如何在多幅ggplot图中保持细菌家族的一致配色？

需要绘制多幅柱状图，每幅展示一种植物对应的前10种细菌，以细菌所属的**Family（科）**为柱子填充颜色。单图绘制正常，但后续要合并为多面图，要求同一家族在所有图中使用相同配色（比如Pantoea所属的Erwiniaceae科在两幅示例图中当前颜色不同）。由于数据集可能包含上百个家族，且各图前10种细菌的家族存在差异，希望避免手动为每个家族指定颜色。

示例数据 #

植物Cintybus的前10种细菌数据 #

dput(top10_cintybus)
structure(list(Order = c("Enterobacterales", "Enterobacterales", 
"Enterobacterales", "Sphingomonadales", "Enterobacterales", "Bacillales", 
"Hyphomicrobiales", "Bacillales", "Xanthomonadales", "Hyphomicrobiales"
), Family = c("Enterobacteriaceae", "Erwiniaceae", "Yersiniaceae", 
"Sphingomonadaceae", "Morganellaceae", "Bacillaceae", "Methylobacteriaceae", 
"Bacillaceae", "Xanthomonadaceae", "Rhizobiaceae"), MKC132 = c(0L, 
0L, 27L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), MKC146 = c(33L, 8L, 0L, 
0L, 0L, 0L, 0L, 0L, 0L, 0L), MKC227 = c(11L, 0L, 0L, 0L, 6L, 
2L, 0L, 3L, 0L, 0L), MKC231 = c(37L, 0L, 0L, 20L, 0L, 0L, 3L, 
0L, 2L, 2L), MKC242 = c(0L, 7L, 0L, 0L, 0L, 2L, 0L, 0L, 0L, 0L
), MKC276 = c(9L, 0L, 7L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), MKC351 = c(6L, 
19L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), Total = c(96, 34, 34, 20, 
6, 4, 3, 3, 2, 2), Genus = structure(c(10L, 8L, 9L, 7L, 6L, 5L, 
4L, 3L, 2L, 1L), levels = c("Allorhizobium", "Xanthomonas", "Bacillus", 
"Methylobacterium", "Heyndrickxia", "Arsenophonus", "Sphingomonas", 
"Pantoea", "Serratia", "???.1"), class = "factor")), row.names = c(NA, 
10L), class = "data.frame")

植物Alappa的前10种细菌数据 #

dput(top10_alappa)
structure(list(Order = c("Enterobacterales", "Xanthomonadales", 
"Enterobacterales", "Enterobacterales", "Enterobacterales", "Enterobacterales", 
"Enterobacterales", "Hyphomicrobiales", "Enterobacterales", "Burkholderiales"
), Family = c("Erwiniaceae", "Xanthomonadaceae", "Enterobacteriaceae", 
"Erwiniaceae", "Enterobacteriaceae", "Enterobacteriaceae", "Enterobacteriaceae", 
"Rhizobiaceae", "Morganellaceae", "Oxalobacteraceae"), MKC154 = c(11L, 
0L, 36L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), MKC167A = c(14105L, 0L, 
5810L, 13055L, 1223L, 2316L, 1276L, 0L, 550L, 13L), MKC167B = c(18L, 
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), MKC214 = c(83842L, 5L, 22936L, 
175L, 6828L, 94L, 0L, 7L, 0L, 0L), MKC226 = c(0L, 0L, 11L, 0L, 
0L, 0L, 0L, 0L, 0L, 0L), MKC233 = c(55L, 0L, 13L, 14L, 0L, 0L, 
0L, 0L, 0L, 0L), MKC314 = c(0L, 0L, 0L, 3L, 0L, 0L, 0L, 0L, 0L, 
0L), MKC364 = c(32L, 8L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), MKC366 = c(38L, 
46599L, 0L, 10L, 62L, 0L, 0L, 549L, 0L, 512L), Total = c(98101, 
46612, 28806, 13257, 8113, 2410, 1276, 556, 550, 525), Genus = structure(10:1, levels = c("Janthinobacterium", 
"Morganella", "Allorhizobium", "Citrobacter", "Siccibacter", 
"Enterobacter", "Erwinia", "???.1", "Stenotrophomonas", "Pantoea"
), class = "factor")), row.names = c(NA, 10L), class = "data.frame")

原绘图代码 #

species="Cintybus"
ggplot(data=top10_cintybus,aes(x=Genus, y=Total, fill=Family)) + 
  geom_bar(stat = "identity", colour="black") +
  coord_flip() +
  theme_bw() +
  scale_y_continuous(trans="log10", limits=c(1,1000000), labels=scales::comma,
                     expand=expansion(mult=c(0,.05))) +
  theme(axis.title.x = element_text(size=18)) +
  theme(axis.text.x = element_text(colour="black", face="bold", size=15)) +
  theme(axis.title.y = element_text(size=18, vjust=2.5)) +
  theme(axis.text.y = element_text(face="bold.italic", colour="black", size=15)) +
  geom_text(aes(label=format(Total, big.mark=",")), hjust=1.5, 
            color="white", fontface="plain", size=5) +
  xlab("Genus") + ylab("Abundance") +
  ggtitle(species) + theme(plot.title = element_text(size=18))

