使用 facet_wrap 时的子集 x 轴

Question

可能以前有人问过这个问题，但我没有找到解决方案。 我有一个看起来像这样的 TSV (test.tsv)：

TPM variants    NOI_ID  HLA NAL
324.28  several p1  one 2
169.21  NA  p1  two 15
154.78  NA  p1  three   0
143.31  NA  p1  four    2
468.7   NA  p2  five    0
322.76  several p2  six 2
620.98  NA  p2  two 0
591.17  NA  p2  seven   0
637.74  NA  p3  eight   4
519.8   NA  p3  nine    10
1439.58 NA  p3  ten 23
122.05  NA  p4  five    14
149.74  NA  p4  eleven  77
213.7   NA  p4  twelve  100
162.53  NA  p4  one 15

使用此代码：

fig13 <- read.table("test.tsv", sep="\t", header=T, check.names=FALSE)
fig13 = fig13[-which(grepl("_w8", fig13$NOI_ID)),]
fig13_melt <- melt(fig13[c("TPM", "NOI_ID", "HLA", "variants")], id=c("NOI_ID", "HLA", "variants"))

hla_barplot = ggplot(fig13_melt, aes(x=1:nrow(fig13_melt), y=value, fill=variants)) +
     geom_bar(stat="identity", position="dodge") + ggtitle("HLA status", subtitle = "all samples") + theme_bw() +
     theme(axis.title.y=element_blank(), axis.title.x=element_blank(), 
           plot.title = element_text(face = "bold", size = 15, hjust = 0.5),
           plot.subtitle=element_text(size=12, hjust=0.5, face="italic"),
           axis.text.y = element_text(size=6),
           axis.text.x = element_text(angle = 90, hjust=1, size=6)) +
     geom_text(aes(label = round(value,0), vjust = 1, size = 1)) +
     scale_x_discrete(labels=fig13_melt$HLA, breaks=1:nrow(fig13_melt), limits=factor(1:nrow(fig13_melt)), name='HLA')
hla_barplot

我可以绘制以下内容：

但是，当我尝试使用 facet_wrap 分割情节时：

hla_barplot + facet_wrap(.~ NOI_ID, nrow = 1)

我得到以下信息：

所以，据我所知，每个子图都有整个数据集的所有 x 标签。 有没有办法在 x 轴上绘制每个子组的标签？

Answer 1

问题是您在x上映射了1:nrow(...)并修复了 x scale limits=factor(1:nrow(fig13_melt))的限制。 按照评论中的建议这样做scales="free_x"将不起作用。

相反，我建议在x上映射HLA ，摆脱scale_x_discrete并使用scales="free_x"释放你的比例。

如果您想重新排列条形图，我建议您相应地设置HLA列的因子水平。 为此，我将一个帮助列 HLA2 添加到您的 df 中，我将行号添加到其中，以便您的两个“一个”类别变得唯一。 之后，我对scale_x_discrete的标签参数使用函数来删除行号：

library(ggplot2)

fig13_melt$HLA2 <- paste0(fig13_melt$HLA, seq(nrow(fig13_melt)))
fig13_melt$HLA2 <- forcats::fct_inorder(fig13_melt$HLA2)

ggplot(fig13_melt, aes(x = HLA2, y = value, fill = variants)) +
  geom_bar(stat = "identity", position = "dodge") +
  geom_text(aes(label = round(value, 0), vjust = 1, size = 1), show.legend = FALSE) +
  labs(title = "HLA status", subtitle = "all samples", x = "HLA") +
  theme_bw() +
  theme(
    axis.title.y = element_blank(), axis.title.x = element_blank(),
    plot.title = element_text(face = "bold", size = 15, hjust = 0.5),
    plot.subtitle = element_text(size = 12, hjust = 0.5, face = "italic"),
    axis.text.y = element_text(size = 6),
    axis.text.x = element_text(angle = 90, hjust = 1, size = 6)
  ) +
  scale_x_discrete(labels = ~ gsub("\\d+$", "", .x)) +
  facet_wrap(~NOI_ID, nrow = 1, scales = "free_x")

数据

fig13_melt <- structure(list(NOI_ID = c(
  "p1", "p1", "p1", "p1", "p2", "p2",
  "p2", "p2", "p3", "p3", "p3", "p4", "p4", "p4", "p4"
), HLA = c(
  "one",
  "two", "three", "four", "five", "six", "two", "seven", "eight",
  "nine", "ten", "five", "eleven", "twelve", "one"
), variants = c(
  "several",
  NA, NA, NA, NA, "several", NA, NA, NA, NA, NA, NA, NA, NA, NA
), variable = structure(c(
  1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
  1L, 1L, 1L, 1L, 1L, 1L
), levels = "TPM", class = "factor"), value = c(
  324.28,
  169.21, 154.78, 143.31, 468.7, 322.76, 620.98, 591.17, 637.74,
  519.8, 1439.58, 122.05, 149.74, 213.7, 162.53
)), row.names = c(
  NA,
  -15L
), class = "data.frame")

Answer 2

有3个部分需要修改：

1. 在aes()中使用x = factor(1:nrow(fig13_melt))使 x 轴离散而不是连续。 这样，您还可以通过在factor()中设置levels=...来更改 x 轴的标签顺序。

ggplot(fig13_melt, aes(x = factor(1:nrow(fig13_melt)), y = value, fill = variants))

2. 删除 scale_x_discrete() 中的limits = factor(1:nrow(fig13_melt)) scale_x_discrete() ； 否则，将显示 x 轴中的所有类别。

scale_x_discrete(labels = fig13_melt$HLA,
                 breaks = factor(1:nrow(fig13_melt)),
                 name='HLA')

3. 将scales = "free_x"添加到facet_wrap() ：

facet_wrap(.~ NOI_ID, nrow = 1, scales = "free_x")

---

数据

fig13_melt <- structure(list(NOI_ID = c("p1", "p1", "p1", "p1", "p2", "p2",
"p2", "p2", "p3", "p3", "p3", "p4", "p4", "p4", "p4"), HLA = c("one",
"two", "three", "four", "five", "six", "two", "seven", "eight", 
"nine", "ten", "five", "eleven", "twelve", "one"), variants = c("several",
NA, NA, NA, NA, "several", NA, NA, NA, NA, NA, NA, NA, NA, NA
), variable = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L), levels = "TPM", class = "factor"), value = c(324.28,
169.21, 154.78, 143.31, 468.7, 322.76, 620.98, 591.17, 637.74,
519.8, 1439.58, 122.05, 149.74, 213.7, 162.53)), row.names = c(NA,
-15L), class = "data.frame")