R:circlize circos plot - 如何以最小的重叠绘制扇区之间的未连接区域

Question

我有一个数据框，其中包含 4 组患者和细胞类型之间的共同特征。我有很多不同的功能，但共享的(存在于超过 1 个组中)只是少数。

我想制作一个 circos 图，以反射(reflect)患者组和细胞类型之间的共享特征之间的少量联系，同时了解每个组中有多少非共享特征。

按照我的想法，它应该是一个包含 4 个扇区(每组患者和细胞类型一个)的图，它们之间有一些连接。每个扇区大小应反射(reflect)组中的要素总数，并且该区域的大部分不应与其他组相连，而是空的。

这是我目前所拥有的，但我不希望扇区专门用于每个功能，只针对每组患者和细胞类型。

MWE:

library(circlize)

patients <- c(rep("patient1",20), rep("patient2",10))
cell.types <- c(rep("cell1",12), rep("cell2",8),rep("cell1",6), rep("cell2",4))
features <- c(paste("feature",1:12,sep="_"), paste("feature",9:16,sep="_"), paste("feature",c(1,2,9,10,17,18),sep="_"), paste("feature",c(1,18,19,20),sep="_"))
dat <- data.frame(patient=patients, cell.type=cell.types, feature=features)
dat
dat <- with(dat, table(paste(patient,cell.type,sep='|'), feature))
dat

chordDiagram(as.data.frame(dat), transparency = 0.5)

编辑!!

@m-dz 在他的答案中显示的实际上是我正在寻找的格式，4 个不同的患者/细胞类型组合的 4 个扇区，仅显示连接，而非连接的功能，虽然未显示，应该考虑行业的规模。

但是，我意识到我的情况比上述 MWE 中的情况更复杂。

一个特征被认为出现在 2 个患者/细胞类型组中，不仅当它在 2 个组中相同，而且当它相似 时。 ..(高于阈值的序列标识)。这样，我就有了裁员……

patient1-cell1 中的功能 A 可以连接到 patient2-cell1 中的功能 A，也可以连接到功能 B...对于 patient1-cell1，功能 A 应该只计算一次(唯一计数)，并扩展到 2 个不同的功能在患者 2 细胞 1 中。

请参阅下面的示例，了解我的实际数据如何更精确，看看使用这个示例是否可以得到最终的 circos 图!谢谢!!

##MWE
#NON OVERLAPPING SETS!

#1: non-shared features
nonshared <- data.frame(patient=c(rep("pat1",20), rep("pat2",10)), cell.type=c(rep("cell1",12), rep("cell2",8),rep("cell1",6), rep("cell2",4)), feature=paste("a",1:30,sep=''))
nonshared

#2: features shared between cell types within same patient
sharedcells <- data.frame(patient=c(rep("pat1",3), rep("pat2",4)), cell.types=c(rep("cell1||cell2",3),rep("cell1||cell2",4)), features=c("b1||b1","b1||b1","b1||b1","b2||b2","b3||b3","b4||b4","b4||b5"))
sharedcells

#3: features shared between patients within same cell types
sharedpats <- data.frame(patients=c(rep("pat1||pat2",2), rep("pat1||pat2",6)), cell.type=c(rep("cell1",2),rep("cell2",6)), features=c("c1||c1","c2||c1","c3||c3","c3||c4","c3||c5","c6||c5","c7||c7","c8||c8"))
sharedpats

