X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=test%2Fjalview%2Fanalysis%2FAlignmentUtilsTests.java;h=e231e7f6e40bbad24472830efbfa81a6bd5a7baf;hb=57738a1f3c19b1c3a00bd3ac5108f8cd0af32f99;hp=1bff8bf5358d380096bf507d1f8e751b99a3b902;hpb=06de78be50c3934158fa1d35ec92ad86b54e959f;p=jalview.git diff --git a/test/jalview/analysis/AlignmentUtilsTests.java b/test/jalview/analysis/AlignmentUtilsTests.java index 1bff8bf..e231e7f 100644 --- a/test/jalview/analysis/AlignmentUtilsTests.java +++ b/test/jalview/analysis/AlignmentUtilsTests.java @@ -48,8 +48,10 @@ import jalview.io.DataSourceType; import jalview.io.FileFormat; import jalview.io.FileFormatI; import jalview.io.FormatAdapter; +import jalview.io.gff.SequenceOntologyI; import jalview.util.MapList; import jalview.util.MappingUtils; +import jalview.ws.params.InvalidArgumentException; import java.io.IOException; import java.util.ArrayList; @@ -83,15 +85,14 @@ public class AlignmentUtilsTests SequenceI s1 = ts.deriveSequence().getSubSequence(i, i + 7); al.addSequence(s1); } - System.out.println(new AppletFormatAdapter().formatSequences( - FileFormat.Clustal, - al, true)); + System.out.println(new AppletFormatAdapter() + .formatSequences(FileFormat.Clustal, al, true)); for (int flnk = -1; flnk < 25; flnk++) { AlignmentI exp = AlignmentUtils.expandContext(al, flnk); System.out.println("\nFlank size: " + flnk); - System.out.println(new AppletFormatAdapter().formatSequences( - FileFormat.Clustal, exp, true)); + System.out.println(new AppletFormatAdapter() + .formatSequences(FileFormat.Clustal, exp, true)); if (flnk == -1) { /* @@ -101,11 +102,10 @@ public class AlignmentUtilsTests { String ung = sq.getSequenceAsString().replaceAll("-+", ""); final String errorMsg = "Flanking sequence not the same as original dataset sequence.\n" - + ung - + "\n" + + ung + "\n" + sq.getDatasetSequence().getSequenceAsString(); - assertTrue(errorMsg, ung.equalsIgnoreCase(sq.getDatasetSequence() - .getSequenceAsString())); + assertTrue(errorMsg, ung.equalsIgnoreCase( + sq.getDatasetSequence().getSequenceAsString())); } } else if (flnk == 24) @@ -175,8 +175,8 @@ public class AlignmentUtilsTests * Expand the subsequence to the full sequence abcDEFghi */ AlignmentI expanded = AlignmentUtils.expandContext(al, -1); - assertEquals("abcDEFghi", expanded.getSequenceAt(0) - .getSequenceAsString()); + assertEquals("abcDEFghi", + expanded.getSequenceAt(0).getSequenceAsString()); /* * Confirm the alignment and sequence have the same SS annotation, @@ -247,8 +247,8 @@ public class AlignmentUtilsTests protected AlignmentI loadAlignment(final String data, FileFormatI format) throws IOException { - AlignmentI a = new FormatAdapter().readFile(data, - DataSourceType.PASTE, format); + AlignmentI a = new FormatAdapter().readFile(data, DataSourceType.PASTE, + format); a.setDataset(null); return a; } @@ -263,14 +263,14 @@ public class AlignmentUtilsTests @Test(groups = { "Functional" }) public void testMapProteinAlignmentToCdna_noXrefs() throws IOException { - List protseqs = new ArrayList(); + List protseqs = new ArrayList<>(); protseqs.add(new Sequence("UNIPROT|V12345", "EIQ")); protseqs.add(new Sequence("UNIPROT|V12346", "EIQ")); protseqs.add(new Sequence("UNIPROT|V12347", "SAR")); AlignmentI protein = new Alignment(protseqs.toArray(new SequenceI[3])); protein.setDataset(null); - List dnaseqs = new ArrayList(); + List dnaseqs = new ArrayList<>(); dnaseqs.add(new Sequence("EMBL|A11111", "TCAGCACGC")); // = SAR dnaseqs.add(new Sequence("EMBL|A22222", "GAGATACAA")); // = EIQ dnaseqs.add(new Sequence("EMBL|A33333", "GAAATCCAG")); // = EIQ @@ -297,11 +297,13 @@ public class AlignmentUtilsTests MapList mapList = protMappings[0].getMap(); assertEquals(3, mapList.getFromRatio()); assertEquals(1, mapList.getToRatio()); - assertTrue(Arrays.equals(new int[] { 1, 9 }, mapList.getFromRanges() - .get(0))); + assertTrue( + Arrays.equals(new int[] + { 1, 9 }, mapList.getFromRanges().get(0))); assertEquals(1, mapList.getFromRanges().size()); - assertTrue(Arrays.equals(new int[] { 1, 3 }, - mapList.getToRanges().get(0))); + assertTrue( + Arrays.equals(new int[] + { 1, 3 }, mapList.getToRanges().get(0))); assertEquals(1, mapList.getToRanges().size()); // V12346 mapped to A33333 @@ -374,7 +376,8 @@ public class AlignmentUtilsTests * Exons at codon 2 (AAA) and 4 (TTT) */ MapList map = new MapList(new int[] { 4, 6, 10, 12 }, - new int[] { 1, 2 }, 3, 1); + new int[] + { 1, 2 }, 3, 1); /* * Simple case: no gaps in dna @@ -385,14 +388,14 @@ public class AlignmentUtilsTests /* * Add gaps to dna - but ignore when realigning. */ - checkAlignSequenceAs("-G-G-G--A--A---AC-CC-T-TT-GG-G-", "--A-L-", - false, false, map, "GGG---AAACCCTTTGGG"); + checkAlignSequenceAs("-G-G-G--A--A---AC-CC-T-TT-GG-G-", "--A-L-", false, + false, map, "GGG---AAACCCTTTGGG"); /* * Add gaps to dna - include within exons only when realigning. */ - checkAlignSequenceAs("-G-G-G--A--A---A-C-CC-T-TT-GG-G-", "--A-L-", - true, false, map, "GGG---A--A---ACCCT-TTGGG"); + checkAlignSequenceAs("-G-G-G--A--A---A-C-CC-T-TT-GG-G-", "--A-L-", true, + false, map, "GGG---A--A---ACCCT-TTGGG"); /* * Include gaps outside exons only when realigning. @@ -403,14 +406,14 @@ public class AlignmentUtilsTests /* * Include gaps following first intron if we are 'preserving mapped gaps' */ - checkAlignSequenceAs("-G-G-G--A--A---A-C-CC-T-TT-GG-G-", "--A-L-", - true, true, map, "-G-G-G--A--A---A-C-CC-T-TT-GG-G-"); + checkAlignSequenceAs("-G-G-G--A--A---A-C-CC-T-TT-GG-G-", "--A-L-", true, + true, map, "-G-G-G--A--A---A-C-CC-T-TT-GG-G-"); /* * Include all gaps in dna when realigning. */ - checkAlignSequenceAs("-G-G-G--A--A---A-C-CC-T-TT-GG-G-", "--A-L-", - true, true, map, "-G-G-G--A--A---A-C-CC-T-TT-GG-G-"); + checkAlignSequenceAs("-G-G-G--A--A---A-C-CC-T-TT-GG-G-", "--A-L-", true, + true, map, "-G-G-G--A--A---A-C-CC-T-TT-GG-G-"); } /** @@ -422,8 +425,9 @@ public class AlignmentUtilsTests /* * Exons at codon 2 (AAA) and 4 (TTT) mapped to A and P */ - final MapList map = new MapList(new int[] { 4, 6, 10, 12 }, new int[] { - 1, 1, 3, 3 }, 3, 1); + final MapList map = new MapList(new int[] { 4, 6, 10, 12 }, + new int[] + { 1, 1, 3, 3 }, 3, 1); /* * -L- 'aligns' ccc------ @@ -454,8 +458,8 @@ public class AlignmentUtilsTests SequenceI alignFrom = new Sequence("Seq2", alignModel); alignFrom.createDatasetSequence(); AlignedCodonFrame acf = new AlignedCodonFrame(); - acf.addMap(alignMe.getDatasetSequence(), - alignFrom.getDatasetSequence(), map); + acf.addMap(alignMe.getDatasetSequence(), alignFrom.getDatasetSequence(), + map); AlignmentUtils.alignSequenceAs(alignMe, alignFrom, acf, "---", '-', preserveMappedGaps, preserveUnmappedGaps); @@ -472,7 +476,8 @@ public class AlignmentUtilsTests /* * Intron GGGAAA followed by exon CCCTTT */ - MapList map = new MapList(new int[] { 7, 12 }, new int[] { 1, 2 }, 3, 1); + MapList map = new MapList(new int[] { 7, 12 }, new int[] { 1, 2 }, 3, + 1); checkAlignSequenceAs("GG-G-AA-A-C-CC-T-TT", "AL", false, true, map, "GG-G-AA-ACCCTTT"); @@ -498,16 +503,18 @@ public class AlignmentUtilsTests SequenceI prot2 = new Sequence("Seq2", "CHYQ"); SequenceI prot3 = new Sequence("Seq3", "CHYQ"); SequenceI prot4 = new Sequence("Seq4", "R-QSV"); // unmapped, unchanged - AlignmentI protein = new Alignment(new SequenceI[] { prot1, prot2, - prot3, prot4 }); + AlignmentI protein = new Alignment( + new SequenceI[] + { prot1, prot2, prot3, prot4 }); protein.setDataset(null); - MapList map = new MapList(new int[] { 1, 12 }, new int[] { 1, 4 }, 3, 1); + MapList map = new MapList(new int[] { 1, 12 }, new int[] { 1, 4 }, 3, + 1); AlignedCodonFrame acf = new AlignedCodonFrame(); acf.addMap(dna1.getDatasetSequence(), prot1.getDatasetSequence(), map); acf.addMap(dna2.getDatasetSequence(), prot2.getDatasetSequence(), map); acf.addMap(dna3.getDatasetSequence(), prot3.getDatasetSequence(), map); - ArrayList acfs = new ArrayList(); + ArrayList acfs = new ArrayList<>(); acfs.add(acf); protein.setCodonFrames(acfs); @@ -571,28 +578,28 @@ public class AlignmentUtilsTests "F*PK*G".toCharArray())); // wrong protein - assertFalse(AlignmentUtils.translatesAs("tttcccaaaggg".toCharArray(), - 0, "FPMG".toCharArray())); + assertFalse(AlignmentUtils.translatesAs("tttcccaaaggg".toCharArray(), 0, + "FPMG".toCharArray())); // truncated dna assertFalse(AlignmentUtils.translatesAs("tttcccaaagg".toCharArray(), 0, "FPKG".toCharArray())); // truncated protein - assertFalse(AlignmentUtils.translatesAs("tttcccaaaggg".toCharArray(), - 0, "FPK".toCharArray())); + assertFalse(AlignmentUtils.translatesAs("tttcccaaaggg".toCharArray(), 0, + "FPK".toCharArray())); // overlong dna (doesn't end in stop codon) - assertFalse(AlignmentUtils.translatesAs( - "tttcccaaagggttt".toCharArray(), 0, "FPKG".toCharArray())); + assertFalse(AlignmentUtils.translatesAs("tttcccaaagggttt".toCharArray(), + 0, "FPKG".toCharArray())); // dna + stop codon + more assertFalse(AlignmentUtils.translatesAs( "tttcccaaagggttaga".toCharArray(), 0, "FPKG".toCharArray())); // overlong protein - assertFalse(AlignmentUtils.translatesAs("tttcccaaaggg".toCharArray(), - 0, "FPKGQ".toCharArray())); + assertFalse(AlignmentUtils.translatesAs("tttcccaaaggg".toCharArray(), 0, + "FPKGQ".toCharArray())); } /** @@ -605,14 +612,14 @@ public class AlignmentUtilsTests public void testMapProteinAlignmentToCdna_withStartAndStopCodons() throws IOException { - List protseqs = new ArrayList(); + List protseqs = new ArrayList<>(); protseqs.add(new Sequence("UNIPROT|V12345", "EIQ")); protseqs.add(new Sequence("UNIPROT|V12346", "EIQ")); protseqs.add(new Sequence("UNIPROT|V12347", "SAR")); AlignmentI protein = new Alignment(protseqs.toArray(new SequenceI[3])); protein.setDataset(null); - List dnaseqs = new ArrayList(); + List dnaseqs = new ArrayList<>(); // start + SAR: dnaseqs.add(new Sequence("EMBL|A11111", "ATGTCAGCACGC")); // = EIQ + stop @@ -642,11 +649,13 @@ public class AlignmentUtilsTests MapList mapList = protMappings[0].getMap(); assertEquals(3, mapList.getFromRatio()); assertEquals(1, mapList.getToRatio()); - assertTrue(Arrays.equals(new int[] { 1, 9 }, mapList.getFromRanges() - .get(0))); + assertTrue( + Arrays.equals(new int[] + { 1, 9 }, mapList.getFromRanges().get(0))); assertEquals(1, mapList.getFromRanges().size()); - assertTrue(Arrays.equals(new int[] { 1, 3 }, - mapList.getToRanges().get(0))); + assertTrue( + Arrays.equals(new int[] + { 1, 3 }, mapList.getToRanges().get(0))); assertEquals(1, mapList.getToRanges().size()); // V12346 mapped from A33333 starting position 4 @@ -659,11 +668,13 @@ public class AlignmentUtilsTests mapList = protMappings[0].getMap(); assertEquals(3, mapList.getFromRatio()); assertEquals(1, mapList.getToRatio()); - assertTrue(Arrays.equals(new int[] { 4, 12 }, mapList.getFromRanges() - .get(0))); + assertTrue( + Arrays.equals(new int[] + { 4, 12 }, mapList.getFromRanges().get(0))); assertEquals(1, mapList.getFromRanges().size()); - assertTrue(Arrays.equals(new int[] { 1, 3 }, - mapList.getToRanges().get(0))); + assertTrue( + Arrays.equals(new int[] + { 1, 3 }, mapList.getToRanges().get(0))); assertEquals(1, mapList.getToRanges().size()); // V12347 mapped to A11111 starting position 4 @@ -676,11 +687,13 @@ public class AlignmentUtilsTests mapList = protMappings[0].getMap(); assertEquals(3, mapList.getFromRatio()); assertEquals(1, mapList.getToRatio()); - assertTrue(Arrays.equals(new int[] { 4, 12 }, mapList.getFromRanges() - .get(0))); + assertTrue( + Arrays.equals(new int[] + { 4, 12 }, mapList.getFromRanges().get(0))); assertEquals(1, mapList.getFromRanges().size()); - assertTrue(Arrays.equals(new int[] { 1, 3 }, - mapList.getToRanges().get(0))); + assertTrue( + Arrays.equals(new int[] + { 1, 3 }, mapList.getToRanges().get(0))); assertEquals(1, mapList.getToRanges().size()); // no mapping involving the 'extra' A44444 @@ -697,14 +710,14 @@ public class AlignmentUtilsTests @Test(groups = { "Functional" }) public void testMapProteinAlignmentToCdna_withXrefs() throws IOException { - List protseqs = new ArrayList(); + List protseqs = new ArrayList<>(); protseqs.add(new Sequence("UNIPROT|V12345", "EIQ")); protseqs.add(new Sequence("UNIPROT|V12346", "EIQ")); protseqs.add(new Sequence("UNIPROT|V12347", "SAR")); AlignmentI protein = new Alignment(protseqs.toArray(new SequenceI[3])); protein.setDataset(null); - List dnaseqs = new ArrayList(); + List dnaseqs = new ArrayList<>(); dnaseqs.add(new Sequence("EMBL|A11111", "TCAGCACGC")); // = SAR dnaseqs.add(new Sequence("EMBL|A22222", "ATGGAGATACAA")); // = start + EIQ dnaseqs.add(new Sequence("EMBL|A33333", "GAAATCCAG")); // = EIQ @@ -774,18 +787,18 @@ public class AlignmentUtilsTests public void testMapProteinAlignmentToCdna_prioritiseXrefs() throws IOException { - List protseqs = new ArrayList(); + List protseqs = new ArrayList<>(); protseqs.add(new Sequence("UNIPROT|V12345", "EIQ")); protseqs.add(new Sequence("UNIPROT|V12346", "EIQ")); AlignmentI protein = new Alignment( protseqs.toArray(new SequenceI[protseqs.size()])); protein.setDataset(null); - List dnaseqs = new ArrayList(); + List dnaseqs = new ArrayList<>(); dnaseqs.add(new Sequence("EMBL|A11111", "GAAATCCAG")); // = EIQ dnaseqs.add(new Sequence("EMBL|A22222", "GAAATTCAG")); // = EIQ - AlignmentI cdna = new Alignment(dnaseqs.toArray(new SequenceI[dnaseqs - .size()])); + AlignmentI cdna = new Alignment( + dnaseqs.toArray(new SequenceI[dnaseqs.size()])); cdna.setDataset(null); // Xref A22222 to V12345 (should get mapped) @@ -836,11 +849,14 @@ public class AlignmentUtilsTests ann2.setSequenceRef(seq2); AlignmentAnnotation ann3 = new AlignmentAnnotation("Structure", "ann3", anns); - AlignmentAnnotation ann4 = new AlignmentAnnotation("Temp", "ann4", anns); + AlignmentAnnotation ann4 = new AlignmentAnnotation("Temp", "ann4", + anns); ann4.setSequenceRef(seq1); - AlignmentAnnotation ann5 = new AlignmentAnnotation("Temp", "ann5", anns); + AlignmentAnnotation ann5 = new AlignmentAnnotation("Temp", "ann5", + anns); ann5.setSequenceRef(seq2); - AlignmentAnnotation ann6 = new AlignmentAnnotation("Temp", "ann6", anns); + AlignmentAnnotation ann6 = new AlignmentAnnotation("Temp", "ann6", + anns); AlignmentI al = new Alignment(new SequenceI[] { seq1, seq2, seq3 }); al.addAnnotation(ann1); // Structure for Seq1 al.addAnnotation(ann2); // Structure for Seq2 @@ -848,8 +864,8 @@ public class AlignmentUtilsTests al.addAnnotation(ann4); // Temp for seq1 al.addAnnotation(ann5); // Temp for seq2 al.addAnnotation(ann6); // Temp for no sequence - List