非时间数据的 R 运行平均值

This is the plot I'm having now.

它是从这段代码生成的：

ggplot(data1, aes(x=POS,y=DIFF,colour=GT)) + 
  geom_point() +
  facet_grid(~ CHROM,scales="free_x",space="free_x") + 
  theme(strip.text.x = element_text(size=40),
        strip.background = element_rect(color='lightblue',fill='lightblue'),
        legend.position="top",
        legend.title = element_text(size=40,colour="lightblue"),
        legend.text = element_text(size=40),
        legend.key.size = unit(2.5, "cm")) +
  guides(fill = guide_legend(title.position="top",
                             title = "Legend:GT='REF'+'ALT'"),
         shape = guide_legend(override.aes=list(size=10))) +
  scale_y_log10(breaks=trans_breaks("log10", function(x) 10^x, n=10)) + 
  scale_x_continuous(breaks = pretty_breaks(n=3)) +
  geom_line(stat = "hline",
            yintercept = "mean",
            size = 1)

最后一行，geom_line为每个面板创建平均线。

但现在我想在每个面板中获得更具体的运行平均值。

i.e. If panel1('chr01')x 轴范围从 0 到 100,000,000，我想要每个 1,000,000 范围的平均值。

mean1 = mean(x=0 to x=1,000,000)

mean2 = mean(x=1,000,001 to x=2,000,000)

提供运行平均值的一种方法是geom_smooth()使用loess局部回归方法。为了演示我提出的解决方案，我使用 R 函数创建了一个假基因组数据集。您可以调整span的参数geom_smooth使运行平均值更平滑（更接近 1.0）或更粗糙（更接近 1/数据点数量）。

# Create example data.
set.seed(27182)

y1 = rnorm(10000) + 
     c(rep(0, 1000), dnorm(seq(-2, 5, length.out=8000)) * 3, rep(0, 1000))
y2 = c(rnorm(2000), rnorm(1000, mean=1.5), rnorm(1000, mean=-1, sd=2), 
       rnorm(2000, sd=2))
y3 = rnorm(4000)
pos = c(sort(runif(10000, min=0, max=1e8)),
        sort(runif(6000,  min=0, max=6e7)),
        sort(runif(4000,  min=0, max=4e7)))
chr = rep(c("chr01", "chr02", "chr03"), c(10000, 6000, 4000))

data1 = data.frame(CHROM=chr, POS=pos, DIFF=c(y1, y2, y3))

# Plot.
p = ggplot(data1, aes(x=POS, y=DIFF)) +
    geom_point(alpha=0.1, size=1.5) +
    geom_smooth(colour="darkgoldenrod1", size=1.5, method="loess", degree=0, 
        span=0.1, se=FALSE) +
    scale_x_continuous(breaks=seq(1e7, 3e8, 1e7), 
        labels=paste(seq(10, 300, 10)), expand=c(0, 0)) +
    xlab("Position, Megabases") +
    theme(axis.text.x=element_text(size=8)) +
    facet_grid(. ~ CHROM, scales="free", space="free")

ggsave(filename="plot_1.png", plot=p, width=10, height=5, dpi=150)