r - ggplot2:更复杂的分面

Question

我有一个越来越复杂的热图。融化数据的一个例子:

head(df2)
  Class     Subclass         Family               variable value
1     A chemosensory family_1005117 caenorhabditis_elegans    10
2     A chemosensory family_1011230 caenorhabditis_elegans     4
3     A chemosensory family_1022539 caenorhabditis_elegans    10
4     A        other family_1025293 caenorhabditis_elegans    NA
5     A chemosensory family_1031345 caenorhabditis_elegans    10
6     A chemosensory family_1033309 caenorhabditis_elegans    10
tail(df2)
     Class Subclass        Family        variable value
6496     C  class c family_455391 trichuris_muris     1
6497     C  class c family_812893 trichuris_muris    NA
6498     F  class f family_225491 trichuris_muris     1
6499     F  class f family_236822 trichuris_muris     1
6500     F  class f family_276074 trichuris_muris     1
6501     F  class f family_768194 trichuris_muris    NA

使用 ggplot2 和 geom_tile，我能够生成漂亮的数据热图。我为代码感到自豪(这是我在 R 中的第一次体验)，所以在下面发布了它:

df2[df2 == 0] <- NA
df2[df2 > 11] <- 10
df2.t <- data.table(df2)
df2.t[, clade := ifelse(variable %in% c("pristionchus_pacificus", "caenorhabditis_elegans", "ancylostoma_ceylanicum", "necator_americanus", "nippostrongylus_brasiliensis", "angiostrongylus_costaricensis", "dictyocaulus_viviparus", "haemonchus_contortus"), "Clade V",
                 ifelse(variable %in% c("meloidogyne_hapla","panagrellus_redivivus", "rhabditophanes_kr3021", "strongyloides_ratti"), "Clade IV",
                 ifelse(variable %in% c("toxocara_canis", "dracunculus_medinensis", "loa_loa", "onchocerca_volvulus", "ascaris_suum", "brugia_malayi", "litomosoides_sigmodontis", "syphacia_muris", "thelazia_callipaeda"), "Clade III",
                 ifelse(variable %in% c("romanomermis_culicivorax", "trichinella_spiralis", "trichuris_muris"), "Clade I",
                 ifelse(variable %in% c("echinococcus_multilocularis", "hymenolepis_microstoma", "mesocestoides_corti", "taenia_solium", "schistocephalus_solidus"), "Cestoda",
                 ifelse(variable %in% c("clonorchis_sinensis", "fasciola_hepatica", "schistosoma_japonicum", "schistosoma_mansoni"), "Trematoda", NA))))))]
df2.t$clade <- factor(df2.t$clade, levels = c("Clade I", "Clade III", "Clade IV", "Clade V", "Cestoda", "Trematoda"))
plot2 <- ggplot(df2.t, aes(variable, Family))
tile2 <- plot2 + geom_tile(aes(fill = value)) + facet_grid(Class ~ clade, scales = "free", space = "free")
tile2 <- tile2 + scale_x_discrete(expand = c(0,0)) + scale_y_discrete(expand = c(0,0))
tile2 <- tile2 + theme(axis.text.y = element_blank(), axis.ticks.y = element_blank(), legend.position = "right", axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.55), axis.text.y = element_text(size = rel(0.35)), panel.border = element_rect(fill=NA,color="grey", size=0.5, linetype="solid"))
tile2 <- tile2 + xlab(NULL)
tile2 <- tile2 + scale_fill_gradientn(breaks = c(1,2,3,4,5,6,7,8,9,10),labels = c("1", "2", "3", "4", "5", "6", "7", "8", "9", ">10"), limits = c(1, 10), colours = palette(11), na.value = "white", name = "Members")'

如您所见，涉及到大量的手动重新排序，否则代码非常简单。这是图像输出:



但是，您可能会注意到一整列信息“子类”未被使用。基本上，每个子类都适合一个类。如果我能够在已经显示的类方面中对这些子类进行方面，那就太完美了。据我所知，这是不可能的。准确地说，只有 A 类有不同的子类。其他类只是镜像了它们的类名(F = 类 f)。是否有另一种方法来组织此热图，以便我可以显示所有相关信息？缺失的子类包含一些最关键的数据，并且对于从数据中进行推断是最必要的。

另一种方法是对子类而不是类进行分面，手动重新排序它们以便类聚集在一起，然后在它们周围绘制某种框以划分每个类。我不知道这将如何完成。

任何帮助都会非常有用。如果您需要任何其他信息，请告诉我。

Answer 1

这将在原始 strip 的右侧和图例的左侧放置一个新 strip 。

library(ggplot2)
library(gtable)
library(grid)

p <- ggplot(mtcars, aes(mpg, wt, colour = factor(vs))) + geom_point()
p <- p + facet_grid(cyl ~ gear)

# Convert the plot to a grob
gt <- ggplotGrob(p)

# Get the positions of the right strips in the layout: t = top, l = left, ...
strip <-c(subset(gt$layout, grepl("strip-r", gt$layout$name), select = t:r))

#  New column to the right of current strip
gt <- gtable_add_cols(gt, gt$widths[max(strip$r)], max(strip$r))  

# Add grob, the new strip, into new column
gt <- gtable_add_grob(gt, 
  list(rectGrob(gp = gpar(col = NA, fill = "grey85", size = .5)),
  textGrob("Number of Cylinders", rot = -90, vjust = .27, 
        gp = gpar(cex = .75, fontface = "bold", col = "black"))), 
        t = min(strip$t), l = max(strip$r) + 1, b = max(strip$b), name = c("a", "b"))

# Add small gap between strips
gt <- gtable_add_cols(gt, unit(1/5, "line"), max(strip$r))

# Draw it
grid.newpage()
grid.draw(gt)