types = new ArrayList(); - List scope = new ArrayList(); + List types = new ArrayList<>(); + List scope = new ArrayList<>(); /* * Set all sequence related Structure to hidden (ann1, ann2) @@ -1012,8 +1028,8 @@ public class AlignmentUtilsTests * put a variant feature on dna2 base 8 * - should transfer to cds2 base 5 */ - dna2.addSequenceFeature(new SequenceFeature("variant", "hgmd", 8, 8, - 0f, null)); + dna2.addSequenceFeature( + new SequenceFeature("variant", "hgmd", 8, 8, 0f, null)); /* * need a sourceDbRef if we are to construct dbrefs to the CDS @@ -1030,14 +1046,16 @@ public class AlignmentUtilsTests * CDS sequences are 'discovered' from dna-to-protein mappings on the alignment * dataset (e.g. added from dbrefs by CrossRef.findXrefSequences) */ - MapList mapfordna1 = new MapList(new int[] { 4, 6, 10, 12 }, new int[] { - 1, 2 }, 3, 1); + MapList mapfordna1 = new MapList(new int[] { 4, 6, 10, 12 }, + new int[] + { 1, 2 }, 3, 1); AlignedCodonFrame acf = new AlignedCodonFrame(); acf.addMap(dna1.getDatasetSequence(), pep1.getDatasetSequence(), mapfordna1); dna.addCodonFrame(acf); MapList mapfordna2 = new MapList(new int[] { 1, 3, 7, 9, 13, 15 }, - new int[] { 1, 3 }, 3, 1); + new int[] + { 1, 3 }, 3, 1); acf = new AlignedCodonFrame(); acf.addMap(dna2.getDatasetSequence(), pep2.getDatasetSequence(), mapfordna2); @@ -1051,17 +1069,18 @@ public class AlignmentUtilsTests DBRefEntry dna1xref = new DBRefEntry("UNIPROT", "ENSEMBL", "pep1", new Mapping(mapfordna1)); dna1.addDBRef(dna1xref); - assertEquals(2, dna1.getDBRefs().length); // to self and to pep1 + assertEquals(2, dna1.getDBRefs().size()); // to self and to pep1 DBRefEntry dna2xref = new DBRefEntry("UNIPROT", "ENSEMBL", "pep2", new Mapping(mapfordna2)); dna2.addDBRef(dna2xref); - assertEquals(2, dna2.getDBRefs().length); // to self and to pep2 + assertEquals(2, dna2.getDBRefs().size()); // to self and to pep2 /* * execute method under test: */ - AlignmentI cds = AlignmentUtils.makeCdsAlignment(new SequenceI[] { - dna1, dna2 }, dna.getDataset(), null); + AlignmentI cds = AlignmentUtils + .makeCdsAlignment(new SequenceI[] + { dna1, dna2 }, dna.getDataset(), null); /* * verify cds sequences @@ -1083,16 +1102,16 @@ public class AlignmentUtilsTests * verify CDS has a dbref with mapping to peptide */ assertNotNull(cds1Dss.getDBRefs()); - assertEquals(2, cds1Dss.getDBRefs().length); - dbref = cds1Dss.getDBRefs()[0]; + assertEquals(2, cds1Dss.getDBRefs().size()); + dbref = cds1Dss.getDBRefs().get(0); assertEquals(dna1xref.getSource(), dbref.getSource()); // version is via ensembl's primary ref assertEquals(dna1xref.getVersion(), dbref.getVersion()); assertEquals(dna1xref.getAccessionId(), dbref.getAccessionId()); assertNotNull(dbref.getMap()); assertSame(pep1.getDatasetSequence(), dbref.getMap().getTo()); - MapList cdsMapping = new MapList(new int[] { 1, 6 }, - new int[] { 1, 2 }, 3, 1); + MapList cdsMapping = new MapList(new int[] { 1, 6 }, new int[] { 1, 2 }, + 3, 1); assertEquals(cdsMapping, dbref.getMap().getMap()); /* @@ -1100,8 +1119,8 @@ public class AlignmentUtilsTests */ assertNotNull(pep1.getDBRefs()); // FIXME pep1.getDBRefs() is 1 - is that the correct behaviour ? - assertEquals(2, pep1.getDBRefs().length); - dbref = pep1.getDBRefs()[1]; + assertEquals(2, pep1.getDBRefs().size()); + dbref = pep1.getDBRefs().get(1); assertEquals("ENSEMBL", dbref.getSource()); assertEquals("0", dbref.getVersion()); assertEquals("CDS|dna1", dbref.getAccessionId()); @@ -1112,33 +1131,37 @@ public class AlignmentUtilsTests /* * verify cDNA has added a dbref with mapping to CDS */ - assertEquals(3, dna1.getDBRefs().length); - DBRefEntry dbRefEntry = dna1.getDBRefs()[2]; + assertEquals(3, dna1.getDBRefs().size()); + DBRefEntry dbRefEntry = dna1.getDBRefs().get(2); assertSame(cds1Dss, dbRefEntry.getMap().getTo()); MapList dnaToCdsMapping = new MapList(new int[] { 4, 6, 10, 12 }, - new int[] { 1, 6 }, 1, 1); + new int[] + { 1, 6 }, 1, 1); assertEquals(dnaToCdsMapping, dbRefEntry.getMap().getMap()); - assertEquals(3, dna2.getDBRefs().length); - dbRefEntry = dna2.getDBRefs()[2]; + assertEquals(3, dna2.getDBRefs().size()); + dbRefEntry = dna2.getDBRefs().get(2); assertSame(cds2Dss, dbRefEntry.getMap().getTo()); dnaToCdsMapping = new MapList(new int[] { 1, 3, 7, 9, 13, 15 }, - new int[] { 1, 9 }, 1, 1); + new int[] + { 1, 9 }, 1, 1); assertEquals(dnaToCdsMapping, dbRefEntry.getMap().getMap()); /* * verify CDS has added a dbref with mapping to cDNA */ - assertEquals(2, cds1Dss.getDBRefs().length); - dbRefEntry = cds1Dss.getDBRefs()[1]; + assertEquals(2, cds1Dss.getDBRefs().size()); + dbRefEntry = cds1Dss.getDBRefs().get(1); assertSame(dna1.getDatasetSequence(), dbRefEntry.getMap().getTo()); - MapList cdsToDnaMapping = new MapList(new int[] { 1, 6 }, new int[] { - 4, 6, 10, 12 }, 1, 1); + MapList cdsToDnaMapping = new MapList(new int[] { 1, 6 }, + new int[] + { 4, 6, 10, 12 }, 1, 1); assertEquals(cdsToDnaMapping, dbRefEntry.getMap().getMap()); - assertEquals(2, cds2Dss.getDBRefs().length); - dbRefEntry = cds2Dss.getDBRefs()[1]; + assertEquals(2, cds2Dss.getDBRefs().size()); + dbRefEntry = cds2Dss.getDBRefs().get(1); assertSame(dna2.getDatasetSequence(), dbRefEntry.getMap().getTo()); - cdsToDnaMapping = new MapList(new int[] { 1, 9 }, new int[] { 1, 3, 7, - 9, 13, 15 }, 1, 1); + cdsToDnaMapping = new MapList(new int[] { 1, 9 }, + new int[] + { 1, 3, 7, 9, 13, 15 }, 1, 1); assertEquals(cdsToDnaMapping, dbRefEntry.getMap().getMap()); /* @@ -1240,12 +1263,12 @@ public class AlignmentUtilsTests pep1.createDatasetSequence(); pep2.createDatasetSequence(); pep3.createDatasetSequence(); - pep1.getDatasetSequence().addDBRef( - new DBRefEntry("EMBLCDS", "2", "A12345")); - pep2.getDatasetSequence().addDBRef( - new DBRefEntry("EMBLCDS", "3", "A12346")); - pep3.getDatasetSequence().addDBRef( - new DBRefEntry("EMBLCDS", "4", "A12347")); + pep1.getDatasetSequence() + .addDBRef(new DBRefEntry("EMBLCDS", "2", "A12345")); + pep2.getDatasetSequence() + .addDBRef(new DBRefEntry("EMBLCDS", "3", "A12346")); + pep3.getDatasetSequence() + .addDBRef(new DBRefEntry("EMBLCDS", "4", "A12347")); /* * Create the CDS alignment @@ -1258,7 +1281,8 @@ public class AlignmentUtilsTests */ // map ...GGG...TTT to GF MapList map = new MapList(new int[] { 4, 6, 10, 12 }, - new int[] { 1, 2 }, 3, 1); + new int[] + { 1, 2 }, 3, 1); AlignedCodonFrame acf = new AlignedCodonFrame(); acf.addMap(dna1.getDatasetSequence(), pep1.getDatasetSequence(), map); dna.addCodonFrame(acf); @@ -1278,8 +1302,9 @@ public class AlignmentUtilsTests /* * execute method under test */ - AlignmentI cdsal = AlignmentUtils.makeCdsAlignment( - new SequenceI[] { dna1 }, dna.getDataset(), null); + AlignmentI cdsal = AlignmentUtils + .makeCdsAlignment(new SequenceI[] + { dna1 }, dna.getDataset(), null); /* * Verify we have 3 cds sequences, mapped to pep1/2/3 respectively @@ -1351,8 +1376,8 @@ public class AlignmentUtilsTests .findMappingsForSequence(pep1, dnaMappings); assertEquals(1, mappings.size()); assertEquals(1, mappings.get(0).getMappings().size()); - assertSame(pep1.getDatasetSequence(), mappings.get(0).getMappings() - .get(0).getMapping().getTo()); + assertSame(pep1.getDatasetSequence(), + mappings.get(0).getMappings().get(0).getMapping().getTo()); /* * dna1 