1. 统一所有家族的颜色映射 #

先收集所有数据集里的Family，为每个家族分配固定颜色，避免单图绘图时ggplot自动生成不同配色。

# 合并所有数据集，获取完整的家族列表
all_families <- unique(c(top10_cintybus$Family, top10_alappa$Family))

# 为每个家族生成唯一颜色（可替换为其他配色函数，比如viridis系）
family_colors <- scales::hue_pal()(length(all_families))
names(family_colors) <- all_families

2. 调整单图代码，应用统一颜色映射 #

在绘图时通过scale_fill_manual指定预先生成的颜色映射，确保同一家族颜色一致：

# 绘制Cintybus的图
p_cintybus <- ggplot(data=top10_cintybus,aes(x=Genus, y=Total, fill=Family)) + 
  geom_bar(stat = "identity", colour="black") +
  coord_flip() +
  theme_bw() +
  scale_y_continuous(trans="log10", limits=c(1,1000000), labels=scales::comma,
                     expand=expansion(mult=c(0,.05))) +
  theme(axis.title.x = element_text(size=18)) +
  theme(axis.text.x = element_text(colour="black", face="bold", size=15)) +
  theme(axis.title.y = element_text(size=18, vjust=2.5)) +
  theme(axis.text.y = element_text(face="bold.italic", colour="black", size=15)) +
  geom_text(aes(label=format(Total, big.mark=",")), hjust=1.5, 
            color="white", fontface="plain", size=5) +
  xlab("Genus") + ylab("Abundance") +
  ggtitle("Cintybus") + theme(plot.title = element_text(size=18)) +
  scale_fill_manual(values = family_colors)  # 应用统一颜色映射

# 绘制Alappa的图
p_alappa <- ggplot(data=top10_alappa,aes(x=Genus, y=Total, fill=Family)) + 
  geom_bar(stat = "identity", colour="black") +
  coord_flip() +
  theme_bw() +
  scale_y_continuous(trans="log10", limits=c(1,1000000), labels=scales::comma,
                     expand=expansion(mult=c(0,.05))) +
  theme(axis.title.x = element_text(size=18)) +
  theme(axis.text.x = element_text(colour="black", face="bold", size=15)) +
  theme(axis.title.y = element_text(size=18, vjust=2.5)) +
  theme(axis.text.y = element_text(face="bold.italic", colour="black", size=15)) +
  geom_text(aes(label=format(Total, big.mark=",")), hjust=1.5, 
            color="white", fontface="plain", size=5) +
  xlab("Genus") + ylab("Abundance") +
  ggtitle("Alappa") + theme(plot.title = element_text(size=18)) +
  scale_fill_manual(values = family_colors)  # 应用统一颜色映射

3. 高效生成多面图：合并数据集后用facet_wrap #

将所有植物的前10数据合并到一个数据框，添加植物标识列，直接用facet_wrap生成多面图，无需单独绘制每张图：

# 为每个数据集添加植物标识列
top10_cintybus$Species <- "Cintybus"
top10_alappa$Species <- "Alappa"

# 合并数据集
combined_data <- rbind(top10_cintybus, top10_alappa)

# 绘制多面图
ggplot(data=combined_data,aes(x=Genus, y=Total, fill=Family)) + 
  geom_bar(stat = "identity", colour="black") +
  coord_flip() +
  theme_bw() +
  scale_y_continuous(trans="log10", limits=c(1,1000000), labels=scales::comma,
                     expand=expansion(mult=c(0,.05))) +
  theme(axis.title.x = element_text(size=18)) +
  theme(axis.text.x = element_text(colour="black", face="bold", size=15)) +
  theme(axis.title.y = element_text(size=18, vjust=2.5)) +
  theme(axis.text.y = element_text(face="bold.italic", colour="black", size=15)) +
  geom_text(aes(label=format(Total, big.mark=",")), hjust=1.5, 
            color="white", fontface="plain", size=5) +
  xlab("Genus") + ylab("Abundance") +
  facet_wrap(~Species, scales = "free_y") +  # 根据植物拆分面板，y轴自由缩放
  scale_fill_manual(values = family_colors) +
  theme(plot.title = element_text(size=18))

说明 #

• 若有更多植物数据集，只需重复添加Species列并合并到combined_data即可，无需修改绘图代码。
• 若默认配色区分度不足，可替换配色函数，比如scales::viridis_pal(option = "D")(length(all_families))。

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