基于ggplot绘制带双分组注释的微生物物种丰度热图求助

需求概述 #

• X轴为样本ID，Y轴为物种名称
• 顶部设置两个分组因子进行分面
• 将现有热图调整至目标样式

当前代码 #

ad = tidyr::pivot_wider(Intrasporangiaceae, names_from = 'Species',values_from='Abundance')         
     ad[is.na(ad)] <- 0
     ad = as.matrix(ad[,-c(1:11)])
adscaled <- scale(ad)
Aclust <- hclust(dist(t(ad)))

ggplot(Intrasporangiaceae, aes(Sorghum_Variety, Species, fill = Abundance)) + 
    geom_tile(width=1.0) +
    facet_grid(~Striga_Infestation_Status) +
    
    scale_fill_gradientn(name= 'Abundance',
                         colours = c("#373898ff", "pink","#c11630ff"), 
                         values = c(0,0.1,1), expand = c(0,0), limit = c(0,NA)) +
    scale_y_discrete(limits = colnames(ad)[Aclust$order]) +
    labs(title = paste('Species Abundance in', family_Name), x='', y='') +
    theme(legend.position='right',panel.background=element_blank(),
          axis.line = element_blank(),
          axis.ticks = element_blank(),
          axis.text.x = element_text(size = 8,angle = 90, hjust = 1),
          axis.text.y= element_markdown(),
          legend.text = element_text(size=7),
          legend.key.height = unit(10,'pt'),
          legend.title = element_text(size = 10),
          strip.text = element_text(size = 10),
          axis.title.x = element_text(size = 8),
          axis.title.y = element_text(size = 10),
          plot.title = element_text(size=15, hjust = 0.5)) +
    coord_fixed(ratio = 0.5) +
    theme(panel.spacing = unit(0.04, 'lines'))

核心问题与优化方向 #

1. X轴变量错误：当前用Sorghum_Variety作为X轴，需替换为样本ID列（需根据实际数据确认列名，如Sample_ID）
2. 双分组分面缺失：仅实现了单因子分面，需添加第二个分组因子完成顶部双行分面布局
3. 细节样式不匹配：热图边框、分面间距、轴文本布局需向目标图对齐

优化后代码示例 #

library(tidyverse)
library(ggplot2)

# 数据预处理：确认样本ID列名，此处假设为Sample_ID
dat <- Intrasporangiaceae %>%
  mutate(Sample_ID = as.factor(Sample_ID))

# 物种聚类排序
ad_wide <- dat %>%
  pivot_wider(names_from = Species, values_from = Abundance, values_fill = 0)
ad_matrix <- as.matrix(ad_wide %>% select(-c(1:11)))
ad_scaled <- scale(ad_matrix)
species_clust <- hclust(dist(t(ad_scaled)))
sorted_species <- colnames(ad_matrix)[species_clust$order]

# 绘制优化后热图
ggplot(dat, aes(x = Sample_ID, y = Species, fill = Abundance)) +
  geom_tile(color = "white", linewidth = 0.2) +
  # 双因子分面：将两个分组标签移至X轴上方，按需调整因子顺序
  facet_grid(Striga_Infestation_Status ~ Sorghum_Variety, switch = "x") +
  scale_fill_gradientn(
    name = "丰度",
    colours = c("#373898ff", "pink", "#c11630ff"),
    values = c(0, 0.1, 1),
    expand = c(0, 0),
    limits = c(0, NA)
  ) +
  scale_y_discrete(limits = sorted_species) +
  scale_x_discrete(expand = c(0, 0)) +
  labs(
    title = paste(family_Name, "科物种丰度热图"),
    x = "", y = ""
  ) +
  theme_minimal() +
  theme(
    legend.position = "right",
    axis.text.x = element_text(size = 8, angle = 90, hjust = 1, vjust = 0.5),
    axis.text.y = element_text(size = 8),
    strip.text.x = element_text(size = 10, face = "bold"),
    strip.text.y = element_blank(),
    plot.title = element_text(size = 15, hjust = 0.5, face = "bold"),
    panel.spacing = unit(0.3, "lines"),
    axis.ticks = element_blank(),
    panel.grid = element_blank()
  ) +
  coord_fixed(ratio = 0.6)

关键调整说明 #

• 修正X轴变量为样本ID，确保每个样本对应独立tile
• 使用facet_grid(因子1 ~ 因子2, switch = "x")实现顶部双分组分面
• 添加tile白色边框、移除网格线、调整分面间距，匹配目标图视觉风格
• 需根据实际数据列名调整分组因子、样本ID的变量名

内容的提问来源于stack exchange，提问作者user8019548