to cds1 @@ -1362,8 +1387,8 @@ public class AlignmentUtilsTests Mapping mapping = dnaToCds1Mappings.get(0).getMappings().get(0) .getMapping(); assertSame(cds.get(0).getDatasetSequence(), mapping.getTo()); - assertEquals("G(1) in CDS should map to G(4) in DNA", 4, mapping - .getMap().getToPosition(1)); + assertEquals("G(1) in CDS should map to G(4) in DNA", 4, + mapping.getMap().getToPosition(1)); /* * dna1 to pep2 @@ -1371,8 +1396,8 @@ public class AlignmentUtilsTests mappings = MappingUtils.findMappingsForSequence(pep2, dnaMappings); assertEquals(1, mappings.size()); assertEquals(1, mappings.get(0).getMappings().size()); - assertSame(pep2.getDatasetSequence(), mappings.get(0).getMappings() - .get(0).getMapping().getTo()); + assertSame(pep2.getDatasetSequence(), + mappings.get(0).getMappings().get(0).getMapping().getTo()); /* * dna1 to cds2 @@ -1381,8 +1406,8 @@ public class AlignmentUtilsTests .findMappingsForSequence(cds.get(1), dnaMappings); mapping = dnaToCds2Mappings.get(0).getMappings().get(0).getMapping(); assertSame(cds.get(1).getDatasetSequence(), mapping.getTo()); - assertEquals("c(4) in CDS should map to c(7) in DNA", 7, mapping - .getMap().getToPosition(4)); + assertEquals("c(4) in CDS should map to c(7) in DNA", 7, + mapping.getMap().getToPosition(4)); /* * dna1 to pep3 @@ -1390,8 +1415,8 @@ public class AlignmentUtilsTests mappings = MappingUtils.findMappingsForSequence(pep3, dnaMappings); assertEquals(1, mappings.size()); assertEquals(1, mappings.get(0).getMappings().size()); - assertSame(pep3.getDatasetSequence(), mappings.get(0).getMappings() - .get(0).getMapping().getTo()); + assertSame(pep3.getDatasetSequence(), + mappings.get(0).getMappings().get(0).getMapping().getTo()); /* * dna1 to cds3 @@ -1400,8 +1425,8 @@ public class AlignmentUtilsTests .findMappingsForSequence(cds.get(2), dnaMappings); mapping = dnaToCds3Mappings.get(0).getMappings().get(0).getMapping(); assertSame(cds.get(2).getDatasetSequence(), mapping.getTo()); - assertEquals("T(4) in CDS should map to T(10) in DNA", 10, mapping - .getMap().getToPosition(4)); + assertEquals("T(4) in CDS should map to T(10) in DNA", 10, + mapping.getMap().getToPosition(4)); } @Test(groups = { "Functional" }) @@ -1458,9 +1483,10 @@ public class AlignmentUtilsTests AlignedCodonFrame acf = new AlignedCodonFrame(); // this is like a domain or motif match of part of a peptide sequence - MapList map = new MapList(new int[] { 6, 12 }, new int[] { 1, 7 }, 1, 1); - acf.addMap(alignFrom.getDatasetSequence(), - alignMe.getDatasetSequence(), map); + MapList map = new MapList(new int[] { 6, 12 }, new int[] { 1, 7 }, 1, + 1); + acf.addMap(alignFrom.getDatasetSequence(), alignMe.getDatasetSequence(), + map); AlignmentUtils.alignSequenceAs(alignMe, alignFrom, acf, "-", '-', true, true); @@ -1491,35 +1517,36 @@ public class AlignmentUtilsTests SequenceI cds = new Sequence("cds/10-15", "TAGGCC"); // no overlap - dna.addSequenceFeature(new SequenceFeature("type1", "desc1", 1, 2, 1f, - null)); + dna.addSequenceFeature( + new SequenceFeature("type1", "desc1", 1, 2, 1f, null)); // partial overlap - to [1, 1] - dna.addSequenceFeature(new SequenceFeature("type2", "desc2", 3, 4, 2f, - null)); + dna.addSequenceFeature( + new SequenceFeature("type2", "desc2", 3, 4, 2f, null)); // exact overlap - to [1, 3] - dna.addSequenceFeature(new SequenceFeature("type3", "desc3", 4, 6, 3f, - null)); + dna.addSequenceFeature( + new SequenceFeature("type3", "desc3", 4, 6, 3f, null)); // spanning overlap - to [2, 5] - dna.addSequenceFeature(new SequenceFeature("type4", "desc4", 5, 11, 4f, - null)); + dna.addSequenceFeature( + new SequenceFeature("type4", "desc4", 5, 11, 4f, null)); // exactly overlaps whole mapped range [1, 6] - dna.addSequenceFeature(new SequenceFeature("type5", "desc5", 4, 12, 5f, - null)); + dna.addSequenceFeature( + new SequenceFeature("type5", "desc5", 4, 12, 5f, null)); // no overlap (internal) - dna.addSequenceFeature(new SequenceFeature("type6", "desc6", 7, 9, 6f, - null)); + dna.addSequenceFeature( + new SequenceFeature("type6", "desc6", 7, 9, 6f, null)); // no overlap (3' end) - dna.addSequenceFeature(new SequenceFeature("type7", "desc7", 13, 15, - 7f, null)); + dna.addSequenceFeature( + new SequenceFeature("type7", "desc7", 13, 15, 7f, null)); // overlap (3' end) - to [6, 6] - dna.addSequenceFeature(new SequenceFeature("type8", "desc8", 12, 12, - 8f, null)); + dna.addSequenceFeature( + new SequenceFeature("type8", "desc8", 12, 12, 8f, null)); // extended overlap - to [6, +] - dna.addSequenceFeature(new SequenceFeature("type9", "desc9", 12, 13, - 9f, null)); + dna.addSequenceFeature( + new SequenceFeature("type9", "desc9", 12, 13, 9f, null)); MapList map = new MapList(new int[] { 4, 6, 10, 12 }, - new int[] { 1, 6 }, 1, 1); + new int[] + { 1, 6 }, 1, 1); /* * transferFeatures() will build 'partial overlap' for regions @@ -1574,17 +1601,18 @@ public class AlignmentUtilsTests SequenceI cds = new Sequence("cds/10-15", "TAGGCC"); MapList map = new MapList(new int[] { 4, 6, 10, 12 }, - new int[] { 1, 6 }, 1, 1); + new int[] + { 1, 6 }, 1, 1); // [5, 11] maps to [2, 5] - dna.addSequenceFeature(new SequenceFeature("type4", "desc4", 5, 11, 4f, - null)); + dna.addSequenceFeature( + new SequenceFeature("type4", "desc4", 5, 11, 4f, null)); // [4, 12] maps to [1, 6] - dna.addSequenceFeature(new SequenceFeature("type5", "desc5", 4, 12, 5f, - null)); + dna.addSequenceFeature( + new SequenceFeature("type5", "desc5", 4, 12, 5f, null)); // [12, 12] maps to [6, 6] - dna.addSequenceFeature(new SequenceFeature("type8", "desc8", 12, 12, - 8f, null)); + dna.addSequenceFeature( + new SequenceFeature("type8", "desc8", 12, 12, 8f, null)); // desc4 and desc8 are the 'omit these' varargs AlignmentUtils.transferFeatures(dna, cds, map, null, "type4", "type8"); @@ -1607,17 +1635,18 @@ public class AlignmentUtilsTests SequenceI cds = new Sequence("cds/10-15", "TAGGCC"); MapList map = new MapList(new int[] { 4, 6, 10, 12 }, - new int[] { 1, 6 }, 1, 1); + new int[] + { 1, 6 }, 1, 1); // [5, 11] maps to [2, 5] - dna.addSequenceFeature(new SequenceFeature("type4", "desc4", 5, 11, 4f, - null)); + dna.addSequenceFeature( + new SequenceFeature("type4", "desc4", 5, 11, 4f, null)); // [4, 12] maps to [1, 6] - dna.addSequenceFeature(new SequenceFeature("type5", "desc5", 4, 12, 5f, - null)); + dna.addSequenceFeature( + new SequenceFeature("type5", "desc5", 4, 12, 5f, null)); // [12, 12] maps to [6, 6] - dna.addSequenceFeature(new SequenceFeature("type8", "desc8", 12, 12, - 8f, null)); + dna.addSequenceFeature( + new SequenceFeature("type8", "desc8", 12, 12, 8f, null)); // "type5" is the 'select this type' argument AlignmentUtils.transferFeatures(dna, cds, map, "type5"); @@ -1654,18 +1683,21 @@ public class AlignmentUtilsTests dna.setDataset(null); MapList map = new MapList(new int[] { 4, 12, 16, 18 }, - new int[] { 1, 4 }, 3, 1); + new int[] + { 1, 4 }, 3, 1); AlignedCodonFrame acf = new AlignedCodonFrame(); acf.addMap(dna1.getDatasetSequence(), pep1.getDatasetSequence(), map); dna.addCodonFrame(acf); map = new MapList(new int[] { 4, 8, 12, 12, 16, 18 }, - new int[] { 1, 3 }, 3, 1); + new int[] + { 1, 3 }, 3, 1); acf = new