Question

我试图产生一组密度图，显示四种细胞类型中两组基因的表达水平分布的差异。除了密度图之外，我希望两组的中位数表达水平覆盖在每个图上。基于几个类似问题的答案，我已经能够得到正确的阴谋或正确的中位数，但不能同时得到两者。我没有想法，希望有人能把我弄好。谢谢！

此处提供了示例数据：https://github.com/adadiehl/sample_data/blob/master/sample.data

第一次尝试。生成正确的图，但是在所有四个图上绘制了相同的中位数：

dat = read.table("sample.data")

g = ggplot(dat[which(dat$FPKM > 0),], aes(x = FPKM))
g = g + geom_density(aes(y = ..density.., group = class, color = class, fill = class), alpha=0.2)
g = g + geom_vline(data=dat, aes(xintercept = median(dat$FPKM[ which(dat$FPKM > 0 & dat$class == "Other") ]) ), colour="turquoise3", linetype="longdash")
g = g + geom_vline(data=dat, aes(xintercept = median(dat$FPKM[ which(dat$FPKM > 0 & dat$class == "a_MCKG") ]) ), colour="tomato1", linetype="longdash")
g = g + facet_wrap(~source, ncol=2, scales="free")
g = g + ggtitle("Distribution of FPKM, MCKG vs. Other")
g = g + xlab("FPKM > 0")

第二次尝试：纠正情节但将所有中位数放在所有情节上：

dat = read.table("sample.data")
vline.dat = data.frame(z=levels(dat$source), vl=tapply(dat$FPKM[which(dat$class != "a_MCKG" & dat$FPKM > 0)], dat$source[which(dat$class != "a_MCKG" & dat$FPKM > 0)], median), vm=tapply(dat$FPKM[which(dat$class == "a_MCKG" & dat$FPKM > 0)], dat$source[which(dat$class == "a_MCKG" & dat$FPKM > 0)], median))

g = ggplot(dat[which(dat$FPKM > 0),], aes(x = FPKM))
g = g + geom_density(aes(y = ..density.., group = class, color = class, fill = class), alpha=0.2)
g = g + facet_wrap(~source, ncol=2, scales="free")
g = g + geom_vline(data=vline.dat, aes(xintercept = vl), colour="turquoise3", linetype="longdash")
g = g + geom_vline(data=vline.dat, aes(xintercept = vm), colour="tomato1", linetype="longdash")
g = g + facet_wrap(~source, ncol=2, scales="free")
g = g + ggtitle("Distribution of FPKM, MCKG vs. Other")
g = g + xlab("FPKM > 0")

第三次尝试：情节都是一样但有正确的中位数。

dat = read.table("sample.data")
vline.dat = data.frame(z=levels(dat$source), vl=tapply(dat$FPKM[which(dat$class != "a_MCKG" & dat$FPKM > 0)], dat$source[which(dat$class != "a_MCKG" & dat$FPKM > 0)], median), vm=tapply(dat$FPKM[which(dat$class == "a_MCKG" & dat$FPKM > 0)], dat$source[which(dat$class == "a_MCKG" & dat$FPKM > 0)], median))

g = ggplot(dat[which(dat$FPKM > 0),], aes(x = FPKM))
g = g + geom_density(aes(y = ..density.., group = class, color = class, fill = class), alpha=0.2)
g = g + facet_wrap(~source, ncol=2, scales="free")
g = g + geom_vline(data=vline.dat, aes(xintercept = vl), colour="turquoise3", linetype="longdash")
g = g + geom_vline(data=vline.dat, aes(xintercept = vm), colour="tomato1", linetype="longdash")
g = g + facet_wrap(~z, ncol=2, scales="free")
g = g + ggtitle("Distribution of FPKM, MCKG vs. Other")
g = g + xlab("FPKM > 0")

Answer 1

传递预先汇总的数据是可行的方法：

library(plyr)

names(dat) <- c("FPKM", "class", "source")
dat2 <- subset(dat, FPKM > 0)

ggplot(dat2, aes(x = FPKM)) + 
  geom_density(aes(y = ..density.., group = class, color = class, fill = class), alpha=0.2) +
  geom_vline(data = ddply(dat2, .(source, class), summarize, mmed = median(FPKM)),
             aes(xintercept = mmed, color = class)) +
  facet_wrap(~ source, ncol = 2, scales = "free") +
  ggtitle("Distribution of FPKM, MCKG vs. Other") +
  xlab("FPKM > 0")

或者，您可以使用基数R实现相同的目标：

dat3 <- aggregate(FPKM ~ source + class, data = dat2, FUN = median)

ggplot(dat2, aes(x = FPKM)) + 
  geom_density(aes(y = ..density.., group = class, color = class, fill = class), alpha=0.2) +
  geom_vline(data = dat3,
             aes(xintercept = FPKM, color = class)) +
  facet_wrap(~ source, ncol = 2, scales = "free") +
  ggtitle("Distribution of FPKM, MCKG vs. Other") +
  xlab("FPKM > 0")

N.B。您可能希望避免使用source和class等列名称，因为它们与内置函数冲突。

使用ggplot facet_wrap覆盖R中的不同vlines

1 个答案: