import static org.testng.Assert.assertTrue;
import static org.testng.internal.junit.ArrayAsserts.assertArrayEquals;
+import jalview.api.analysis.SimilarityParamsI;
import jalview.io.DataSourceType;
import jalview.io.FileParse;
import jalview.io.ScoreMatrixFile;
import jalview.math.MatrixI;
+import jalview.schemes.ResidueProperties;
import java.io.IOException;
import java.net.MalformedURLException;
String[] seqs = new String[] { "FKL", "R D", "QIA", "GWC" };
ScoreMatrix sm = ScoreModels.getInstance().getBlosum62();
- MatrixI pairwise = sm.findSimilarities(seqs);
+ MatrixI pairwise = sm.findSimilarities(seqs, SimilarityParams.Jalview);
/*
* should be NxN where N = number of sequences
assertTrue(sm.equals(sm2));
assertEquals(sm.hashCode(), sm2.hashCode());
}
+
+ /**
+ * Tests for scoring options where the longer length of two sequences is used
+ */
+ @Test(groups = "Functional")
+ public void testcomputeSimilarity_matchLongestSequence()
+ {
+ // TODO params.matchGaps() is not used for ScoreMatrix
+ // - includeGaps is sufficient (there is no denominator)
+ // ==> bespoke parameters only 3 booleans?
+ /*
+ * for now, using space for gap to match callers of
+ * AlignmentView.getSequenceStrings()
+ * may change this to '-' (with corresponding change to matrices)
+ */
+ String s1 = "FR K S";
+ String s2 = "FS L";
+ ScoreMatrix blosum = ScoreModels.getInstance().getBlosum62();
+
+ /*
+ * score gap-gap and gap-char
+ * shorter sequence treated as if with trailing gaps
+ * score = F^F + R^S + -^- + K^- + -^L + S^-
+ * = 6 + -1 + 1 + -4 + -4 + -4 = -6
+ */
+ SimilarityParamsI params = new SimilarityParams(true, true, true, false);
+ assertEquals(blosum.computeSimilarity(s1, s2, params), -6d);
+ // matchGap (arg2) is ignored:
+ params = new SimilarityParams(true, false, true, false);
+ assertEquals(blosum.computeSimilarity(s1, s2, params), -6d);
+
+ /*
+ * score gap-char but not gap-gap
+ * score = F^F + R^S + 0 + K^- + -^L + S^-
+ * = 6 + -1 + 0 + -4 + -4 + -4 = -7
+ */
+ params = new SimilarityParams(false, true, true, false);
+ assertEquals(blosum.computeSimilarity(s1, s2, params), -7d);
+ // matchGap (arg2) is ignored:
+ params = new SimilarityParams(false, false, true, false);
+ assertEquals(blosum.computeSimilarity(s1, s2, params), -7d);
+
+ /*
+ * score gap-gap but not gap-char
+ * score = F^F + R^S + -^- + 0 + 0 + 0
+ * = 6 + -1 + 1 = 6
+ */
+ params = new SimilarityParams(true, false, false, false);
+ assertEquals(blosum.computeSimilarity(s1, s2, params), 6d);
+ // matchGap (arg2) is ignored:
+ params = new SimilarityParams(true, true, false, false);
+ assertEquals(blosum.computeSimilarity(s1, s2, params), 6d);
+
+ /*
+ * score neither gap-gap nor gap-char
+ * score = F^F + R^S + 0 + 0 + 0 + 0
+ * = 6 + -1 = 5
+ */
+ params = new SimilarityParams(false, false, false, false);
+ assertEquals(blosum.computeSimilarity(s1, s2, params), 5d);
+ // matchGap (arg2) is ignored:
+ params = new SimilarityParams(false, true, false, false);
+ assertEquals(blosum.computeSimilarity(s1, s2, params), 5d);
+ }
+
+ /**
+ * Tests for scoring options where only the shorter length of two sequences is
+ * used
+ */
+ @Test(groups = "Functional")
+ public void testcomputeSimilarity_matchShortestSequence()
+ {
+ // TODO params.matchGaps() is not used for ScoreMatrix
+ // - includeGaps is sufficient (there is no denominator)
+ // ==> bespoke parameters only 3 booleans?