#4: features shared between patients and cell types
#4.1: shared across pat1-cell1, pat1-cell2, pat2-cell1, pat2-cell2
sharedall1 <- data.frame(both=c(rep("pat1-cell1||pat1-cell2||pat2-cell1||pat2-cell2",4)), features=c("d1||d1||d1||d1","d2||d2||d2||d3","d4||d4||d3||d3","d5||d5||d5||d5"))
#4.2: shared across pat1-cell1, pat1-cell2, pat2-cell1
sharedall2 <- data.frame(both=c(rep("pat1-cell1||pat1-cell2||pat2-cell1",2)), features=c("d6||d6||d6","d7||d7||d7"))
#4.3: shared across pat1-cell1, pat1-cell2, pat2-cell2
sharedall3 <- data.frame(both="pat1-cell1||pat1-cell2||pat2-cell2", features="d8||d8||d9")
#4.4: shared across pat1-cell1, pat2-cell1, pat2-cell2
sharedall4 <- data.frame(both="pat1-cell1||pat2-cell1||pat2-cell2", features="d10||d10||d9")
#4.5: shared across pat1-cell2, pat2-cell1, pat2-cell2
sharedall5 <- data.frame(both=c(rep("pat1-cell2||pat2-cell1||pat2-cell2",3)), features=c("d11||d11||d11","d12||d13||d13","d12||d14||d14"))
#4.6: shared across pat1-cell1, pat2-cell2
sharedall6 <- data.frame()
#4.7: shared across pat1-cell2, pat2-cell1
sharedall7 <- data.frame(both=c(rep("pat1-cell2||pat2-cell1",2)), features=c("d15||d16","d17||d17"))

sharedall <- rbind(sharedall1, sharedall2, sharedall3, sharedall4, sharedall5, sharedall6, sharedall7)
sharedall
#you see there might be overlaps between the different subsets of sharedall, but not between sharedall, sharedparts, sharedcells, and nonshared

#I NEED A CIRCOS PLOT THAT SHOWS ALL THE CONNECTIONS. THE NON-CONNECTED (nonshared) FEATURES SHOULD NOT BE SHOWN, BUT THE SHOULD COUNT TO THE SIZE OF THE SECTOR (CORRESPONDING TO A PATIENT-CELL COMBINATION)

#THE FEATURES SHOULD BE COUNT UNIQUELY, SO IF THERE ARE ENTRIES LIKE:
#3 pat1||pat2     cell2   c3||c3
#4 pat1||pat2     cell2   c3||c4
#5 pat1||pat2     cell2   c3||c5
#THE FEATURE c3 SHOULD BE COUNT ONCE FOR pat1, AND EXPAND TO 3 DIFFERENT FEATURES IN pat2

Answer 1

关于预期结果的旁注:目的是创建一个简单地显示有多少特征共享的图，忽略单个特征(下面的第一个图)或共享特征重叠(例如，在第二个图中，看起来相同的特征是在所有组之间共享，从第一个图来看这是不正确的，但这里重要的是组之间共享特征的比率。

下面的代码产生以下两个图(左图1供引用):

所有单独的功能

独特和共享功能的简单计数

其中一个应该符合预期。

# Prep. data --------------------------------------------------------------

nonshared <- data.frame(patient=c(rep("pat1",20), rep("pat2",10)), cell.type=c(rep("cell1",12), rep("cell2",8),rep("cell1",6), rep("cell2",4)), feature=paste("a",1:30,sep=''))
sharedcells <- data.frame(patient=c(rep("pat1",3), rep("pat2",4)), cell.types=c(rep("cell1||cell2",3),rep("cell1||cell2",4)), features=c("b1||b1","b1||b1","b1||b1","b2||b2","b3||b3","b4||b4","b4||b5"))
sharedpats <- data.frame(patients=c(rep("pat1||pat2",2), rep("pat1||pat2",6)), cell.type=c(rep("cell1",2),rep("cell2",6)), features=c("c1||c1","c2||c1","c3||c3","c3||c4","c3||c5","c6||c5","c7||c7","c8||c8"))
sharedall1 <- data.frame(both=c(rep("pat1-cell1||pat1-cell2||pat2-cell1||pat2-cell2",4)), features=c("d1||d1||d1||d1","d2||d2||d2||d3","d4||d4||d3||d3","d5||d5||d5||d5"))
sharedall2 <- data.frame(both=c(rep("pat1-cell1||pat1-cell2||pat2-cell1",2)), features=c("d6||d6||d6","d7||d7||d7"))
sharedall3 <- data.frame(both="pat1-cell1||pat1-cell2||pat2-cell2", features="d8||d8||d9")
sharedall4 <- data.frame(both="pat1-cell1||pat2-cell1||pat2-cell2", features="d10||d10||d9")
sharedall5 <- data.frame(both=c(rep("pat1-cell2||pat2-cell1||pat2-cell2",3)), features=c("d11||d11||d11","d12||d13||d13","d12||d14||d14"))
sharedall6 <- data.frame()
sharedall7 <- data.frame(both=c(rep("pat1-cell2||pat2-cell1",2)), features=c("d15||d16","d17||d17"))
sharedall <- rbind(sharedall1, sharedall2, sharedall3, sharedall4, sharedall5, sharedall6, sharedall7)

