Feature entry correction

NAMESPACE

@@ -3,7 +3,6 @@
 export(.extractAMRtable)
 export(.updateBVBRCdata)
 export(CDHIT2duckdb)
-export(buildClusterFeatureMap)
 export(buildDyadFeatureMap)
 export(checkDataAvailability)
 export(cleanData)

R/data_processing.R

@@ -446,6 +446,7 @@ NULL
     tidyr::separate_rows(protein_ids, sep = ";") |>
     # dplyr::filter(!stringr::str_detect(protein_ids, "_pseudo")) |>
     dplyr::mutate(protein_ids = gsub("_pseudo", "", protein_ids)) |>
+    dplyr::mutate(protein_ids = gsub("_len", "", protein_ids)) |>
     DBI::dbWriteTable(conn = con, name = "genome_gene_protein", overwrite = TRUE)
 }
 
@@ -1405,7 +1406,7 @@ CDHIT2duckdb <- function(duckdb_path,
 #'   Default: `8`.
 #' @param n_workers Integer. Number of parallel HMMER jobs to run. Default: `8`.
 #' @param verbose Logical. Print progress messages. Default: `TRUE`.#'
-#' @returns
+#' @returns Invisibily returns completed HMMER Parquet files per requested database.
 #'
 #' @keywords internal
 .runHMMER <- function(duckdb_path,
@@ -2235,7 +2236,7 @@ CDHIT2duckdb <- function(duckdb_path,
 #' @param ref_file_path Directory containing reference TSVs used by
 #'   [cleanMetaData()] and [cleanData()] for metadata harmonization.
 #'   Default: `"data_raw/"`.
-#' 
+#'
 #' @export
 cleanMetaData <- function(duckdb_path, path, ref_file_path = "data_raw/") {
   duckdb_path <- normalizePath(duckdb_path)

R/feature_to_head.R

@@ -411,7 +411,7 @@ buildDyadFeatureMap <- function(
       view_name = "v_pfam",
       parquet_dir = parquet_dir,
       dataset_name = "protein_Pfam",
-      feature_expr = "query_name"
+      feature_expr = "REPLACE(query_name, '-', '.')"
     )
   }
 
@@ -444,7 +444,7 @@ buildDyadFeatureMap <- function(
       view_name = "v_defensecas",
       parquet_dir = parquet_dir,
       dataset_name = "protein_DefenseCas",
-      feature_expr = "query_name"
+      feature_expr = "REPLACE(query_name, '-', '.')"
     )
   }