AlignedCodonFrame(); acf.addMap(dna2.getDatasetSequence(), pep2.getDatasetSequence(), map); dna.addCodonFrame(acf); - AlignmentI cds = AlignmentUtils.makeCdsAlignment(new SequenceI[] { - dna1, dna2, dna3 }, dna.getDataset(), null); + AlignmentI cds = AlignmentUtils + .makeCdsAlignment(new SequenceI[] + { dna1, dna2, dna3 }, dna.getDataset(), null); List cdsSeqs = cds.getSequences(); assertEquals(2, cdsSeqs.size()); assertEquals("GGGCCCTTTGGG", cdsSeqs.get(0).getSequenceAsString()); @@ -1705,7 +1737,8 @@ public class AlignmentUtilsTests pep1CdsMappings); assertEquals(1, sr.getResults().size()); SearchResultMatchI m = sr.getResults().get(0); - assertEquals(cds.getSequenceAt(0).getDatasetSequence(), m.getSequence()); + assertEquals(cds.getSequenceAt(0).getDatasetSequence(), + m.getSequence()); assertEquals(1, m.getStart()); assertEquals(3, m.getEnd()); sr = MappingUtils.buildSearchResults(pep1, 2, pep1CdsMappings); @@ -1734,7 +1767,8 @@ public class AlignmentUtilsTests sr = MappingUtils.buildSearchResults(pep2, 1, pep2CdsMappings); assertEquals(1, sr.getResults().size()); m = sr.getResults().get(0); - assertEquals(cds.getSequenceAt(1).getDatasetSequence(), m.getSequence()); + assertEquals(cds.getSequenceAt(1).getDatasetSequence(), + m.getSequence()); assertEquals(1, m.getStart()); assertEquals(3, m.getEnd()); sr = MappingUtils.buildSearchResults(pep2, 2, pep2CdsMappings); @@ -1766,12 +1800,14 @@ public class AlignmentUtilsTests SequenceI prot1 = new Sequence("Seq1", "XKFG"); // X for incomplete start SequenceI prot2 = new Sequence("Seq2", "NG"); SequenceI prot3 = new Sequence("Seq3", "XG"); // X for incomplete start - AlignmentI protein = new Alignment(new SequenceI[] { prot1, prot2, - prot3 }); + AlignmentI protein = new Alignment( + new SequenceI[] + { prot1, prot2, prot3 }); protein.setDataset(null); // map dna1 [3, 11] to prot1 [2, 4] KFG - MapList map = new MapList(new int[] { 3, 11 }, new int[] { 2, 4 }, 3, 1); + MapList map = new MapList(new int[] { 3, 11 }, new int[] { 2, 4 }, 3, + 1); AlignedCodonFrame acf = new AlignedCodonFrame(); acf.addMap(dna1.getDatasetSequence(), prot1.getDatasetSequence(), map); @@ -1783,7 +1819,7 @@ public class AlignmentUtilsTests map = new MapList(new int[] { 9, 11 }, new int[] { 2, 2 }, 3, 1); acf.addMap(dna3.getDatasetSequence(), prot3.getDatasetSequence(), map); - ArrayList acfs = new ArrayList(); + ArrayList acfs = new ArrayList<>(); acfs.add(acf); protein.setCodonFrames(acfs); @@ -1869,330 +1905,6 @@ public class AlignmentUtilsTests } /** - * Test the method that computes a map of codon variants for each protein - * position from "sequence_variant" features on dna - */ - @Test(groups = "Functional") - public void testBuildDnaVariantsMap() - { - SequenceI dna = new Sequence("dna", "atgAAATTTGGGCCCtag"); - MapList map = new MapList(new int[] { 1, 18 }, new int[] { 1, 5 }, 3, 1); - - /* - * first with no variants on dna - */ - LinkedHashMap[]> variantsMap = AlignmentUtils - .buildDnaVariantsMap(dna, map); - assertTrue(variantsMap.isEmpty()); - - /* - * single allele codon 1, on base 1 - */ - SequenceFeature sf1 = new SequenceFeature("sequence_variant", "", 1, 1, - 0f, null); - sf1.setValue("alleles", "T"); - sf1.setValue("ID", "sequence_variant:rs758803211"); - dna.addSequenceFeature(sf1); - - /* - * two alleles codon 2, on bases 2 and 3 (distinct variants) - */ - SequenceFeature sf2 = new SequenceFeature("sequence_variant", "", 5, 5, - 0f, null); - sf2.setValue("alleles", "T"); - sf2.setValue("ID", "sequence_variant:rs758803212"); - dna.addSequenceFeature(sf2); - SequenceFeature sf3 = new SequenceFeature("sequence_variant", "", 6, 6, - 0f, null); - sf3.setValue("alleles", "G"); - sf3.setValue("ID", "sequence_variant:rs758803213"); - dna.addSequenceFeature(sf3); - - /* - * two alleles codon 3, both on base 2 (one variant) - */ - SequenceFeature sf4 = new SequenceFeature("sequence_variant", "", 8, 8, - 0f, null); - sf4.setValue("alleles", "C, G"); - sf4.setValue("ID", "sequence_variant:rs758803214"); - dna.addSequenceFeature(sf4); - - // no alleles on codon 4 - - /* - * alleles on codon 5 on all 3 bases (distinct variants) - */ - SequenceFeature sf5 = new SequenceFeature("sequence_variant", "", 13, - 13, 0f, null); - sf5.setValue("alleles", "C, G"); // (C duplicates given base value) - sf5.setValue("ID", "sequence_variant:rs758803215"); - dna.addSequenceFeature(sf5); - SequenceFeature sf6 = new SequenceFeature("sequence_variant", "", 14, - 14, 0f, null); - sf6.setValue("alleles", "g, a"); // should force to upper-case - sf6.setValue("ID", "sequence_variant:rs758803216"); - dna.addSequenceFeature(sf6); - SequenceFeature sf7 = new SequenceFeature("sequence_variant", "", 15, - 15, 0f, null); - sf7.setValue("alleles", "A, T"); - sf7.setValue("ID", "sequence_variant:rs758803217"); - dna.addSequenceFeature(sf7); - - /* - * build map - expect variants on positions 1, 2, 3, 5 - */ - variantsMap = AlignmentUtils.buildDnaVariantsMap(dna, map); - assertEquals(4, variantsMap.size()); - - /* - * protein residue 1: variant on codon (ATG) base 1, not on 2 or 3 - */ - List[] pep1Variants = variantsMap.get(1); - assertEquals(3, pep1Variants.length); - assertEquals(1, pep1Variants[0].size()); - assertEquals("A", pep1Variants[0].get(0).base); // codon[1] base - assertSame(sf1, pep1Variants[0].get(0).variant); // codon[1] variant - assertEquals(1, pep1Variants[1].size()); - assertEquals("T", pep1Variants[1].get(0).base); // codon[2] base - assertNull(pep1Variants[1].get(0).variant); // no variant here - assertEquals(1, pep1Variants[2].size()); - assertEquals("G", pep1Variants[2].get(0).base); // codon[3] base - assertNull(pep1Variants[2].get(0).variant); // no variant here - - /* - * protein residue 2: variants on codon (AAA) bases 2 and 3 - */ - List[] pep2Variants = variantsMap.get(2); - assertEquals(3, pep2Variants.length); - assertEquals(1, pep2Variants[0].size()); - // codon[1] base recorded while processing variant on codon[2] - assertEquals("A", pep2Variants[0].get(0).base); - assertNull(pep2Variants[0].get(0).variant); // no variant here - // codon[2] base and variant: - assertEquals(1, pep2Variants[1].size()); - assertEquals("A", pep2Variants[1].get(0).base); - assertSame(sf2, pep2Variants[1].get(0).variant); - // codon[3] base was recorded when processing codon[2] variant - // and then the variant for codon[3] added to it - assertEquals(1, pep2Variants[2].size()); - assertEquals("A", pep2Variants[2].get(0).base); - assertSame(sf3, pep2Variants[2].get(0).variant); - - /* - * protein residue 3: variants on codon (TTT) base 2 only - */ - List[] pep3Variants = variantsMap.get(3); - assertEquals(3, pep3Variants.length); - assertEquals(1, pep3Variants[0].size()); - assertEquals("T", pep3Variants[0].get(0).base); // codon[1] base - assertNull(pep3Variants[0].get(0).variant); // no variant here - assertEquals(1, pep3Variants[1].size()); - assertEquals("T", pep3Variants[1].get(0).base); // codon[2] base - assertSame(sf4, pep3Variants[1].get(0).variant); // codon[2] variant - assertEquals(1, pep3Variants[2].size()); - assertEquals("T", pep3Variants[2].get(0).base); // codon[3] base - assertNull(pep3Variants[2].get(0).variant); // no variant here - - /* - * three variants on protein position 5 - */ - List[] pep5Variants = variantsMap.get(5); - assertEquals(3, pep5Variants.length); - assertEquals(1, pep5Variants[0].size()); - assertEquals("C", pep5Variants[0].get(0).base); // codon[1] base - assertSame(sf5, pep5Variants[0].get(0).variant); // codon[1] variant - assertEquals(1, pep5Variants[1].size()); - assertEquals("C", pep5Variants[1].get(0).base); // codon[2] base - assertSame(sf6, pep5Variants[1].get(0).variant); // codon[2] variant - assertEquals(1, pep5Variants[2].size()); - assertEquals("C", pep5Variants[2].get(0).base); // codon[3] base - assertSame(sf7, pep5Variants[2].get(0).variant); // codon[3] variant - } - - /** - * Tests for the method that computes all peptide variants given codon - * variants - */ - @Test(groups = "Functional") - public void testComputePeptideVariants() - { - /* - * scenario: AAATTTCCC codes for KFP - * variants: - * GAA -> E source: Ensembl - * CAA -> Q source: dbSNP - * AAG synonymous source: COSMIC - * AAT -> N source: Ensembl - * ...TTC synonymous source: dbSNP - * ......CAC,CGC -> H,R source: COSMIC - * (one variant with two alleles) - */ - SequenceI peptide = new Sequence("pep/10-12", "KFP"); - - /* - * two distinct variants for codon 1 position 1 - * second one has clinical significance - */ - String ensembl = "Ensembl"; - String dbSnp = "dbSNP"; - String cosmic = "COSMIC"; - SequenceFeature sf1 = new SequenceFeature("sequence_variant", "", 1, 1, - 0f, ensembl); - sf1.setValue("alleles", "A,G"); // GAA -> E - sf1.setValue("ID", "var1.125A>G"); - SequenceFeature sf2 = new SequenceFeature("sequence_variant", "", 1, 1, - 0f, dbSnp); - sf2.setValue("alleles", "A,C"); // CAA -> Q - sf2.setValue("ID", "var2"); - sf2.setValue("clinical_significance", "Dodgy"); - SequenceFeature sf3 = new SequenceFeature("sequence_variant", "", 3, 3, - 0f, cosmic); - sf3.setValue("alleles", "A,G"); // synonymous - sf3.setValue("ID", "var3"); - sf3.setValue("clinical_significance", "None"); - SequenceFeature sf4 = new SequenceFeature("sequence_variant", "", 3, 3, - 0f, ensembl); - sf4.setValue("alleles", "A,T"); // AAT -> N - sf4.setValue("ID", "sequence_variant:var4"); // prefix gets stripped off - sf4.setValue("clinical_significance", "Benign"); - SequenceFeature sf5 = new SequenceFeature("sequence_variant", "", 6, 6, - 0f, dbSnp); - sf5.setValue("alleles", "T,C"); // synonymous - sf5.setValue("ID", "var5"); - sf5.setValue("clinical_significance", "Bad"); - SequenceFeature sf6 = new SequenceFeature("sequence_variant", "", 8, 8, - 0f, cosmic); - sf6.setValue("alleles", "C,A,G"); // CAC,CGC -> H,R - sf6.setValue("ID", "var6"); - sf6.setValue("clinical_significance", "Good"); - - List codon1Variants = new ArrayList(); - List codon2Variants = new ArrayList(); - List codon3Variants = new ArrayList(); - List codonVariants[] = new ArrayList[3]; - codonVariants[0] = codon1Variants; - codonVariants[1] = codon2Variants; - codonVariants[2] = codon3Variants; - - /* - * compute variants for protein position 1 - */ - codon1Variants.add(new DnaVariant("A", sf1)); - codon1Variants.add(new DnaVariant("A", sf2)); - codon2Variants.add(new DnaVariant("A")); - codon2Variants.add(new DnaVariant("A")); - codon3Variants.add(new DnaVariant("A", sf3)); - codon3Variants.add(new DnaVariant("A", sf4)); - AlignmentUtils.computePeptideVariants(peptide, 1, codonVariants); - - /* - * compute variants for protein position 2 - */ - codon1Variants.clear(); - codon2Variants.clear(); - codon3Variants.clear(); - codon1Variants.add(new DnaVariant("T")); - codon2Variants.add(new DnaVariant("T")); - codon3Variants.add(new DnaVariant("T", sf5)); - AlignmentUtils.computePeptideVariants(peptide, 2, codonVariants); - - /* - * compute variants for protein position 3 - */ - codon1Variants.clear(); - codon2Variants.clear(); - codon3Variants.clear(); - codon1Variants.add(new DnaVariant("C")); - codon2Variants.add(new DnaVariant("C", sf6)); - codon3Variants.add(new DnaVariant("C")); - AlignmentUtils.computePeptideVariants(peptide, 3, codonVariants); - - /* - * verify added sequence features for - * var1 K -> E Ensembl - * var2 K -> Q dbSNP - * var4 K -> N Ensembl - * var6 P -> H COSMIC - * var6 P -> R COSMIC - */ - List sfs = peptide.getSequenceFeatures(); - SequenceFeatures.sortFeatures(sfs, true); - assertEquals(5, sfs.size()); - - /* - * features are sorted by start position ascending, but in no - * particular order where start positions match; asserts here - * simply match the data returned (the order is not important) - */ - SequenceFeature sf = sfs.get(0); - assertEquals(1, sf.getBegin()); - assertEquals(1, sf.getEnd()); - assertEquals("p.Lys1Asn", sf.getDescription()); - assertEquals("var4", sf.getValue("ID")); - assertEquals("Benign", sf.getValue("clinical_significance")); - assertEquals("ID=var4;clinical_significance=Benign", sf.getAttributes()); - assertEquals(1, sf.links.size()); - assertEquals( - "p.Lys1Asn var4|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var4", - sf.links.get(0)); - assertEquals(ensembl, sf.getFeatureGroup()); - - sf = sfs.get(1); - assertEquals(1, sf.getBegin()); - assertEquals(1, sf.getEnd()); - assertEquals("p.Lys1Gln", sf.getDescription()); - assertEquals("var2", sf.getValue("ID")); - assertEquals("Dodgy", sf.getValue("clinical_significance")); - assertEquals("ID=var2;clinical_significance=Dodgy", sf.getAttributes()); - assertEquals(1, sf.links.size()); - assertEquals( - "p.Lys1Gln var2|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var2", - sf.links.get(0)); - assertEquals(dbSnp, sf.getFeatureGroup()); - - sf = sfs.get(2); - assertEquals(1, sf.getBegin()); - assertEquals(1, sf.getEnd()); - assertEquals("p.Lys1Glu", sf.getDescription()); - assertEquals("var1.125A>G", sf.getValue("ID")); - assertNull(sf.getValue("clinical_significance")); - assertEquals("ID=var1.125A>G", sf.getAttributes()); - assertEquals(1, sf.links.size()); - // link to variation is urlencoded - assertEquals( - "p.Lys1Glu var1.125A>G|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var1.125A%3EG", - sf.links.get(0)); - assertEquals(ensembl, sf.getFeatureGroup()); - - sf = sfs.get(3); - assertEquals(3, sf.getBegin()); - assertEquals(3, sf.getEnd()); - assertEquals("p.Pro3Arg", sf.getDescription()); - assertEquals("var6", sf.getValue("ID")); - assertEquals("Good", sf.getValue("clinical_significance")); - assertEquals("ID=var6;clinical_significance=Good", sf.getAttributes()); - assertEquals(1, sf.links.size()); - assertEquals( - "p.Pro3Arg var6|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var6", - sf.links.get(0)); - assertEquals(cosmic, sf.getFeatureGroup()); - - // var5 generates two distinct protein variant features - sf = sfs.get(4); - assertEquals(3, sf.getBegin()); - assertEquals(3, sf.getEnd()); - assertEquals("p.Pro3His", sf.getDescription()); - assertEquals("var6", sf.getValue("ID")); - assertEquals("Good", sf.getValue("clinical_significance")); - assertEquals("ID=var6;clinical_significance=Good", sf.getAttributes()); - assertEquals(1, sf.links.size()); - assertEquals( - "p.Pro3His var6|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var6", - sf.links.get(0)); - assertEquals(cosmic, sf.getFeatureGroup()); - } - - /** * Tests for the method that maps the subset of a dna sequence that has CDS * (or subtype) feature, with CDS strand = '-' (reverse) */ @@ -2296,7 +2008,8 @@ public class AlignmentUtilsTests dna.addCodonFrame(acf); AlignmentUtils.alignAs(cds, dna); assertEquals("---GGGTTT", cds.getSequenceAt(0).getSequenceAsString()); - assertEquals("CCC------AAA", cds.getSequenceAt(1).getSequenceAsString()); + assertEquals("CCC------AAA", + cds.getSequenceAt(1).getSequenceAsString()); } @Test(groups = { "Functional" }) @@ -2306,9 +2019,10 @@ public class AlignmentUtilsTests SequenceI seq1 = new Sequence("cds", "AAATTT"); from.createDatasetSequence(); seq1.createDatasetSequence(); - Mapping mapping = new Mapping(seq1, new MapList( - new int[] { 3, 6, 9, 10 }, new int[] { 1, 6 }, 1, 1)); - Map> map = new TreeMap>(); + Mapping mapping = new Mapping(seq1, + new MapList(new int[] + { 3, 6, 9, 10 }, new int[] { 1, 6 }, 1, 1)); + Map> map = new TreeMap<>(); AlignmentUtils.addMappedPositions(seq1, from, mapping, map); /* @@ -2338,9 +2052,10 @@ public class AlignmentUtilsTests SequenceI seq1 = new Sequence("cds", "AAATTT"); from.createDatasetSequence(); seq1.createDatasetSequence(); - Mapping mapping = new Mapping(seq1, new MapList( - new int[] { 3, 6, 9, 10 }, new int[] { 1, 6 }, 1, 1)); - Map> map = new TreeMap>(); + Mapping mapping = new Mapping(seq1, + new MapList(new int[] + { 3, 6, 9, 10 }, new int[] { 1, 6 }, 1, 1)); + Map> map = new TreeMap<>(); AlignmentUtils.addMappedPositions(seq1, from, mapping, map); /* @@ -2383,7 +2098,8 @@ public class AlignmentUtilsTests AlignedCodonFrame acf = new AlignedCodonFrame(); MapList map = new MapList(new int[] { 4, 6, 10, 12 }, - new int[] { 1, 2 }, 3, 1); + new int[] + { 1, 2 }, 3, 1); acf.addMap(dna1.getDatasetSequence(), pep1.getDatasetSequence(), map); acf.addMap(dna1.getDatasetSequence(), pep3.getDatasetSequence(), map); dna.addCodonFrame(acf); @@ -2398,8 +2114,10 @@ public class AlignmentUtilsTests /* * execute method under test to find CDS for EMBL peptides only */ - AlignmentI cds = AlignmentUtils.makeCdsAlignment(new SequenceI[] { - dna1, dna2 }, dna.getDataset(), emblPeptides.getSequencesArray()); + AlignmentI cds = AlignmentUtils + .makeCdsAlignment(new SequenceI[] + { dna1, dna2 }, dna.getDataset(), + emblPeptides.getSequencesArray()); assertEquals(2, cds.getSequences().size()); assertEquals("GGGTTT", cds.getSequenceAt(0).getSequenceAsString()); @@ -2512,9 +2230,14 @@ public class AlignmentUtilsTests AlignmentI al2 = new Alignment(new SequenceI[] { dna3, dna4 }); ((Alignment) al2).createDatasetAlignment(); + /* + * alignment removes gapped columns (two internal, two trailing) + */ assertTrue(AlignmentUtils.alignAsSameSequences(al1, al2)); - assertEquals(seq1, al1.getSequenceAt(0).getSequenceAsString()); - assertEquals(seq2, al1.getSequenceAt(1).getSequenceAsString()); + String aligned1 = "-cc-GG-GTTT-aaa"; + assertEquals(aligned1, al1.getSequenceAt(0).getSequenceAsString()); + String aligned2 = "C--C-Cgg-gtttAAA"; + assertEquals(aligned2, al1.getSequenceAt(1).getSequenceAsString()); /* * add another sequence to 'aligned' - should still succeed, since @@ -2524,8 +2247,8 @@ public class AlignmentUtilsTests dna5.createDatasetSequence(); al2.addSequence(dna5); assertTrue(AlignmentUtils.alignAsSameSequences(al1, al2)); - assertEquals(seq1, al1.getSequenceAt(0).getSequenceAsString()); - assertEquals(seq2, al1.getSequenceAt(1).getSequenceAsString()); + assertEquals(aligned1, al1.getSequenceAt(0).getSequenceAsString()); + assertEquals(aligned2, al1.getSequenceAt(1).getSequenceAsString()); /* * add another sequence to 'unaligned' - should fail, since now not @@ -2543,15 +2266,15 @@ public class AlignmentUtilsTests { SequenceI dna1 = new Sequence("dna1", "cccGGGTTTaaa"); SequenceI dna2 = new Sequence("dna2", "CCCgggtttAAA"); - SequenceI as1 = dna1.deriveSequence(); - SequenceI as2 = dna1.deriveSequence().getSubSequence(3, 7); - SequenceI as3 = dna2.deriveSequence(); + SequenceI as1 = dna1.deriveSequence(); // cccGGGTTTaaa/1-12 + SequenceI as2 = dna1.deriveSequence().getSubSequence(3, 7); // GGGT/4-7 + SequenceI as3 = dna2.deriveSequence(); // CCCgggtttAAA/1-12 as1.insertCharAt(6, 5, '-'); - String s_as1 = as1.getSequenceAsString(); + assertEquals("cccGGG-----TTTaaa", as1.getSequenceAsString()); as2.insertCharAt(6, 5, '-'); - String s_as2 = as2.getSequenceAsString(); - as3.insertCharAt(6, 5, '-'); - String s_as3 = as3.getSequenceAsString(); + assertEquals("GGGT-----", as2.getSequenceAsString()); + as3.insertCharAt(3, 5, '-'); + assertEquals("CCC-----gggtttAAA", as3.getSequenceAsString()); AlignmentI aligned = new Alignment(new SequenceI[] { as1, as2, as3 }); // why do we need to cast this still ? @@ -2559,14 +2282,18 @@ public class AlignmentUtilsTests SequenceI uas1 = dna1.deriveSequence(); SequenceI uas2 = dna1.deriveSequence().getSubSequence(3, 7); SequenceI uas3 = dna2.deriveSequence(); - AlignmentI tobealigned = new Alignment(new SequenceI[] { uas1, uas2, - uas3 }); + AlignmentI tobealigned = new Alignment( + new SequenceI[] + { uas1, uas2, uas3 }); ((Alignment) tobealigned).createDatasetAlignment(); + /* + * alignAs lines up dataset sequences and removes empty columns (two) + */ assertTrue(AlignmentUtils.alignAsSameSequences(tobealigned, aligned)); - assertEquals(s_as1, uas1.getSequenceAsString()); - assertEquals(s_as2, uas2.getSequenceAsString()); - assertEquals(s_as3, uas3.getSequenceAsString()); + assertEquals("cccGGG---TTTaaa", uas1.getSequenceAsString()); + assertEquals("GGGT", uas2.getSequenceAsString()); + assertEquals("CCC---gggtttAAA", uas3.getSequenceAsString()); } @Test(groups = { "Functional" }) @@ -2605,19 +2332,19 @@ public class AlignmentUtilsTests * transcript 'CDS' is 10-16, 17-21 * which is 'gene' 158-164, 210-214 */ - MapList toMap = toLoci.getMap(); + MapList toMap = toLoci.getMapping(); assertEquals(1, toMap.getFromRanges().size()); assertEquals(2, toMap.getFromRanges().get(0).length); assertEquals(1, toMap.getFromRanges().get(0)[0]); assertEquals(12, toMap.getFromRanges().get(0)[1]); - assertEquals(1, toMap.getToRanges().size()); - assertEquals(4, toMap.getToRanges().get(0).length); + assertEquals(2, toMap.getToRanges().size()); + assertEquals(2, toMap.getToRanges().get(0).length); assertEquals(158, toMap.getToRanges().get(0)[0]); assertEquals(164, toMap.getToRanges().get(0)[1]); - assertEquals(210, toMap.getToRanges().get(0)[2]); - assertEquals(214, toMap.getToRanges().get(0)[3]); + assertEquals(210, toMap.getToRanges().get(1)[0]); + assertEquals(214, toMap.getToRanges().get(1)[1]); // or summarised as (but toString might change in future): - assertEquals("[ [1, 12] ] 1:1 to [ [158, 164, 210, 214] ]", + assertEquals("[ [1, 12] ] 1:1 to [ [158, 164] [210, 214] ]", toMap.toString()); /* @@ -2628,8 +2355,8 @@ public class AlignmentUtilsTests AlignmentUtils.transferGeneLoci(from, map, to); assertEquals("GRCh38", toLoci.getAssemblyId()); assertEquals("7", toLoci.getChromosomeId()); - toMap = toLoci.getMap(); - assertEquals("[ [1, 12] ] 1:1 to [ [158, 164, 210, 214] ]", + toMap = toLoci.getMapping(); + assertEquals("[ [1, 12] ] 1:1 to [ [158, 164] [210, 214] ]", toMap.toString()); } @@ -2661,7 +2388,7 @@ public class AlignmentUtilsTests * Case 2: CDS 3 times length of peptide + stop codon * (note code does not currently check trailing codon is a stop codon) */ - dna = new