X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=test%2Fjalview%2Fanalysis%2FAAFrequencyTest.java;h=14cc526459c6de174f53b622ed74e3cd4db5bf47;hb=c794c5033adeee182b03a5ea92c0a7495a29661f;hp=2b6c5121bdbfbfa39579814ff7ddd5f8e45b9ecd;hpb=3609d4b908fa64cab35f2348401baab3347188fc;p=jalview.git diff --git a/test/jalview/analysis/AAFrequencyTest.java b/test/jalview/analysis/AAFrequencyTest.java index 2b6c512..14cc526 100644 --- a/test/jalview/analysis/AAFrequencyTest.java +++ b/test/jalview/analysis/AAFrequencyTest.java @@ -30,6 +30,7 @@ import jalview.datamodel.Profile; import jalview.datamodel.ProfileI; import jalview.datamodel.Profiles; import jalview.datamodel.ProfilesI; +import jalview.datamodel.ResidueCount; import jalview.datamodel.Sequence; import jalview.datamodel.SequenceI; import jalview.gui.JvOptionPane; @@ -40,6 +41,8 @@ import jalview.io.HMMFile; import java.io.IOException; import java.net.MalformedURLException; +import java.util.Hashtable; + import org.testng.annotations.BeforeClass; import org.testng.annotations.Test; @@ -254,6 +257,185 @@ public class AAFrequencyTest assertEquals("T", ann.displayCharacter); } + /** + * Test to include rounding down of a non-zero count to 0% (JAL-3202) + */ + @Test(groups = { "Functional" }) + public void testExtractProfile() + { + /* + * 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 @@ -342,5 +524,4 @@ public class AAFrequencyTest assertEquals(0f, ic, 0.0001f); int i = 0; } - }