X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=test%2Fjalview%2Fanalysis%2FAlignmentUtilsTests.java;h=e231e7f6e40bbad24472830efbfa81a6bd5a7baf;hb=57738a1f3c19b1c3a00bd3ac5108f8cd0af32f99;hp=9eec241dd4f25614c99b77ec3760c534b1e62f0e;hpb=0b573ed90b14079f7326281f50c0c9cffdace586;p=jalview.git diff --git a/test/jalview/analysis/AlignmentUtilsTests.java b/test/jalview/analysis/AlignmentUtilsTests.java index 9eec241..e231e7f 100644 --- a/test/jalview/analysis/AlignmentUtilsTests.java +++ b/test/jalview/analysis/AlignmentUtilsTests.java @@ -85,15 +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) { /* @@ -103,11 +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) @@ -177,8 +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, @@ -249,8 +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; } @@ -299,11 +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 @@ -376,7 +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 @@ -387,14 +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. @@ -405,14 +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-"); } /** @@ -424,8 +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------ @@ -456,8 +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); @@ -474,7 +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"); @@ -500,11 +503,13 @@ 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); @@ -573,28 +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())); } /** @@ -644,11 +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 @@ -661,11 +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 @@ -678,11 +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 @@ -786,8 +797,8 @@ public class AlignmentUtilsTests 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) @@ -838,11 +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 @@ -975,7 +989,7 @@ public class AlignmentUtilsTests assertTrue(AlignmentUtils.haveCrossRef(seq2, seq1)); // now the other way round - seq1.setDBRefs(null); + seq1.setDBRefs(null); seq2.addDBRef(new DBRefEntry("EMBL", "1", "A12345")); assertTrue(AlignmentUtils.haveCrossRef(seq1, seq2)); assertTrue(AlignmentUtils.haveCrossRef(seq2, seq1)); @@ -1014,8 +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 @@ -1032,14 +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); @@ -1062,8 +1078,9 @@ public class AlignmentUtilsTests /* * 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 @@ -1093,8 +1110,8 @@ public class AlignmentUtilsTests 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()); /* @@ -1118,13 +1135,15 @@ public class AlignmentUtilsTests 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().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()); /* @@ -1133,14 +1152,16 @@ public class AlignmentUtilsTests 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().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()); /* @@ -1242,12 +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 @@ -1260,7 +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); @@ -1280,8 +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 @@ -1353,8 +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 @@ -1364,8 +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 @@ -1373,8 +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 @@ -1383,8 +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 @@ -1392,8 +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 @@ -1402,8 +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" }) @@ -1460,9 +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); @@ -1493,35 +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 @@ -1576,17 +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"); @@ -1609,17 +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"); @@ -1656,18 +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()); @@ -1707,7 +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); @@ -1736,7 +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); @@ -1768,12 +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); @@ -1974,7 +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" }) @@ -1984,8 +2019,9 @@ 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)); + 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); @@ -2016,8 +2052,9 @@ 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)); + 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); @@ -2061,7 +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); @@ -2076,8 +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()); @@ -2195,11 +2235,9 @@ public class AlignmentUtilsTests */ assertTrue(AlignmentUtils.alignAsSameSequences(al1, al2)); String aligned1 = "-cc-GG-GTTT-aaa"; - assertEquals(aligned1, - al1.getSequenceAt(0).getSequenceAsString()); + assertEquals(aligned1, al1.getSequenceAt(0).getSequenceAsString()); String aligned2 = "C--C-Cgg-gtttAAA"; - assertEquals(aligned2, - al1.getSequenceAt(1).getSequenceAsString()); + assertEquals(aligned2, al1.getSequenceAt(1).getSequenceAsString()); /* * add another sequence to 'aligned' - should still succeed, since @@ -2244,8 +2282,9 @@ 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(); /* @@ -2436,11 +2475,11 @@ public class AlignmentUtilsTests SequenceI pep1 = new Sequence("pep1", "MLS"); pep1.createDatasetSequence(); List seqMappings = new ArrayList<>(); - MapList mapList = new MapList( + MapList mapList = new MapList(new int[] { 5, 6, 9, 15 }, new int[] - { 5, 6, 9, 15 }, new int[] { 1, 3 }, 3, 1); + { 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(), @@ -2461,8 +2500,9 @@ public class AlignmentUtilsTests // 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); + 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, @@ -2493,28 +2533,27 @@ public class AlignmentUtilsTests 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); + 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 @@ -2522,7 +2561,7 @@ public class AlignmentUtilsTests 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) @@ -2541,13 +2580,14 @@ public class AlignmentUtilsTests // 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); + 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! */