Implement advanced primer search filtering and reference handling

This update introduces new configuration options for pair selection, including multi-match filtering, circularity settings, and reference site validation. It also enhances the search functionality to correctly identify and track repeated sequences and reference locations, improving the accuracy of primer pair identification.

pkg/obiprimer/search.go

@@ -19,6 +19,8 @@ type SearchParams struct {
 	FalsePositive  float64 // -x: fraction of the counterexamples it may match (0.1)
 	MinSpecificity float64 // -T: pairs with a lower Bs are dropped (0.6)
 	Circular       bool    // -c: sequences are circular
+	NoMultiMatch   bool    // -U: discard the primers matching several times in a sequence
+	Reference      string  // -R: identifier of an example sequence on which the amplicons are located ("" = none)
 
 	Partitions int // partitions of the k-mer counter (default 256)
 	TmpDir     string
@@ -41,6 +43,8 @@ type SearchInfo struct {
 	StrictWords int // words found without error in at least StrictQuorum of the examples
 	MinStrict   int // that quorum, in sequences
 	Matches     int // approximate occurrences of those words
+	Repeated    int // strict words dropped because repeated in an example (-U)
+	MultiMatch  int // words dropped because matching several times in a sequence (-U)
 	Pair        PairInfo
 }
 
@@ -63,6 +67,16 @@ func Search(c *Corpus, taxa *Taxa, p SearchParams) ([]PairStats, *SearchInfo, er
 		return nil, nil, err
 	}
 	info := &SearchInfo{Counts: sw.Counts, StrictWords: len(sw.Words), MinStrict: sw.MinSequences}
+	if p.NoMultiMatch {
+		sw.Words, info.Repeated = DropRepeatedWords(sw.Words)
+	}
+
+	refIndex := -1
+	if p.Reference != "" {
+		if refIndex, err = c.IndexOfExample(p.Reference); err != nil {
+			return nil, info, err
+		}
+	}
 
 	words := make([]uint64, len(sw.Words))
 	for i, w := range sw.Words {
@@ -72,6 +86,9 @@ func Search(c *Corpus, taxa *Taxa, p SearchParams) ([]PairStats, *SearchInfo, er
 	if err != nil {
 		return nil, info, err
 	}
+	if p.NoMultiMatch {
+		wm, info.MultiMatch = DropMultiMatch(wm)
+	}
 	for _, w := range wm {
 		info.Matches += len(w.Matches)
 	}
@@ -85,6 +102,8 @@ func Search(c *Corpus, taxa *Taxa, p SearchParams) ([]PairStats, *SearchInfo, er
 		FalsePositive:  p.FalsePositive,
 		MinSpecificity: p.MinSpecificity,
 		Circular:       p.Circular,
+		Reference:      refIndex,
+		HasReference:   refIndex >= 0,
 	}, p.Model)
 	info.Pair = pinfo
 	return pairs, info, err