.

R/RadixTree_search_helpers.R

@@ -1,3 +1,47 @@
+#' @title Distance search for similar sequences
+#' @description Find similar sequences within a distance threshold
+#' @param query `r rdoc("query")`
+#' @param target `r rdoc("target")`
+#' @param max_distance `r rdoc("max_distance")`
+#' @param max_fraction `r rdoc("max_fraction")`
+#' @param mode `r rdoc("mode")`
+#' @param cost_matrix `r rdoc("cost_matrix")`
+#' @param gap_cost `r rdoc("gap_cost")`
+#' @param gap_open_cost `r rdoc("gap_open_cost")`
+#' @param tree_class Which R6 class to use. Either RadixTree or RadixForest (default: RadixTree)
+#' @param nthreads `r rdoc("nthreads")`
+#' @param show_progress `r rdoc("show_progress")`
+#' @details
+#' This function finds all sequences in _target_ that are within a distance threshold of any sequence in _query_.
+#' This function uses either a RadixTree or RadixForest to store _target_ sequences. See the R6 class documentation for additional details.
+#' 
+#' `r rdoc("details")`
+#' @return The output is a data.frame of all matches with columns "query" and "target".
+#' For anchored searches, the output also includes attributes "query_size" and "target_size"
+#' which are vectors containing the portion of the query and target sequences that are aligned.
+#' @examples
+#' dist_search(c("ACGT", "AAAA"), c("ACG", "ACGT"), max_distance = 1, mode = "levenshtein")
+#' @name dist_search
+dist_search <- function(query, target, max_distance = NULL, max_fraction = NULL, mode = "levenshtein",
+                        cost_matrix = NULL, gap_cost = NULL, gap_open_cost = NULL, tree_class = "RadixTree",
+                        nthreads = 1, show_progress = FALSE) {
+  if (!tree_class %in% c("RadixTree", "RadixForest")) {
+    stop("tree_class must be one of RadixTree or RadixForest")
+  }
+  if (tree_class == "RadixTree") {
+    obj <- RadixTree$new()
+    obj$insert(target)
+    obj$search(query, max_distance, max_fraction, mode, cost_matrix, gap_cost, gap_open_cost, nthreads, show_progress)
+  } else if(tree_class == "RadixForest") {
+    if(!is.null(cost_matrix) || !is.null(gap_cost) || !is.null(gap_open_cost)) {
+      stop("cost_matrix, gap_cost and gap_open_cost are not supported for RadixForest")
+    }
+    obj <- RadixForest$new()
+    obj$insert(target)
+    obj$search(query, max_distance, max_fraction, mode, nthreads, show_progress)
+  }
+}
+
 #' @title split_search
 #' @description Search for similar sequences based on splitting sequences into left and right sides
 #' and searching for matches in each side using a bi-directional anchored alignment.