  group_by(type) %>%
  summarise(max_mean = max(value), .groups = "drop") %>%
  mutate(y_pos = max_mean + c(0.05, 0.15, 0.25))

fig_bar <- ggplot(long_data, aes(x = condition, y = value, fill = type)) +
  # 绘制堆叠柱状图（展示均值）
  stat_summary(fun = mean, geom = "col", position = "stack") +
  
  # 为nec添加配对t检验显著性标记
  stat_compare_means(
    data = filter(long_data, type == "nec"),
    comparisons = comparisons, paired = TRUE, method = "t.test",
    label = "p.signif", y.position = mean_pos$y_pos[mean_pos$type == "nec"],
    symnum.args = list(cutpoints = c(0, 0.0001, 0.001, 0.01, 0.05, Inf), 
                       symbols = c("****","***", "**", "*", " "))
  ) +
  
  # 为late添加配对t检验显著性标记
  stat_compare_means(
    data = filter(long_data, type == "late"),
    comparisons = comparisons, paired = TRUE, method = "t.test",
    label = "p.signif", y.position = mean_pos$y_pos[mean_pos$type == "late"],
    symnum.args = list(cutpoints = c(0, 0.0001, 0.001, 0.01, 0.05, Inf), 
                       symbols = c("****","***", "**", "*", " "))
  ) +
  
  # 为apop添加配对t检验显著性标记
  stat_compare_means(
    data = filter(long_data, type == "apop"),
    comparisons = comparisons, paired = TRUE, method = "t.test",
    label = "p.signif", y.position = mean_pos$y_pos[mean_pos$type == "apop"],
    symnum.args = list(cutpoints = c(0, 0.0001, 0.001, 0.01, 0.05, Inf), 
                       symbols = c("****","***", "**", "*", " "))
  ) +
  
  # 绘图样式设置
  labs(y="Percent of Cells", x="", fill = "Cell Type") +
  ggtitle("Colo205") +
  scale_y_continuous(expand = c(0,0), limits = c(0, 0.8), labels = scales::percent) +
  scale_fill_manual(values = c("nec" = "grey15", "late" = "grey45", "apop" = "grey65")) +
  theme_prism()

fig_bar

说明 #

• 用pivot_longer将宽格式转为长格式，符合ggplot2的绘图逻辑，便于分组处理数据。
• 通过stat_summary直接绘制堆叠柱状图的均值，替代原多次geom_bar叠加的不规范方式。
• 针对每个细胞类型单独筛选数据传递给stat_compare_means，并通过y.position设置错开的标记位置，避免重叠。
• 配对t检验的paired=TRUE会自动基于rep列匹配重复样本，保证检验结果的准确性。

内容的提问来源于stack exchange，提问作者Ryan Fuller