Address CodeRabbit review feedback

Author: swaraj-neu

R/clean_MZMine.R

@@ -52,6 +52,10 @@
             stop("mzmine_annotations is missing required column(s): ",
                  paste(missing_ann, collapse = ", "), ".")
         }
+        ann[, score := suppressWarnings(as.numeric(score))]
+        if (anyNA(ann$score)) {
+            stop("mzmine_annotations$score must be numeric (or coercible to numeric).")
+        }
         data.table::setorder(ann, id, -score)
         ann_top <- unique(ann, by = "id")
         matched <- ann_top[match(mz_input[[id_col]], ann_top[["id"]]),

R/converters_MZMinetoMSstatsFormat.R

@@ -6,8 +6,11 @@
 #'   `row retention time`, and per-sample peak-area columns named
 #'   `"<run> Peak area"` (e.g. `"sampleA.mzML Peak area"`).
 #' @param annotation `data.frame` with columns `Run`, `Condition`,
-#'   `BioReplicate`. `Run` values must match the sample column names with the
-#'   trailing `" Peak area"` stripped.
+#'   `BioReplicate`. `Run` values must match MSstatsConvert-standardized sample
+#'   names (after column-name normalization removes spaces and dots) with the
+#'   trailing `"Peakarea"` suffix removed. For example, a quant-file column
+#'   `"sampleA.mzML Peak area"` becomes `"sampleAmzML"` after standardization,
+#'   so the corresponding `Run` value must be `sampleAmzML`.
 #' @param mzmine_annotations optional `data.frame` of MZMine spectral-library
 #'   annotations with columns `id`, `compound_name`, `score`. When supplied,
 #'   the highest-scoring `compound_name` per feature is used as `ProteinName`;
@@ -52,7 +55,7 @@ MZMinetoMSstatsFormat = function(
                                         log_file_path)
 
     input = MSstatsConvert::MSstatsImport(list(input = input),
-                                          "MSstats", "MZMine")
+                                          "MSstats", "MZMine", ...)
     input = MSstatsConvert::MSstatsClean(
         input, mzmine_annotations = mzmine_annotations)
     annotation = MSstatsConvert::MSstatsMakeAnnotation(input, annotation)

inst/tinytest/test_converters_MZMinetoMSstatsFormat.R

@@ -97,7 +97,10 @@ expect_equal(ncol(output_nolib), 11)
 expect_equal(nrow(output_nolib), 24)
 expected_mz_rt = c("123.056_1.23", "245.129_3.45", "367.201_5.67",
                    "489.334_7.89", "555.447_9.1", "123.056_1.45")
-expect_true(all(as.character(output_nolib_dt$ProteinName) %in% expected_mz_rt))
+expect_equal(
+    sort(unique(as.character(output_nolib_dt$ProteinName))),
+    sort(expected_mz_rt)
+)
 # Compound names from the library must not leak in
 expect_false(any(as.character(output_nolib_dt$ProteinName) %in%
                  c("Caffeine", "GlucoseHigh", "GlucoseLow", "Lactate")))