+ /*
+ * for now, using space for gap to match callers of
+ * AlignmentView.getSequenceStrings()
+ * may change this to '-' (with corresponding change to matrices)
+ */
+ String s1 = "FR K S";
+ String s2 = "FS L";
+ ScoreMatrix blosum = ScoreModels.getInstance().getBlosum62();
+
+ /*
+ * score gap-gap and gap-char
+ * match shorter sequence only
+ * score = F^F + R^S + -^- + K^- + -^L
+ * = 6 + -1 + 1 + -4 + -4 = -2
+ */
+ SimilarityParamsI params = new SimilarityParams(true, true, true, true);
+ assertEquals(blosum.computeSimilarity(s1, s2, params), -2d);
+ // matchGap (arg2) is ignored:
+ params = new SimilarityParams(true, false, true, true);
+ assertEquals(blosum.computeSimilarity(s1, s2, params), -2d);
+
+ /*
+ * score gap-char but not gap-gap
+ * score = F^F + R^S + 0 + K^- + -^L
+ * = 6 + -1 + 0 + -4 + -4 = -3
+ */
+ params = new SimilarityParams(false, true, true, true);
+ assertEquals(blosum.computeSimilarity(s1, s2, params), -3d);
+ // matchGap (arg2) is ignored:
+ params = new SimilarityParams(false, false, true, true);
+ assertEquals(blosum.computeSimilarity(s1, s2, params), -3d);
+
+ /*
+ * score gap-gap but not gap-char
+ * score = F^F + R^S + -^- + 0 + 0
+ * = 6 + -1 + 1 = 6
+ */
+ params = new SimilarityParams(true, false, false, true);
+ assertEquals(blosum.computeSimilarity(s1, s2, params), 6d);
+ // matchGap (arg2) is ignored:
+ params = new SimilarityParams(true, true, false, true);
+ assertEquals(blosum.computeSimilarity(s1, s2, params), 6d);
+
+ /*
+ * score neither gap-gap nor gap-char
+ * score = F^F + R^S + 0 + 0 + 0
+ * = 6 + -1 = 5
+ */
+ params = new SimilarityParams(false, false, false, true);
+ assertEquals(blosum.computeSimilarity(s1, s2, params), 5d);
+ // matchGap (arg2) is ignored:
+ params = new SimilarityParams(false, true, false, true);
+ assertEquals(blosum.computeSimilarity(s1, s2, params), 5d);
+ }
+
+ @Test(groups = "Functional")
+ public void testSymmetric()
+ {
+ verifySymmetric(ScoreModels.getInstance().getBlosum62());
+ verifySymmetric(ScoreModels.getInstance().getPam250());
+ verifySymmetric(ScoreModels.getInstance().getDefaultModel(false)); // dna
+ }
+
+ private void verifySymmetric(ScoreMatrix sm)
+ {
+ float[][] m = sm.getMatrix();
+ int rows = m.length;
+ for (int row = 0; row < rows; row++)
+ {
+ assertEquals(m[row].length, rows);
+ for (int col = 0; col < rows; col++)
+ {
+ assertEquals(m[row][col], m[col][row], String.format("%s [%s, %s]",
+ sm.getName(), ResidueProperties.aa[row],
+ ResidueProperties.aa[col]));
+ }
+ }
+ }
+
+ /**
+ * A test that just asserts the expected values in the Blosum62 score matrix
+ */
+ @Test(groups = "Functional")
+ public void testBlosum62_values()
+ {
+ ScoreMatrix sm = ScoreModels.getInstance().getBlosum62();
+
+ /*
+ * verify expected scores against ARNDCQEGHILKMFPSTWYVBZX
+ * scraped from https://www.ncbi.nlm.nih.gov/Class/FieldGuide/BLOSUM62.txt
+ */
+ verifyValues(sm, 'A', new float[] { 4, -1, -2, -2, 0, -1, -1, 0, -2,
+ -1,
+ -1, -1, -1, -2, -1, 1, 0, -3, -2, 0, -2, -1, 0 });
+ verifyValues(sm, 'R', new float[] { -1, 5, 0, -2, -3, 1, 0, -2, 0, -3,
+ -2, 2, -1, -3, -2, -1, -1, -3, -2, -3, -1, 0, -1 });
