added documentation

bin/cdhit_wrapper.R

@@ -18,8 +18,8 @@ opt <- parse_args(opt_parser)
 #' cd-hit wrapper
 #' 
 #' @param input
-#' @param similarity cdhit = -c
-#' @param coverage In Nucleotides. cdhit = -A
+#' @param similarity Similarity threshold.
+#' @param coverage Minimal alignment length for both sequences in nucelotides.
 #' @param output Clustered bedfile. Adds cluster number in last column (lower number = bigger cluster).
 #' @param clean Clean up after run.
 #' 
@@ -42,7 +42,7 @@ cdhitest <- function(input, similarity = 0.8, coverage = 8, output = "cluster.be
 
   ### cd-hit-est
   cdhit_output <- "cdhit_output"
-  cdhit_call <- paste("cd-hit-est -i", fasta_file, "-o", cdhit_output, "-c", similarity, "-A", coverage, "-G 0 -n 3 -g 1 -r 0 -l 5 -sc 1")
+  cdhit_call <- paste("cd-hit-est -i", fasta_file, "-o", cdhit_output, "-c", similarity, "-A", coverage, "-G 0 -n 3 -g 1 -r 0 -l 5 -sc 1 -d 0")
 
   system(command = cdhit_call, wait = TRUE)
 

bin/reduce_bed.R

@@ -131,6 +131,8 @@ reduce_bed <- function(input, kmer = 10, motif = 10, output = "reduced.bed", thr
 #' @param kmer Length of kmer
 #' @param motif Length of motif
 #' @param minoverlap Minimum number of bases overlapping between kmer and motif. Must be <= motif & <= kmer. Defaults to ceiling(motif / 2).
+#' 
+#' @return Number of interesting kmer.
 significant_kmer <- function(bed, kmer, motif, minoverlap = ceiling(motif / 2)) {
   if (minoverlap > kmer || minoverlap > motif) {
     stop("Kmer & motif must be greater or equal than minoverlap!")