+ /*
+ * 200 sequences of which 30 gapped (170 ungapped)
+ * max count 70 for modal residue 'G'
+ */
+ ProfileI profile = new Profile(200, 30, 70, "G");
+ ResidueCount counts = new ResidueCount();
+ counts.put('G', 70);
+ counts.put('R', 60);
+ counts.put('L', 38);
+ counts.put('H', 2);
+ profile.setCounts(counts);
+
+ /*
+ * [0, noOfValues, totalPercent, char1, count1, ...]
+ * G: 70/170 = 41.2 = 41
+ * R: 60/170 = 35.3 = 35
+ * L: 38/170 = 22.3 = 22
+ * H: 2/170 = 1
+ * total (rounded) percentages = 99
+ */
+ int[] extracted = AAFrequency.extractProfile(profile, true);
+ int[] expected = new int[] { 0, 4, 99, 'G', 41, 'R', 35, 'L', 22, 'H',
+ 1 };
+ org.testng.Assert.assertEquals(extracted, expected);
+
+ /*
+ * add some counts of 1; these round down to 0% and should be discarded
+ */
+ counts.put('G', 68); // 68/170 = 40% exactly (percentages now total 98)
+ counts.put('Q', 1);
+ counts.put('K', 1);
+ extracted = AAFrequency.extractProfile(profile, true);
+ expected = new int[] { 0, 4, 98, 'G', 40, 'R', 35, 'L', 22, 'H', 1 };
+ org.testng.Assert.assertEquals(extracted, expected);
+
+ }
+
+ /**
+ * Tests for the profile calculation where gaps are included i.e. the
+ * denominator is the total number of sequences in the column
+ */
+ @Test(groups = { "Functional" })
+ public void testExtractProfile_countGaps()
+ {
+ /*
+ * 200 sequences of which 30 gapped (170 ungapped)
+ * max count 70 for modal residue 'G'
+ */
+ ProfileI profile = new Profile(200, 30, 70, "G");
+ ResidueCount counts = new ResidueCount();
+ counts.put('G', 70);
+ counts.put('R', 60);
+ counts.put('L', 38);
+ counts.put('H', 2);
+ profile.setCounts(counts);
+
+ /*
+ * [0, noOfValues, totalPercent, char1, count1, ...]
+ * G: 70/200 = 35%
+ * R: 60/200 = 30%
+ * L: 38/200 = 19%
+ * H: 2/200 = 1%
+ * total (rounded) percentages = 85
+ */
+ int[] extracted = AAFrequency.extractProfile(profile, false);
+ int[] expected = new int[] { AlignmentAnnotation.SEQUENCE_PROFILE, 4,
+ 85, 'G', 35, 'R', 30, 'L', 19, 'H',
+ 1 };
+ org.testng.Assert.assertEquals(extracted, expected);
+
+ /*
+ * add some counts of 1; these round down to 0% and should be discarded
+ */
+ counts.put('G', 68); // 68/200 = 34%
+ counts.put('Q', 1);
+ counts.put('K', 1);
+ extracted = AAFrequency.extractProfile(profile, false);
+ expected = new int[] { AlignmentAnnotation.SEQUENCE_PROFILE, 4, 84, 'G',
+ 34, 'R', 30, 'L', 19, 'H', 1 };
+ org.testng.Assert.assertEquals(extracted, expected);
+
+ }
+
+ @Test(groups = { "Functional" })
+ public void testExtractCdnaProfile()
+ {
+ /*
+ * 200 sequences of which 30 gapped (170 ungapped)
+ * max count 70 for modal residue 'G'
+ */
+ Hashtable profile = new Hashtable();
+
+ /*
+ * cdna profile is {seqCount, ungappedCount, codonCount1, ...codonCount64}
+ * where 1..64 positions correspond to encoded codons
+ * see CodingUtils.encodeCodon()
+ */
+ int[] codonCounts = new int[66];
+ char[] codon1 = new char[] { 'G', 'C', 'A' };
+ char[] codon2 = new char[] { 'c', 'C', 'A' };
+ char[] codon3 = new char[] { 't', 'g', 'A' };
+ char[] codon4 = new char[] { 'G', 'C', 't' };
+ int encoded1 = CodingUtils.encodeCodon(codon1);
+ int encoded2 = CodingUtils.encodeCodon(codon2);
+ int encoded3 = CodingUtils.encodeCodon(codon3);
+ int encoded4 = CodingUtils.encodeCodon(codon4);
+ codonCounts[2 + encoded1] = 30;
+ codonCounts[2 + encoded2] = 70;
+ codonCounts[2 + encoded3] = 9;
+ codonCounts[2 + encoded4] = 1;
+ codonCounts[0] = 120;
+ codonCounts[1] = 110;
+ profile.put(AAFrequency.PROFILE, codonCounts);
+
+ /*
+ * [0, noOfValues, totalPercent, char1, count1, ...]
