如何在R中制作时间轴/瀑布图，用于基因/基因组覆盖

Question

我想制作一个相对简单的情节（让人联想到诸如此类的时间线：http://www.ats.ucla.edu/stat/sas/code/timeline.gif），但不是时间在x轴上，它将是基因组中的基本位置。 “时间跨度”将是DNA序列支架的覆盖距离，显示它们落入基因组的范围，它们重叠的位置和没有覆盖的位置。这是我正在寻找的粗略模型，显示rRNA的重叠群覆盖，（我遗漏了，但需要，x轴显示开始和停止的位置，以及重叠群的标记（彩色线））： http://i.imgur.com/MDABx.png，具有以下坐标：

Contig# Start1  Stop1   Start2  Stop2   Start3  Stop3   Start4  Stop4
1   1   90  90  100 120 150 200 400
2   1   100 120 150 200 400 NA  NA
3   1   30  90  100 120 135 200 400
4   1   100 120 140 200 400 NA  NA
5   -35 80  90  100 130 150 200 400
6   1   100 200 300 360 400 NA  NA

我很确定这可以在R中完成，可能使用ggplot2，但由于某种原因我无法弄明白。

Answer 1

这不会像你的情节那样有条理，但它会将线条放入你尚未提供的坐标中：

dfr <- data.frame(seg=sample(1:6, 20, replace=TRUE), start=sample(1:100, 20, replace=TRUE), end=sample(1:100,20, replace=TRUE) )
 plot(c(1,100), c(1,6), type="n")
 with(dfr, segments(y0=seg, y1=seg, x0=start, x1=end, col=2:7, lwd=3))

使用新数据集：

 Contig <- read.table(text=" Start1  Stop1 Start2 Stop2 Start3 Stop3 Start4 Stop4
 1   1   90  90  100 120 150 200 400
 2   1   100 120 150 200 400 NA  NA
 3   1   30  90  100 120 135 200 400
 4   1   100 120 140 200 400 NA  NA
 5   -35 80  90  100 130 150 200 400
 6   1   100 200 300 360 400 NA  NA")
 # the reshape function can be tricky.... but seems to finally work.
 reshape(Contig, direction="long", sep="",
     varying=list(Start=names(Contig)[c(1,3,5,7)],
                   Stop=names(Contig)[c(2,4,6,8)] )  )
#------------------------------
    time Start1 Stop1 id
1.1    1      1    90  1
2.1    1      1   100  2
3.1    1      1    30  3
4.1    1      1   100  4
5.1    1    -35    80  5
6.1    1      1   100  6
1.2    2     90   100  1
2.2    2    120   150  2
3.2    2     90   100  3
4.2    2    120   140  4
5.2    2     90   100  5
6.2    2    200   300  6
1.3    3    120   150  1
2.3    3    200   400  2
3.3    3    120   135  3
4.3    3    200   400  4
5.3    3    130   150  5
6.3    3    360   400  6
1.4    4    200   400  1
2.4    4     NA    NA  2
3.4    4    200   400  3
4.4    4     NA    NA  4
5.4    4    200   400  5
6.4    4     NA    NA  6
#-----------------

 LContig <- reshape(Contig, direction="long", sep="",
   varying=list(Start=names(Contig)[c(1,3,5,7)], Stop=names(Contig)[c(2,4,6,8)] )  )
 plot(range(c(Contig$Start1, Contig$Stop1) , na.rm=TRUE ), c(1,6),
            type="n", xlab="Segments", ylab="Groups")
  with(LContig, segments(y0=id, y1=id, x0=Start1, x1=Stop1, col=2:7, lwd=3))

Answer 2

以下是使用ggplot2的版本：

# Never forget
options(stringsAsFactors = FALSE)

# Load ggplot2 and reshape2
library(ggplot2)
library(reshape2)


# Read in the data
contig <- read.table(
    text = "id Start1  Stop1   Start2  Stop2   Start3  Stop3   Start4  Stop4
            1  1       90      90      100     120     150     200     400
            2  1       100     120     150     200     400     NA      NA
            3  1       30      90      100     120     135     200     400
            4  1       100     120     140     200     400     NA      NA
            5  -35     80      90      100     130     150     200     400
            6  1       100     200     300     360     400     NA      NA",
    header = TRUE
)


# Reshape it
# Melt it all the way down - each data value is gets a record
# identified by id and variable name
contig.melt <- melt(contig, id.var = "id")

# Your variable names contain two pieces of information:
# whether this point is a start or a stop, and
# which span this point is associated with.
# Much easier to work with those separately, so I'll parse them
# into variables.

# Which span?
contig.melt$span <- gsub(x = contig.melt$variable, 
                         pattern = ".*(\\d)",
                         replace = "\\1")

# Start or stop?
contig.melt$point <- gsub(x = contig.melt$variable, 
                          pattern = "(.*)\\d",
                          replace = "\\1")

# Cast it back into a dataset with a record for each span
contig.long <- dcast(contig.melt, id + span ~ point)


# Plot it. The vertical position and line colors are determined by
# the ID. I'm calling that x here, but I'll flip the coords later
ggplot(contig.long, aes(x = id, color = factor(id))) +

    # geom_linerange plots a line from Start (ymin) to stop (ymax)
    # Control the width of the plot with size
    geom_linerange(aes(ymin = Start, ymax = Stop), size = 2) +

    # Flip the coordinates
    coord_flip() +

    # Make it pretty
    scale_colour_brewer("RNA ID", palette = "Dark2") +
    labs(x = "RNA ID", y = "Position") +
    theme_bw()