如何从 df 的不同列中获取闪避的 geom_bar (ggplot2)

Question

显示数据框df：

     ID               gene1                   gene2
    4602              TET2                    TET2
    4602              TP53                    TP53
    4602              TET2                    TET2
    5095             ASXL1                   ASXL1
    5095            DNMT3A                  DNMT3A
    5095              NPM1                    <NA>

我一直在尝试获取一个 匹配 条形图，显示列 gene1 和 gene2 的计数（条形）。 gene1 方法是标准方法，而gene2 是另一个突变检测器，应该与gene1 进行比较。如您所见，在样本5095 中仅检测到 2 个突变，而第 3 个未复制。

如何为每个ID 制作一个带有两个条形的条形图，显示gene1 和gene2 中的计数？

这里是 dput()

structure(list(ID = c(4602, 4602, 4602, 5095, 5095, 5095, 5095, 
4649, 4649, 4649, 5069, 5069, 5069, 5146, 5132, 5132, 5132, 5132, 
5132, 5132, 4297, 4297, 4297, 4297, 4297, 4345, 4345, 4345, 4345, 
4345, 4356, 4356, 4356, 4356, 4385, 4385, 4385, 4385, 4385, 4385, 
4437, 4437, 4437, 4437, 4437, 4437, 4442, 4442, 4442, 4442, 4442, 
4479, 4479, 4479, 4479, 4479, 4479, 4479, 4479, 4479, 4479, 4479, 
4479, 4479, 4479, 4479, 4487, 4487, 4487, 4487, 4487, 4487, 4537, 
4537, 4537, 4537, 4537, 4537, 4621, 4621, 4621, 4621, 4621, 4621, 
4621, 4624, 4624, 4624, 4624, 4624, 4665, 4736, 4736, 4736, 4736, 
4736, 4895, 4895, 4895, 4895, 4895, 4903, 4903, 4903, 4903, 4691, 
4691, 4691, 4691, 4261, 4261, 4261, 4261, 4394, 4394, 4394, 4394, 
4424, 4424, 4424, 4424, 4943, 4943, 4943, 5073, 5169, 5169), 
    gene1 = c("TET2", "TP53", "TET2", "ASXL1", "DNMT3A", "NPM1", 
    "PTPN11", "TP53", "TP53", "TET2", "DNMT3A", "TET2", "TET2", 
    "negative", "JAK2", "ASXL1", "BRAF", "CBL", "TET2", "TET2", 
    "DNMT3A", "IDH1", "NPM1", "CREBBP", "FLT3", "DNMT3A", "FLT3", 
    "NPM1", "BCOR", "KIT", "DNMT3A", "IDH1", "NRAS", "BCOR", 
    "KRAS", "NPM1", "PTPN11", "ETV6", "PHF6", "TET2", "DNMT3A", 
    "KRAS", "NPM1", "WT1", "TET2", "WT1", "DNMT3A", "FLT3", "NPM1", 
    "NRAS", "WT1", "DNMT3A", "IDH2", "NPM1", "SRSF2", "ATRX", 
    "CUX1", "CUX1", "FLT3", "GNAS", "PHF6", "PIGA", "PIGA", "PRPF40B", 
    "PTPN11", "TET2", "IDH1", "IDH2", "RUNX1", "U2AF1", "TET2", 
    "TP53", "DNMT3A", "IDH2", "ATRX", "GATA2", "STAG2", "TP53", 
    "IDH2", "SRSF2", "ASXL1", "GATA1", "KDM6A", "STAG2", "TP53", 
    "IDH2", "JAK2", "SRSF2", "ASXL1", "RIT1", "KRAS", "NPM1", 
    "NRAS", "NRAS", "BCOR", "MYD88", "FLT3", "NPM1", "NRAS", 
    "TET2", "TET2", "DNMT3A", "IDH1", "NPM1", "CREBBP", "DNMT3A", 
    "IDH1", "IDH2", "NPM1", "FLT3", "FLT3", "GATA2", "SH2B3", 
    "FLT3", "NPM1", "KDM6A", "SMC1A", "IDH2", "SRSF2", "ASXL2", 
    "RUNX1", "IDH2", "JAK2", "NPM1", "JAK2", "SRSF2", "STAG2"
    ), gene2 = c("TET2", "TP53", "TET2", "ASXL1", "DNMT3A", NA, 
    "PTPN11", "TP53", "TP53", "TET2", "DNMT3A", NA, "TET2", "PTEN", 
    NA, NA, "BRAF", "CBL", "TET2", "TET2", "JAK2", "SRSF2", NA, 
    "DNMT3A", "IDH1", "NPM1", NA, "FLT3", "DNMT3A", "FLT3", "NPM1", 
    NA, NA, "DNMT3A", "IDH1", "NRAS", "BCOR", "KRAS", "NPM1", 
    "PTPN11", "ETV6", "PHF6", "TET2", "DNMT3A", "KRAS", "NPM1", 
    NA, "TET2", NA, "DNMT3A", "FLT3", "NPM1", "NRAS", NA, NA, 
    "IDH2", "NPM1", "SRSF2", NA, "CALR", NA, NA, NA, NA, NA, 
    NA, NA, NA, NA, "IDH1", "IDH2", "RUNX1", "U2AF1", "TET2", 
    NA, "DNMT3A", "IDH2", NA, NA, NA, NA, "IDH2", "SRSF2", "ASXL1", 
    NA, NA, "KMT2D", "TP53", "IDH2", "JAK2", "SRSF2", "ASXL1", 
    NA, "KRAS", "NPM1", "NRAS", "NRAS", NA, NA, "FLT3", "NPM1", 
    "NRAS", "TET2", "TET2", "DNMT3A", "IDH1", "NPM1", "CREBBP", 
    "DNMT3A", "IDH1", "IDH2", "NPM1", "FLT3", "FLT3", NA, NA, 
    "FLT3", "NPM1", NA, "SMC1A", "IDH2", "SRSF2", NA, "RUNX1", 
    "IDH2", "JAK2", "NPM1")), class = "data.frame", row.names = c(NA, 
-127L))

Answer 1

还有一个：

df %>%  
  group_by(ID) %>% 
  add_count(gene1, gene2) %>% 
  pivot_longer(
    cols = contains("gene")
  ) %>% 
  ungroup() %>% 
  ggplot(aes(factor(name), n, fill=value, group=value, label=value)) + 
  geom_col() +
  facet_wrap(.~ID, scales = "free_y") +
  geom_text(size = 3, position = position_stack(vjust = 0.5)) +
  theme_classic()+
  xlab("") +
  guides(fill=FALSE)

最后一次尝试，现在应该可以了。现在我们在旋转之前进行计数：

df %>%  
  group_by(ID) %>% 
  add_count(gene1, gene2) %>% 
  pivot_longer(
    cols = contains("gene")
  ) %>% 
  ungroup() %>% 
  ggplot(aes(factor(name), n, fill=value, group=value)) + 
  geom_col() +
  facet_wrap(.~ID, scales = "free_y") +
  theme(legend.position = "bottom")+
  guides(fill=guide_legend(nrow=2))