#I NEED A CIRCOS PLOT THAT SHOWS ALL THE CONNECTIONS. THE NON-CONNECTED (nonshared) FEATURES SHOULD NOT BE SHOWN, BUT THE SHOULD COUNT TO THE SIZE OF THE SECTOR (CORRESPONDING TO A PATIENT-CELL COMBINATION)

#THE FEATURES SHOULD BE COUNT UNIQUELY, SO IF THERE ARE ENTRIES LIKE:
#3 pat1||pat2     cell2   c3||c3
#4 pat1||pat2     cell2   c3||c4
#5 pat1||pat2     cell2   c3||c5
#THE FEATURE c3 SHOULD BE COUNT ONCE FOR pat1, AND EXPAND TO 3 DIFFERENT FEATURES IN pat2



# Start -------------------------------------------------------------------

library(circlize)
library(data.table)
library(magrittr)
library(stringr)
library(RColorBrewer)

# Split and pad with 0 ----------------------------------------------------
fun <- function(x) unlist(tstrsplit(x, split = '||', fixed = TRUE))

nonshared %>% setDT()
sharedcells %>% setDT()
sharedpats %>% setDT()
sharedall %>% setDT()

nonshared <- nonshared[, .(group = paste(patient, cell.type, sep = '-'), feature)][, feature := paste0('a', str_pad(str_extract(feature, '[0-9]+'), 2, 'left', '0'))]
sharedcells <- sharedcells[, lapply(.SD, fun), by = 1:nrow(sharedcells)][, .(group = paste(patient, cell.types, sep = '-'), feature = features)][, feature := paste0('b', str_pad(str_extract(feature, '[0-9]+'), 2, 'left', '0'))]
sharedpats <- sharedpats[, lapply(.SD, fun), by = 1:nrow(sharedpats)][, .(group = paste(patients, cell.type, sep = '-'), feature = features)][, feature := paste0('c', str_pad(str_extract(feature, '[0-9]+'), 2, 'left', '0'))]
sharedall <- sharedall[, lapply(.SD, fun), by = 1:nrow(sharedall)][, .(group = both, feature = features)][, feature := paste0('d', str_pad(str_extract(feature, '[0-9]+'), 2, 'left', '0'))]

dt_split <- rbindlist(
  list(
    nonshared,
    sharedcells,
    sharedpats,
    sharedall
  )
)

# Set key and self join to find shared features ---------------------------
setkey(dt_split, feature)
dt_join <- dt_split[dt_split, .(group, i.group, feature), allow.cartesian = TRUE] %>%
  .[group != i.group, ]

# Create a "sorted key" ---------------------------------------------------
# key := paste(sort(.SD)...
# To leave only unique combinations of groups and features
dt_join <-
  dt_join[,
          key := paste(sort(.SD), collapse = '|'),
          by = 1:nrow(dt_join),
          .SDcols = c('group', 'i.group')
          ] %>%
  setorder(feature, key) %>%
  unique(by = c('key', 'feature')) %>%
  .[, .(
    group_from = i.group,
    group_to = group,
    feature = feature)]

# Rename and key ----------------------------------------------------------

dt_split %>% setnames(old = 'group', new = 'group_from') %>% setkey(group_from, feature)
dt_join %>% setkey(group_from, feature)



