Turn a dataframe that indicates what cluster each sample belongs to into a distance matrix

dist_from_cluster_membership.R

#Function that converts dataframe of cluster identities
# to distance matrix representation of clusters (where rows/cols are samples/IDs and
# 0 indicates that pair are not in same cluster, 1 indicates they are in same cluster
as_dist_mat <- function(dtemp){
  # dtemp is dataframe with two columns:
 #ID is a unique cell ID
 #Cluster is a variable giving cluster a cell belongs to 
 #It should be arranged so we are certain
  #cells are in ascending order
  
  dmat <- matrix(0, nrow = nID, ncol = nID)
  for (iclust in 1:nclust){
    dtemp2 <- subset(dtemp, Cluster == iclust)
    
    #ID pairs - make dataframe where each row represents
    # two cells in the same cluster
    d <- expand.grid(dtemp2$ID, dtemp2$ID)
    
    #Now match ID to get row/col positions
    d$i <- match(d$Var1, IDs)
    d$j <- match(d$Var2, IDs)
    
    #convert coordinates to array indices
    d$pos <- d$i + (d$j-1)*nID 
    #Now fill out matrix with 1s to represent IDs in same cluster
    dmat[d$pos] <- 1
  }
  dmat
}