使用 presence/absence 数据 R 的共现网络

Co-occurence networks using presence/absence data R

我正在尝试为我的 presence/absence 细菌物种数据制作一个共现网络图,但我不确定如何处理它。我希望最终得到这样的结果 enter image description herewhere each species is linked to another species if they are both present in the same patient, with a larger circle for higher frequency species. I originally tried using widyr and tidygraph packages but I'm not sure if my data set is compatible with them enter image description here,因为它将患者作为列,将个体物种作为行。最好我想知道 packages/code 我可以使用什么来处理我的数据集,或者我如何更改我的数据集以使用这些包。

您可以使用矩阵叉积来获得共生矩阵。然后用igraph包把邻接矩阵转成图就简单了。试试这个:

library(igraph)

# Create fake data set
# rows = patients
# cols = species
set.seed(2222)
df <- matrix(sample(c(TRUE, FALSE), 50, replace = TRUE), 5)
colnames(df) <- letters[1:10]

# Generate co-occurrence matrix with crossproduct
co_mat <- t(df) %*% df

# Set diagonal values to 0
diag(co_mat) <- 0

# Assign dim names
dimnames(co_mat) <- list(colnames(df), colnames(df))

# Create graph from adjacency matrix
# ! edge weights are equal to frequency of co-occurrence
g <- graph_from_adjacency_matrix(co_mat, mode = "upper", weighted = TRUE)

# Assign nodes weight equal to species frequency
g <- set.vertex.attribute(g, "v_weight", value = colSums(df))

plot(g, vertex.size = V(g)$v_weight * 5 + 5, edge.width = E(g)$weight * 5)

这是我们的假数据

         a     b     c     d     e     f     g     h     i     j
[1,]  TRUE  TRUE  TRUE  TRUE FALSE FALSE FALSE FALSE  TRUE FALSE
[2,]  TRUE FALSE FALSE FALSE  TRUE  TRUE  TRUE FALSE  TRUE FALSE
[3,] FALSE  TRUE FALSE FALSE  TRUE FALSE  TRUE FALSE FALSE FALSE
[4,] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE  TRUE  TRUE
[5,] FALSE  TRUE FALSE FALSE  TRUE FALSE FALSE  TRUE  TRUE FALSE

结果如下:

像 Istrel 一样,我也会推荐 igraph。可能是 ggplot 的第二个解决方案..

library(ggnetwork)
library(ggplot2)
library(igraph)

#sample data:
set.seed(1)
mat <- matrix(rbinom(50 * 5, 1, 0.1), ncol = 15, nrow = 100)

# This is not necessary for the example data. But in your case, if you want  species as nodes you have to do a transpose: 
#mat <- t(mat)

#### Optional! But usually there are often "empty cases" which you might want to remove: 
# remove 0-sum-columns
mat <- mat[,apply(mat, 2, function(x) !all(x==0))] 
# remove 0-sum-rows
mat <- mat[apply(mat, 1, function(x) !all(x==0)),]

# transform in term-term adjacency matrix
mat.t <- mat  %*% t(mat)

##### calculate graph 
g <- igraph::graph.adjacency(mat.t,mode="undirected",weighted=T,diag=FALSE)

# calculate coordinates (see https://igraph.org/r/doc/layout_.html for different layouts)
layout <- as.matrix(layout_with_lgl(g))

p<-ggplot(g, layout = layout, aes(x = x, y = y, xend = xend, yend = yend)) +
  geom_edges( color = "grey20", alpha = 0.2, size = 2) + # add e.g. curvature =  0.15 for curved edges
  geom_nodes(size =  (centralization.degree(g)$res +3) , color="darkolivegreen4", alpha = 1) +
  geom_nodes(size =  centralization.degree(g)$res , color="darkolivegreen2", alpha = 1) +
  geom_nodetext(aes(label = vertex.names), size= 5) +
  theme_blank()
p

enter image description here

使用 ggplot 美学:

# calculate degree:
V(g)$Degree <- centralization.degree(g)$res

p<-ggplot(g, layout = layout, aes(x = x, y = y, xend = xend, yend = yend)) +
  geom_edges( color = "grey20", alpha = 0.2, size = 2) + # add e.g. curvature = 0.15 for curved edges
  geom_nodes(aes(size =  Degree) , color="darkolivegreen2", alpha = 1) +
  scale_size_continuous(range = c(5, 16)) +
  geom_nodetext(aes(label = vertex.names), size= 5) +
  theme_blank()
p