+ verifyValues(sm, 'N', new float[] { -2, 0, 6, 1, -3, 0, 0, 0, 1, -3,
+ -3,
+ 0, -2, -3, -2, 1, 0, -4, -2, -3, 3, 0, -1 });
+ verifyValues(sm, 'D', new float[] { -2, -2, 1, 6, -3, 0, 2, -1, -1, -3,
+ -4, -1, -3, -3, -1, 0, -1, -4, -3, -3, 4, 1, -1 });
+ verifyValues(sm, 'C', new float[] { 0, -3, -3, -3, 9, -3, -4, -3, -3,
+ -1,
+ -1, -3, -1, -2, -3, -1, -1, -2, -2, -1, -3, -3, -2 });
+ verifyValues(sm, 'Q', new float[] { -1, 1, 0, 0, -3, 5, 2, -2, 0, -3,
+ -2,
+ 1, 0, -3, -1, 0, -1, -2, -1, -2, 0, 3, -1 });
+ verifyValues(sm, 'E', new float[] { -1, 0, 0, 2, -4, 2, 5, -2, 0, -3,
+ -3,
+ 1, -2, -3, -1, 0, -1, -3, -2, -2, 1, 4, -1 });
+ verifyValues(sm, 'G', new float[] { 0, -2, 0, -1, -3, -2, -2, 6, -2,
+ -4,
+ -4, -2, -3, -3, -2, 0, -2, -2, -3, -3, -1, -2, -1 });
+ verifyValues(sm, 'H', new float[] { -2, 0, 1, -1, -3, 0, 0, -2, 8, -3,
+ -3, -1, -2, -1, -2, -1, -2, -2, 2, -3, 0, 0, -1 });
+ verifyValues(sm, 'I', new float[] { -1, -3, -3, -3, -1, -3, -3, -4, -3,
+ 4, 2, -3, 1, 0, -3, -2, -1, -3, -1, 3, -3, -3, -1 });
+ verifyValues(sm, 'L', new float[] { -1, -2, -3, -4, -1, -2, -3, -4, -3,
+ 2, 4, -2, 2, 0, -3, -2, -1, -2, -1, 1, -4, -3, -1 });
+ verifyValues(sm, 'K', new float[] { -1, 2, 0, -1, -3, 1, 1, -2, -1, -3,
+ -2, 5, -1, -3, -1, 0, -1, -3, -2, -2, 0, 1, -1 });
+ verifyValues(sm, 'M', new float[] { -1, -1, -2, -3, -1, 0, -2, -3, -2,
+ 1,
+ 2, -1, 5, 0, -2, -1, -1, -1, -1, 1, -3, -1, -1 });
+ verifyValues(sm, 'F', new float[] { -2, -3, -3, -3, -2, -3, -3, -3, -1,
+ 0, 0, -3, 0, 6, -4, -2, -2, 1, 3, -1, -3, -3, -1 });
+ verifyValues(sm, 'P', new float[] { -1, -2, -2, -1, -3, -1, -1, -2, -2,
+ -3, -3, -1, -2, -4, 7, -1, -1, -4, -3, -2, -2, -1, -2 });
+ verifyValues(sm, 'S', new float[] { 1, -1, 1, 0, -1, 0, 0, 0, -1, -2,
+ -2,
+ 0, -1, -2, -1, 4, 1, -3, -2, -2, 0, 0, 0 });
+ verifyValues(sm, 'T', new float[] { 0, -1, 0, -1, -1, -1, -1, -2, -2,
+ -1,
+ -1, -1, -1, -2, -1, 1, 5, -2, -2, 0, -1, -1, 0 });
+ verifyValues(sm, 'W', new float[] { -3, -3, -4, -4, -2, -2, -3, -2, -2,
+ -3, -2, -3, -1, 1, -4, -3, -2, 11, 2, -3, -4, -3, -2 });
+ verifyValues(sm, 'Y', new float[] { -2, -2, -2, -3, -2, -1, -2, -3, 2,
+ -1, -1, -2, -1, 3, -3, -2, -2, 2, 7, -1, -3, -2, -1 });
+ verifyValues(sm, 'V', new float[] { 0, -3, -3, -3, -1, -2, -2, -3, -3,
+ 3,
+ 1, -2, 1, -1, -2, -2, 0, -3, -1, 4, -3, -2, -1 });
+ verifyValues(sm, 'B', new float[] { -2, -1, 3, 4, -3, 0, 1, -1, 0, -3,
+ -4, 0, -3, -3, -2, 0, -1, -4, -3, -3, 4, 1, -1 });
+ verifyValues(sm, 'Z', new float[] { -1, 0, 0, 1, -3, 3, 4, -2, 0, -3,
+ -3,
+ 1, -1, -3, -1, 0, -1, -3, -2, -2, 1, 4, -1 });
+ verifyValues(sm, 'X', new float[] { 0, -1, -1, -1, -2, -1, -1, -1, -1,
+ -1, -1, -1, -1, -1, -2, 0, 0, -2, -1, -1, -1, -1, -1 });
+ }
+
+ /**
+ * Helper method to check pairwise scores for one residue
+ *
+ * @param sm
+ * @param res
+ * @param expected
+ * score values against 'res', in ResidueProperties.aaIndex order
+ */
+ private void verifyValues(ScoreMatrix sm, char res, float[] expected)
+ {
+ for (int j = 0; j < expected.length; j++)
+ {
+ char c2 = ResidueProperties.aa[j].charAt(0);
+ assertEquals(sm.getPairwiseScore(res, c2), expected[j],
+ String.format("%s->%s", res, c2));
+ }
+ }
}