Sequence("dna", "AACGacgtCTCCTTGA"); + dna = new Sequence("dna", "AACGacgtCTCCTCCC"); dna.createDatasetSequence(); dna.addSequenceFeature(new SequenceFeature("CDS", "", 1, 4, null)); dna.addSequenceFeature(new SequenceFeature("CDS", "", 9, 16, null)); @@ -2674,17 +2401,42 @@ public class AlignmentUtilsTests Arrays.deepToString(ml.getFromRanges().toArray())); /* - * Case 3: CDS not 3 times length of peptide - no mapping is made + * Case 3: CDS longer than 3 * peptide + stop codon - no mapping is made + */ + dna = new Sequence("dna", "AACGacgtCTCCTTGATCA"); + dna.createDatasetSequence(); + dna.addSequenceFeature(new SequenceFeature("CDS", "", 1, 4, null)); + dna.addSequenceFeature(new SequenceFeature("CDS", "", 9, 19, null)); + ml = AlignmentUtils.mapCdsToProtein(dna, peptide); + assertNull(ml); + + /* + * Case 4: CDS shorter than 3 * peptide - no mapping is made + */ + dna = new Sequence("dna", "AACGacgtCTCC"); + dna.createDatasetSequence(); + dna.addSequenceFeature(new SequenceFeature("CDS", "", 1, 4, null)); + dna.addSequenceFeature(new SequenceFeature("CDS", "", 9, 12, null)); + ml = AlignmentUtils.mapCdsToProtein(dna, peptide); + assertNull(ml); + + /* + * Case 5: CDS 3 times length of peptide + part codon - mapping is truncated */ dna = new Sequence("dna", "AACGacgtCTCCTTG"); dna.createDatasetSequence(); dna.addSequenceFeature(new SequenceFeature("CDS", "", 1, 4, null)); dna.addSequenceFeature(new SequenceFeature("CDS", "", 9, 15, null)); ml = AlignmentUtils.mapCdsToProtein(dna, peptide); - assertNull(ml); + assertEquals(3, ml.getFromRatio()); + assertEquals(1, ml.getToRatio()); + assertEquals("[[1, 3]]", + Arrays.deepToString(ml.getToRanges().toArray())); + assertEquals("[[1, 4], [9, 13]]", + Arrays.deepToString(ml.getFromRanges().toArray())); /* - * Case 4: incomplete start codon corresponding to X in peptide + * Case 6: incomplete start codon corresponding to X in peptide */ dna = new Sequence("dna", "ACGacgtCTCCTTGG"); dna.createDatasetSequence(); @@ -2699,4 +2451,153 @@ public class AlignmentUtilsTests assertEquals("[[3, 3], [8, 12]]", Arrays.deepToString(ml.getFromRanges().toArray())); } + + /** + * Tests for the method that locates the CDS sequence that has a mapping to + * the given protein. That is, given a transcript-to-peptide mapping, find the + * cds-to-peptide mapping that relates to both, and return the CDS sequence. + */ + @Test + public void testFindCdsForProtein() + { + List mappings = new ArrayList<>(); + AlignedCodonFrame acf1 = new AlignedCodonFrame(); + mappings.add(acf1); + + SequenceI dna1 = new Sequence("dna1", "cgatATcgGCTATCTATGacg"); + dna1.createDatasetSequence(); + + // NB we currently exclude STOP codon from CDS sequences + // the test would need to change if this changes in future + SequenceI cds1 = new Sequence("cds1", "ATGCTATCT"); + cds1.createDatasetSequence(); + + SequenceI pep1 = new Sequence("pep1", "MLS"); + pep1.createDatasetSequence(); + List seqMappings = new ArrayList<>(); + MapList mapList = new MapList(new int[] { 5, 6, 9, 15 }, + new int[] + { 1, 3 }, 3, 1); + Mapping dnaToPeptide = new Mapping(pep1.getDatasetSequence(), mapList); + + // add dna to peptide mapping + seqMappings.add(acf1); + acf1.addMap(dna1.getDatasetSequence(), pep1.getDatasetSequence(), + mapList); + + /* + * first case - no dna-to-CDS mapping exists - search fails + */ + SequenceI seq = AlignmentUtils.findCdsForProtein(mappings, dna1, + seqMappings, dnaToPeptide); + assertNull(seq); + + /* + * second case - CDS-to-peptide mapping exists but no dna-to-CDS + * - search fails + */ + // todo this test fails if the mapping is added to acf1, not acf2 + // need to tidy up use of lists of mappings in AlignedCodonFrame + AlignedCodonFrame acf2 = new AlignedCodonFrame(); + mappings.add(acf2); + MapList cdsToPeptideMapping = new MapList(new int[] { 1, 9 }, + new int[] + { 1, 3 }, 3, 1); + acf2.addMap(cds1.getDatasetSequence(), pep1.getDatasetSequence(), + cdsToPeptideMapping); + assertNull(AlignmentUtils.findCdsForProtein(mappings, dna1, seqMappings, + dnaToPeptide)); + + /* + * third case - add dna-to-CDS mapping - CDS is now found! + */ + MapList dnaToCdsMapping = new MapList(new int[] { 5, 6, 9, 15 }, + new int[] + { 1, 9 }, 1, 1); + acf1.addMap(dna1.getDatasetSequence(), cds1.getDatasetSequence(), + dnaToCdsMapping); + seq = AlignmentUtils.findCdsForProtein(mappings, dna1, seqMappings, + dnaToPeptide); + assertSame(seq, cds1.getDatasetSequence()); + } + + /** + * Tests for the method that locates the CDS sequence that has a mapping to + * the given protein. That is, given a transcript-to-peptide mapping, find the + * cds-to-peptide mapping that relates to both, and return the CDS sequence. + * This test is for the case where transcript and CDS are the same length. + */ + @Test + public void testFindCdsForProtein_noUTR() + { + List mappings = new ArrayList<>(); + AlignedCodonFrame acf1 = new AlignedCodonFrame(); + mappings.add(acf1); + + SequenceI dna1 = new Sequence("dna1", "ATGCTATCTTAA"); + dna1.createDatasetSequence(); + + // NB we currently exclude STOP codon from CDS sequences + // the test would need to change if this changes in future + SequenceI cds1 = new Sequence("cds1", "ATGCTATCT"); + cds1.createDatasetSequence(); + + SequenceI pep1 = new Sequence("pep1", "MLS"); + pep1.createDatasetSequence(); + List seqMappings = new ArrayList<>(); + MapList mapList = new MapList(new int[] { 1, 9 }, new int[] { 1, 3 }, 3, + 1); + Mapping dnaToPeptide = new Mapping(pep1.getDatasetSequence(), mapList); + + // add dna to peptide mapping + seqMappings.add(acf1); + acf1.addMap(dna1.getDatasetSequence(), pep1.getDatasetSequence(), + mapList); + + /* + * first case - transcript lacks CDS features - it appears to be + * the CDS sequence and is returned + */ + SequenceI seq = AlignmentUtils.findCdsForProtein(mappings, dna1, + seqMappings, dnaToPeptide); + assertSame(seq, dna1.getDatasetSequence()); + + /* + * second case - transcript has CDS feature - this means it is + * not returned as a match for CDS (CDS sequences don't have CDS features) + */ + dna1.addSequenceFeature( + new SequenceFeature(SequenceOntologyI.CDS, "cds", 1, 12, null)); + seq = AlignmentUtils.findCdsForProtein(mappings, dna1, seqMappings, + dnaToPeptide); + assertNull(seq); + + /* + * third case - CDS-to-peptide mapping exists but no dna-to-CDS + * - search fails + */ + // todo this test fails if the mapping is added to acf1, not acf2 + // need to tidy up use of lists of mappings in AlignedCodonFrame + AlignedCodonFrame acf2 = new AlignedCodonFrame(); + mappings.add(acf2); + MapList cdsToPeptideMapping = new MapList(new int[] { 1, 9 }, + new int[] + { 1, 3 }, 3, 1); + acf2.addMap(cds1.getDatasetSequence(), pep1.getDatasetSequence(), + cdsToPeptideMapping); + assertNull(AlignmentUtils.findCdsForProtein(mappings, dna1, seqMappings, + dnaToPeptide)); + + /* + * fourth case - add dna-to-CDS mapping - CDS is now found! + */ + MapList dnaToCdsMapping = new MapList(new int[] { 1, 9 }, + new int[] + { 1, 9 }, 1, 1); + acf1.addMap(dna1.getDatasetSequence(), cds1.getDatasetSequence(), + dnaToCdsMapping); + seq = AlignmentUtils.findCdsForProtein(mappings, dna1, seqMappings, + dnaToPeptide); + assertSame(seq, cds1.getDatasetSequence()); + } }