# Individual features -----------------------------------------------------

# Features without connections --------------------------------------------

dt_singles <- dt_split[, .(group_from, group_to = group_from, feature)] %>%
  .[, N := .N, by = feature] %>%
  .[!(N > 1 & group_from == group_to), !c('N')]

# Bind all, add some columns etc. -----------------------------------------

dt_bind <- rbind(dt_singles, dt_join) %>% setorder(group_from, feature, group_to)

dt_bind[, ':='(
  group_from_f = paste(group_from, feature, sep = '.'),
  group_to_f = paste(group_to, feature, sep = '.'))]
dt_bind[, feature := NULL]  # feature can be removed

# Colour
dt_bind[, colour := ifelse(group_from_f == group_to_f, "#FFFFFF00", '#00000050')]  # Change first to #FF0000FF to show red blobs

# Prep. sectors -----------------------------------------------------------

sectors_f <- union(dt_bind[, group_from_f], dt_bind[, group_to_f]) %>% sort()

colour_lookup <-
  union(dt_bind[, group_from], dt_bind[, group_to]) %>% sort() %>%
  structure(seq_along(.) + 1, names = .)
sector_colours <- str_replace_all(sectors_f, '.[a-d][0-9]+', '') %>%
  colour_lookup[.]

# Gaps between sectors ----------------------------------------------------

gap_sizes <- c(0.0, 1.0)
gap_degree <-
  sapply(table(names(sector_colours)), function(i) c(rep(gap_sizes[1], i-1), gap_sizes[2])) %>%
  unlist() %>% unname()
# gap_degree <- rep(0, length(sectors_f))  # Or no gap



# Plot! -------------------------------------------------------------------

# Each "sector" is a separate patient/cell/feature combination

circos.par(gap.degree = gap_degree)
circos.initialize(sectors_f, xlim = c(0, 1))
circos.trackPlotRegion(ylim = c(0, 1), track.height = 0.05, bg.col = sector_colours, bg.border = NA)

for(i in 1:nrow(dt_bind)) {
  row_i <- dt_bind[i, ]
  circos.link(
    row_i[['group_from_f']], c(0, 1),
    row_i[['group_to_f']], c(0, 1),
    border = NA, col = row_i[['colour']]
  )
}

# "Feature" labels
circos.trackPlotRegion(track.index = 2, ylim = c(0, 1), panel.fun = function(x, y) {
  sector.index = get.cell.meta.data("sector.index")
  circos.text(0.5, 0.25, sector.index, col = "white", cex = 0.6, facing = "clockwise", niceFacing = TRUE)
}, bg.border = NA)

# "Patient/cell" labels
for(s in names(colour_lookup)) {
  sectors <- sectors_f %>% { .[str_detect(., s)] }
  highlight.sector(
    sector.index = sectors, track.index = 1, col = colour_lookup[s],
    text = s, text.vjust = -1, niceFacing = TRUE)
}

circos.clear()



# counts of unique and shared features ------------------------------------

xlims <- dt_split[, .N, by = group_from][, .(x_from = 0, x_to = N)] %>% as.matrix()
links <- dt_join[, .N, by = .(group_from, group_to)]
colours <- dt_split[, unique(group_from)] %>% structure(seq_along(.) + 1, names = .)

library(circlize)

sectors = names(colours)
circos.par(cell.padding = c(0, 0, 0, 0))
circos.initialize(sectors, xlim = xlims)
circos.trackPlotRegion(ylim = c(0, 1), track.height = 0.05, bg.col = colours, bg.border = NA)

for(i in 1:nrow(links)) {
  link <- links[i, ]
  circos.link(link[[1]], c(0, link[[3]]), link[[2]], c(0, link[[3]]), col = '#00000025', border = NA)
}

# "Patient/cell" labels
for(s in sectors) {
  highlight.sector(
    sector.index = s, track.index = 1, col = colours[s], 
    text = s, text.vjust = -1, niceFacing = TRUE)
}

circos.clear()

编辑:仅添加已删除评论中的链接:见 this answer一个很好的标签示例!