implement manual threshold override for meshclust

R/meshclustR.R

@@ -13,6 +13,10 @@
 #' `which meshclust` on commandline). Default is set to "meshclust".
 #' @param filepath The path to the directory where the temporary and log
 #' files will be saved.
+#' @param threshold Numeric value between 0 and 0.99 or FALSE (default).
+#' Numeric values will be used as clustering thresholds for meshclust to override
+#' the automatically set threshold. If FALSE, meshclust will determine the
+#' threshold (recommended).
 #' @return A data frame with information regarding the clustering analysis.
 #'
 #' @examples
@@ -23,7 +27,8 @@
 #' @export
 meshclustR <- function(seqs = MyDNAStringSet,
                        meshclust_bin = meshclust,
-                       filepath = path){
+                       filepath = path,
+                       threshold = FALSE){
 
   #create temporary file path
   temp_file <- file.path(filepath, 'cluster_me.fa')
@@ -34,8 +39,14 @@ meshclustR <- function(seqs = MyDNAStringSet,
     tools::file_path_sans_ext(basename(temp_file)),'.txt'))
 
   #run Meshclust
-  system2(meshclust_bin, args = c('-d', temp_file,
-                                  '-o', out_file))
+  if(is.numeric(threshold) && 0 < threshold && threshold <= 0.99){
+    system2(meshclust, args = c("-d", temp_file,
+                                "-o", out_file,
+                                "-t", threshold))
+  }else{
+    system2(meshclust, args = c("-d", temp_file,
+                                "-o", out_file))
+  }
 
   #read output file and parse
   stable_cluster <- readr::read_delim(out_file, delim = '\t',

man/meshclustR.Rd

@@ -4,7 +4,12 @@
 \alias{meshclustR}
 \title{Write temporary file to cluster using MeshclustR}
 \usage{
-meshclustR(seqs = MyDNAStringSet, meshclust_bin = meshclust, filepath = path)
+meshclustR(
+  seqs = MyDNAStringSet,
+  meshclust_bin = meshclust,
+  filepath = path,
+  threshold = FALSE
+)
 }
 \arguments{
 \item{seqs}{A DNAStringSet object containing the DNA sequences to be clustered.}
@@ -14,6 +19,11 @@ meshclustR(seqs = MyDNAStringSet, meshclust_bin = meshclust, filepath = path)
 
 \item{filepath}{The path to the directory where the temporary and log
 files will be saved.}
+
+\item{threshold}{Numeric value between 0 and 0.99 or FALSE (default).
+Numeric values will be used as clustering thresholds for meshclust to override
+the automatically set threshold. If FALSE, meshclust will determine the
+threshold (recommended).}
 }
 \value{
 A data frame with information regarding the clustering analysis.