Question

我有以下MWE，我在其中制作热图而不执行任何聚类并显示任何树形图。我想把我的行（基因）按类别分组，比现在更好看。

这是MWE：

#MWE
library(gplots)
mymat <- matrix(rexp(600, rate=.1), ncol=12)
colnames(mymat) <- c(rep("treatment_1", 3), rep("treatment_2", 3), rep("treatment_3", 3), rep("treatment_4", 3))
rownames(mymat) <- paste("gene", 1:dim(mymat)[1], sep="_")
rownames(mymat) <- paste(rownames(mymat), c(rep("CATEGORY_1", 10), rep("CATEGORY_2", 10), rep("CATEGORY_3", 10), rep("CATEGORY_4", 10), rep("CATEGORY_5", 10)), sep=" --- ")
mymat #50x12 MATRIX. 50 GENES IN 5 CATEGORIES, ACROSS 4 TREATMENTS WITH 3 REPLICATES EACH
png(filename="TEST.png", height=800, width=600)
print(
heatmap.2(mymat, col=greenred(75),
      trace="none",
      keysize=1,
      margins=c(8,14),
      scale="row",
      dendrogram="none",
      Colv = FALSE,
      Rowv = FALSE,
      cexRow=0.5 + 1/log10(dim(mymat)[1]),
      cexCol=1.25,
      main="Genes grouped by categories")
)
dev.off()

产生这个：

我想将行中的CATEGORIES组合在一起（如果可能的话，还要将列中的处理组合在一起），所以它看起来如下所示：

或者甚至更好，左边的CATEGORIES，与执行聚类和显示树状图的方式相同;然而更容易和更清楚...

有什么办法吗？谢谢！

修改!!

我在评论中了解了RowSideColors，我在下面制作了MWE。但是，我似乎无法在输出png中打印图例，加上图例中的颜色不正确，我也无法获得正确的位置。所以请帮助我下面的MWE中的传奇。

另一方面，我使用了由12种颜色组成的调色板“Set3”，但如果我需要超过12种颜色（如果我有超过12种颜色）怎么办？

新MWE

library(gplots)
library(RColorBrewer)
col1 <- brewer.pal(12, "Set3")
mymat <- matrix(rexp(600, rate=.1), ncol=12)
colnames(mymat) <- c(rep("treatment_1", 3), rep("treatment_2", 3), rep("treatment_3", 3), rep("treatment_4", 3))
rownames(mymat) <- paste("gene", 1:dim(mymat)[1], sep="_")
mymat
mydf <- data.frame(gene=paste("gene", 1:dim(mymat)[1], sep="_"), category=c(rep("CATEGORY_1", 10), rep("CATEGORY_2", 10), rep("CATEGORY_3", 10), rep("CATEGORY_4", 10), rep("CATEGORY_5", 10)))
mydf
png(filename="TEST.png", height=800, width=600)
print(
    heatmap.2(mymat, col=greenred(75),
              trace="none",
              keysize=1,
              margins=c(8,6),
              scale="row",
              dendrogram="none",
              Colv = FALSE,
              Rowv = FALSE,
              cexRow=0.5 + 1/log10(dim(mymat)[1]),
              cexCol=1.25,
              main="Genes grouped by categories",
              RowSideColors=col1[as.numeric(mydf$category)]
              )
    #THE LEGEND DOESN'T WORK INSIDE print(), AND THE POSITION AND COLORS ARE WRONG
    #legend("topright",
    #       legend = unique(mydf$category),
    #       col = col1[as.numeric(mydf$category)],
    #       lty= 1,
    #       lwd = 5,
    #       cex=.7
    #       )
)
dev.off()

产生：

请帮我解说这个传说，对于假设的情况，我需要超过12种颜色。谢谢！

Answer 1

我会使用pheatmap包。你的例子看起来像那样：

library(pheatmap)
library(RColorBrewer)

# Generte data (modified the mydf slightly)
col1 <- brewer.pal(12, "Set3")
mymat <- matrix(rexp(600, rate=.1), ncol=12)
colnames(mymat) <- c(rep("treatment_1", 3), rep("treatment_2", 3), rep("treatment_3", 3), rep("treatment_4", 3))
rownames(mymat) <- paste("gene", 1:dim(mymat)[1], sep="_")

mydf <- data.frame(row.names = paste("gene", 1:dim(mymat)[1], sep="_"), category = c(rep("CATEGORY_1", 10), rep("CATEGORY_2", 10), rep("CATEGORY_3", 10), rep("CATEGORY_4", 10), rep("CATEGORY_5", 10)))

# add row annotations
pheatmap(mymat, cluster_cols = F, cluster_rows = F, annotation_row = mydf)

# Add gaps
pheatmap(mymat, cluster_cols = F, cluster_rows = F, annotation_row = mydf, gaps_row = c(10, 20, 30, 40))

# Save to file with dimensions that keep both row and column names readable
pheatmap(mymat, cluster_cols = F, cluster_rows = F, annotation_row = mydf, gaps_row = c(10, 20, 30, 40), cellheight = 10, cellwidth = 20, file = "TEST.png")

R heatmap.2行和列的手动分组

1 个答案: