bed_to_fasta update

bin/bed_to_fasta.R

@@ -1,25 +1,21 @@
-bed <- data.table::data.table(1:10,1:10,c("AAAAAAAAA","CTGAGA","CCCTAGC","GC","AA","ACGTACGTGTCA","GGGCCGCTA","GCA","TTTTTGCA","AAAATCGACGT"),c(1,2,3,1,1,1,2,2,3,3))
-
 #!/usr/bin/env Rscript
 
 # Splitting BED-files depending on their cluster.
 # The Sequences of each cluster are writen as an FASTA-file.
-# @parameter bedInput <string> BED-file with sequences and cluster-id as column
-# @parameter out <string> output directory
+# @parameter bedInput <string> BED-file with sequences and cluster-id as column"TEs
 # @parameter prefix <string> prefix for filenames
 
 args = commandArgs(trailingOnly = TRUE)
 
-
 bedInput <- args[1]
-out <- args[2] # "G://Rene.Wiegandt/10_Master/"
-prefix <- args[3] # "Fasta" 
+prefix <- args[2] # "Fasta" 
 
 bed <- data.table::fread(bedInput, header = FALSE, sep = "\t")
 
-clusters <- split(bed, bed$V4, sorted = TRUE, flatten = FALSE) # <---- Spalte mit Cluster
+clusters <- split(bed, bed$V3, sorted = TRUE, flatten = FALSE) # <---- Spalte mit Cluster
 discard <- lapply(1:length(clusters), function(i){
-  sequences <- as.list(as.data.frame(clusters[i])[[3]])   # <---- Splate mit Sequenz
-  outfile <- paste0(out,prefix,"_cluster_",i)
-  seqinr::write.fasta(sequences = sequences, names = as.data.frame(clusters[i])[[2]], file.out = outfile, as.string = TRUE) # <---- Spalte mit Name
+  sequences <- as.list(as.data.frame(clusters[i])[[2]])   # <---- Splate mit Sequenz
+  outfile <- paste0(prefix,"_cluster_",i,".FASTA")
+  seqinr::write.fasta(sequences = sequences, names = as.data.frame(clusters[i])[[1]]
+                      , file.out = outfile, as.string = TRUE) # <---- Spalte mit Name
 })