Refactor primer logic and enhance taxonomy features

This commit introduces refinements to primer design strategies, species identification rules, and performance analysis. It also updates taxonomy handling by implementing methods for setting and dropping taxonomic paths, along with necessary utility improvements for set handling and comprehensive test coverage.

pkg/obiprimer/search_real_test.go

@@ -16,6 +16,12 @@ import (
 // loadTutorial reads the Cyprinidae examples of the tutorial data (the opt-in
 // tests need OBIPRIMERS_TUTORIAL, see TestStrictWordsAgainstEcoPrimers).
 func loadTutorial(t *testing.T) (*Corpus, *Taxa, *obitax.Taxonomy) {
+	t.Helper()
+	return loadTutorialWith(t, nil)
+}
+
+// loadTutorialWith is loadTutorial with counterexample clades (ecoPrimers -i).
+func loadTutorialWith(t *testing.T, ignore []string) (*Corpus, *Taxa, *obitax.Taxonomy) {
 	t.Helper()
 	dir := os.Getenv("OBIPRIMERS_TUTORIAL")
 	if dir == "" {
@@ -33,7 +39,11 @@ func loadTutorial(t *testing.T) (*Corpus, *Taxa, *obitax.Taxonomy) {
 	if err != nil {
 		t.Fatal(err)
 	}
-	corpus, err := LoadCorpus(seqs, Selection{Restrict: restrict})
+	sel := Selection{Restrict: restrict}
+	if sel.Ignore, err = BelongingTo(taxonomy, ignore); err != nil {
+		t.Fatal(err)
+	}
+	corpus, err := LoadCorpus(seqs, sel)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -173,3 +183,61 @@ func TestReferenceSitesAreRealSites(t *testing.T) {
 		})
 	}
 }
+
+// ecoPrimers with counterexamples: -r 7953 -i 1 (the Cyprinidae against all the
+// other sequences of the database, 7497 counterexamples of 7387 species), -e 3
+// -3 2 -l 30 -L 150 -c. ecoPrimers needed 45 minutes and keeps 173 pairs.
+// testdata/ecoprimers_Cyprinidae_I1.pairs.tsv holds for each: the primers, the
+// good flags, the amplified example and counterexample sequences, the amplified
+// example and counterexample taxa, and the identified taxa.
+func TestCounterExamplesAgainstEcoPrimers(t *testing.T) {
+	corpus, taxa, _ := loadTutorialWith(t, []string{"1"})
+	if c := corpus.Counts(); c.Examples != 325 || c.CounterExamples != 7497 || taxa.CounterExamples != 7387 {
+		t.Fatalf("counts %+v, %d counterexample species (ecoPrimers: 325, 7497, 7387)", c, taxa.CounterExamples)
+	}
+	pairs, info, err := Search(corpus, taxa, tutorialParams(t))
+	if err != nil {
+		t.Fatal(err)
+	}
+	t.Logf("%+v", *info)
+
+	f, err := os.Open(filepath.Join("testdata", "ecoprimers_Cyprinidae_I1.pairs.tsv"))
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer f.Close()
+	type row struct {
+		good string
+		v    [5]int
+	}
+	want := map[string]row{}
+	sc := bufio.NewScanner(f)
+	for sc.Scan() {
+		var p1, p2 string
+		var r row
+		if _, err := fmt.Sscanf(sc.Text(), "%s\t%s\t%s\t%d\t%d\t%d\t%d\t%d", &p1, &p2, &r.good,
+			&r.v[0], &r.v[1], &r.v[2], &r.v[3], &r.v[4]); err != nil {
+			t.Fatal(err)
+		}
+		want[p1+"/"+p2] = r
+	}
+
+	if len(pairs) != len(want) {
+		t.Errorf("%d pairs, ecoPrimers reports %d", len(pairs), len(want))
+	}
+	bad := 0
+	for _, g := range pairs {
+		w, ok := want[g.Primer1+"/"+g.Primer2]
+		if !ok {
+			t.Errorf("pair %s/%s is not in the ecoPrimers result", g.Primer1, g.Primer2)
+			continue
+		}
+		good := string("bG"[b2i(g.Good1)]) + string("bG"[b2i(g.Good2)])
+		got := [5]int{g.Examples, g.CounterExamples, g.ExampleTaxa, g.CounterTaxa, g.Identified}
+		if got != w.v || good != w.good {
+			if bad++; bad <= 3 {
+				t.Errorf("pair %s/%s: got %s %v, ecoPrimers %s %v", g.Primer1, g.Primer2, good, got, w.good, w.v)
+			}
+		}
+	}
+}