+ * codon1: 30/110 = 27.2 = 27%
+ * codon2: 70/110 = 63.6% = 63%
+ * codon3: 9/110 = 8.1% = 8%
+ * codon4: 1/110 = 0.9% = 0% should be discarded
+ * total (rounded) percentages = 98
+ */
+ int[] extracted = AAFrequency.extractCdnaProfile(profile, true);
+ int[] expected = new int[] { AlignmentAnnotation.CDNA_PROFILE, 3, 98,
+ encoded2, 63, encoded1, 27, encoded3, 8 };
+ org.testng.Assert.assertEquals(extracted, expected);
+ }
+
+ @Test(groups = { "Functional" })
+ public void testExtractCdnaProfile_countGaps()
+ {
+ /*
+ * 200 sequences of which 30 gapped (170 ungapped)
+ * max count 70 for modal residue 'G'
+ */
+ Hashtable profile = new Hashtable();
+
+ /*
+ * cdna profile is {seqCount, ungappedCount, codonCount1, ...codonCount64}
+ * where 1..64 positions correspond to encoded codons
+ * see CodingUtils.encodeCodon()
+ */
+ int[] codonCounts = new int[66];
+ char[] codon1 = new char[] { 'G', 'C', 'A' };
+ char[] codon2 = new char[] { 'c', 'C', 'A' };
+ char[] codon3 = new char[] { 't', 'g', 'A' };
+ char[] codon4 = new char[] { 'G', 'C', 't' };
+ int encoded1 = CodingUtils.encodeCodon(codon1);
+ int encoded2 = CodingUtils.encodeCodon(codon2);
+ int encoded3 = CodingUtils.encodeCodon(codon3);
+ int encoded4 = CodingUtils.encodeCodon(codon4);
+ codonCounts[2 + encoded1] = 30;
+ codonCounts[2 + encoded2] = 70;
+ codonCounts[2 + encoded3] = 9;
+ codonCounts[2 + encoded4] = 1;
+ codonCounts[0] = 120;
+ codonCounts[1] = 110;
+ profile.put(AAFrequency.PROFILE, codonCounts);
+
+ /*
+ * [0, noOfValues, totalPercent, char1, count1, ...]
+ * codon1: 30/120 = 25%
+ * codon2: 70/120 = 58.3 = 58%
+ * codon3: 9/120 = 7.5 = 7%
+ * codon4: 1/120 = 0.8 = 0% should be discarded
+ * total (rounded) percentages = 90
+ */
+ int[] extracted = AAFrequency.extractCdnaProfile(profile, false);
+ int[] expected = new int[] { AlignmentAnnotation.CDNA_PROFILE, 3, 90,
+ encoded2, 58, encoded1, 25, encoded3, 7 };
+ org.testng.Assert.assertEquals(extracted, expected);
+ }
+
+ @Test(groups = { "Functional" })
+ public void testExtractHMMProfile()
+ throws MalformedURLException, IOException
+ {
+ int[] expected = { 0, 4, 100, 'T', 71, 'C', 12, 'G', 9, 'A', 9 };
+ int[] actual = AAFrequency.extractHMMProfile(hmm, 17, false, false);
+ for (int i = 0; i < actual.length; i++)
+ {
+ if (i == 2)
+ {
+ assertEquals(actual[i], expected[i]);
+ }
+ else
+ {
+ assertEquals(actual[i], expected[i]);
+ }
+ }
+
+ int[] expected2 = { 0, 4, 100, 'A', 85, 'C', 0, 'G', 0, 'T', 0 };
+ int[] actual2 = AAFrequency.extractHMMProfile(hmm, 2, true, false);
+ for (int i = 0; i < actual2.length; i++)
+ {
+ if (i == 2)
+ {
+ assertEquals(actual[i], expected[i]);
+ }
+ else
+ {
+ assertEquals(actual[i], expected[i]);
+ }
+ }
+
+ assertNull(AAFrequency.extractHMMProfile(null, 98978867, true, false));
+ }
+
+ @Test(groups = { "Functional" })
+ public void testGetAnalogueCount()
+ {
+ /*
+ * 'T' in column 0 has emission probability 0.7859, scales to 7859
+ */
+ int count = AAFrequency.getAnalogueCount(hmm, 0, 'T', false, false);
+ assertEquals(7859, count);
+
+ /*
+ * same with 'use info height': value is multiplied by log ratio
+ * log(value / background) / log(2) = log(0.7859/0.25)/0.693
+ * = log(3.1)/0.693 = 1.145/0.693 = 1.66
+ * so value becomes 1.2987 and scales up to 12987
+ */
+ count = AAFrequency.getAnalogueCount(hmm, 0, 'T', false, true);
+ assertEquals(12987, count);
+
+ /*
+ * 'G' in column 20 has emission probability 0.75457, scales to 7546
+ */
+ count = AAFrequency.getAnalogueCount(hmm, 20, 'G', false, false);
+ assertEquals(7546, count);
+
+ /*
+ * 'G' in column 1077 has emission probability 0.0533, here
+ * ignored (set to 0) since below background of 0.25
+ */
+ count = AAFrequency.getAnalogueCount(hmm, 1077, 'G', true, false);
+ assertEquals(0, count);
+ }
+
+ @Test(groups = { "Functional" })
+ public void testCompleteInformation()
+ {
+ ProfileI prof1 = new Profile(1, 0, 100, "A");
+ ProfileI prof2 = new Profile(1, 0, 100, "-");
+
+ ProfilesI profs = new Profiles(new ProfileI[] { prof1, prof2 });
+ Annotation ann1 = new Annotation(6.5f);
+ Annotation ann2 = new Annotation(0f);
+ Annotation[] annots = new Annotation[] { ann1, ann2 };
+ SequenceI seq = new Sequence("", "AA", 0, 0);
+ seq.setHMM(hmm);
+ AlignmentAnnotation annot = new AlignmentAnnotation("", "", annots);
+ annot.setSequenceRef(seq);
+ AAFrequency.completeInformation(annot, profs, 0, 1);
+ float ic = annot.annotations[0].value;
+ assertEquals(0.91532f, ic, 0.0001f);
+ ic = annot.annotations[1].value;
+ assertEquals(0f, ic, 0.0001f);
+ int i = 0;