使嵌套的for循环在R中运行更快

Question

I have the following code (nested for loop) in R which is extremely slow. The loop matches values from two columns. Then picks up a corresponding file and iterates through the file to find a match. Then it picks up that row from the file. The iterations could go up to more than 100,000. Please if some one can provide an insight on how to quicken the process.

for(i in 1: length(Jaspar_ids_in_Network)) {
  m <- Jaspar_ids_in_Network[i]
  gene_ids <- as.character(GeneTFS$GeneIds[i])
  gene_names <- as.character(GeneTFS$Genes[i])

  print("i")
  print(i)

  for(j in 1: length(Jaspar_ids_in_Exp)) {
    l <- Jaspar_ids_in_Exp[j]
    print("j")
    print(j)

    if (m == l) {
      check <- as.matrix(read.csv(file=paste0(dirpath,listoffiles[j]),sep=",",header=FALSE))
      data_check <- data.frame(check)
      for(k in 1: nrow(data_check)) {
        gene_ids_JF <- as.character(data_check[k,3])
        genenames_JF <- as.character(data_check[k,4])

        if(gene_ids_JF == gene_ids) {
          GeneTFS$Source[i] <- as.character(data_check[k,3])
          data1 <- rbind(data1, cbind(as.character(data_check[k,3]),  
                                      as.character(data_check[k,8]), 
                                      as.character(data_check[k,9]),  
                                      as.character(data_check[k,6]), 
                                      as.character(data_check[k,7]),  
                                      as.character(data_check[k,5])))
        } else if (toupper(genenames_JF) == toupper(gene_names)) { 
          GeneTFS$Source[i] <- as.character(data_check[k,4])
          data1 <- rbind(data1, cbind(as.character(data_check[k,4]),
                                      as.character(data_check[k,5]), 
                                      as.character(data_check[k,6]), 
                                      as.character(data_check[k,7]),
                                      as.character(data_check[k,8]),
                                      as.character(data_check[k,2])))
        } else {
         # GeneTFS[i,4] <- "No Evidence"    
        }
      }
    } else {
      # GeneTFS[i,4] <- "Record Not Found"          
    }
  }  
}

Answer 1

如果拉出将一对处理为函数f(m,l)的逻辑，则可以将double循环替换为：

outer(Jaspar_ids_in_Network, Jaspar_ids_in_Exp, Vectorize(f))