如何在 R 中按组绘制二进制数据和颜色存在

Question

我是 R 初学者，我正在尝试绘制简单的存在/不存在二进制数据。我到处搜索过，但我无法确定是否可以通过分组/元数据为绘图着色。到目前为止，我用 ggplot 绘制了一个简单的图，代码如下：

我的数据如下所示：

library(ggplot2)
data <- read.csv("resistance.csv", row.names=1)
data_matrix <- data.matrix(data)
mybinarymap <- heatmap(data_matrix, Rowv=NA, Colv=NA, col = c("white","black"))

情节如下：

但是，我想将图块更改为按基因所属的“类”着色，例如额外的数据如下所示：

如果值为 0，则会有一个白色/无颜色的图块，如果该基因存在，则该块将被着色，颜色由“类别”列确定。任何人都可以帮助或建议其他软件包吗？ UpSetR 似乎没有达到我的要求。我想我必须做一些重塑。感谢您的帮助。

Answer 1

您可以在

ggplot2

中完成所有这些操作，并在

reshape2

的帮助下将数据转换为长格式。在这里，我假设您有一个名为

data

的数据框，它看起来像您的第二个数据图像。我必须将您的图像通过 OCR 来重新创建您的数据，因为您没有制作可重现的示例，因此它可能不完全准确：

library(ggplot2)
library(reshape2)

ggplot(melt(data), aes(gene, variable, fill = Class, alpha = value)) + 
  geom_tile(colour = "gray50") +
  scale_alpha_identity(guide = "none") +
  coord_equal(expand = 0) +
  theme_bw() +
  theme(panel.grid.major = element_blank(),
        axis.text.x = element_text(angle = 45, hjust = 1))

---

数据

data <- structure(list(gene = c("aadAl", "aadAS", "aph(3\")-lb", "aph(6)-ld", 
"blaCTX-M-27", "blaOXA-1", "erm(B)", "mdf(A)", "mph(A)", "catAl"
), Class = c("Aminoglycoside", "Aminoglycoside", "Aminoglycoside", 
"Aminoglycoside", "Beta-lactam", "Beta-lactam", "Macrolide", "Macrolide", 
"Macrolide", "Tetracycline"), X598080 = c(1L, 0L, 1L, 1L, 1L, 
 0L, 1L, 1L, 1L, 0L), X607387 = c(1L, 0L, 1L, 1L, 1L, 0L, 0L, 
1L, 0L, 0L), X888048 = c(1L, 0L, 0L, 0L, 0L, 1L, 1L, 1L, 1L, 
1L), X893916 = c(0L, 1L, 0L, 0L, 1L, 0L, 1L, 1L, 1L, 0L)), class = "data.frame",
row.names = c(NA, -10L))

data
#>           gene          Class X598080 X607387 X888048 X893916
#> 1        aadAl Aminoglycoside       1       1       1       0
#> 2        aadAS Aminoglycoside       0       0       0       1
#> 3   aph(3")-lb Aminoglycoside       1       1       0       0
#> 4    aph(6)-ld Aminoglycoside       1       1       0       0
#> 5  blaCTX-M-27    Beta-lactam       1       1       0       1
#> 6     blaOXA-1    Beta-lactam       0       0       1       0
#> 7       erm(B)      Macrolide       1       0       1       1
#> 8       mdf(A)      Macrolide       1       1       1       1
#> 9       mph(A)      Macrolide       1       0       1       1
#> 10       catAl   Tetracycline       0       0       1       0

^{由 reprex 包于 2020-07-13 创建（v0.3.0）}

Answer 2

我尝试过这样的方式

library(ggplot2)
library(reshape2)

# Melt the data
melted_data <- melt(data, id.vars = c("gene", "Class"))
colnames(melted_data) <- c("gene", "Class", "Sample", "Presence")

# Define a color palette for the classes
class_colors <- c("Aminoglycoside" = "red",
                  "Beta-lactam" = "blue",
                  "Macrolide" = "green",
                  "Tetracycline" = "purple")

# Create the ggplot object for the heatmap
heatmap <- ggplot(melted_data, aes(x = Sample, y = gene, fill = Presence)) +
  geom_tile(color = "gray50") +
  scale_fill_gradient(low = "white", high = "black") +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1, vjust = 1),  # Rotate x-axis labels
        panel.grid.major = element_blank(),
        panel.grid.minor = element_blank()) +
  labs(x = NULL, y = NULL)+
 
  coord_flip()

# Create the ggplot object for the annotation bar
# Create the ggplot object for annotation bar without facetting
annotation_bar <- ggplot(melted_data, aes(x = Sample, y = gene, fill = Class)) +
  geom_tile() +
  scale_fill_manual(values = c("Aminoglycoside" = "blue", 
                               "Beta-lactam" = "red",
                               "Macrolide" = "green",
                               "Tetracycline" = "orange")) +  # Specify colors for each class
  theme_void()+ # Remove unnecessary elements
  coord_flip()

# Combine both plots using patchwork
library(patchwork)
heatmap_with_annotation <- (annotation_bar / heatmap) + plot_layout(heights = c(0.1, 1))

# Display the combined plot
heatmap_with_annotation