1 package jalview.io.vcf;
3 import static jalview.io.gff.SequenceOntologyI.SEQUENCE_VARIANT;
4 import static org.testng.Assert.assertEquals;
5 import static org.testng.Assert.assertNull;
6 import static org.testng.Assert.assertSame;
8 import jalview.bin.Cache;
9 import jalview.datamodel.AlignmentI;
10 import jalview.datamodel.DBRefEntry;
11 import jalview.datamodel.Mapping;
12 import jalview.datamodel.Sequence;
13 import jalview.datamodel.SequenceFeature;
14 import jalview.datamodel.SequenceI;
15 import jalview.datamodel.features.FeatureAttributes;
16 import jalview.datamodel.features.FeatureAttributes.Datatype;
17 import jalview.datamodel.features.SequenceFeatures;
18 import jalview.gui.AlignFrame;
19 import jalview.io.DataSourceType;
20 import jalview.io.FileLoader;
21 import jalview.io.gff.Gff3Helper;
22 import jalview.io.gff.SequenceOntologyI;
23 import jalview.util.MapList;
26 import java.io.IOException;
27 import java.io.PrintWriter;
28 import java.util.List;
31 import org.testng.annotations.BeforeClass;
32 import org.testng.annotations.BeforeTest;
33 import org.testng.annotations.Test;
35 public class VCFLoaderTest
37 private static final float DELTA = 0.00001f;
39 // columns 9717- of gene P30419 from Ensembl (much modified)
40 private static final String FASTA = ""
43 * forward strand 'gene' and 'transcript' with two exons
45 ">gene1/1-25 chromosome:GRCh38:17:45051610:45051634:1\n"
46 + "CAAGCTGGCGGACGAGAGTGTGACA\n"
47 + ">transcript1/1-18\n--AGCTGGCG----AGAGTGTGAC-\n"
50 * reverse strand gene and transcript (reverse complement alleles!)
52 + ">gene2/1-25 chromosome:GRCh38:17:45051610:45051634:-1\n"
53 + "TGTCACACTCTCGTCCGCCAGCTTG\n"
54 + ">transcript2/1-18\n" + "-GTCACACTCT----CGCCAGCT--\n"
57 * 'gene' on chromosome 5 with two transcripts
59 + ">gene3/1-25 chromosome:GRCh38:5:45051610:45051634:1\n"
60 + "CAAGCTGGCGGACGAGAGTGTGACA\n"
61 + ">transcript3/1-18\n--AGCTGGCG----AGAGTGTGAC-\n"
62 + ">transcript4/1-18\n-----TGG-GGACGAGAGTGTGA-A\n";
64 private static final String[] VCF = { "##fileformat=VCFv4.2",
65 // fields other than AF are ignored when parsing as they have no INFO definition
66 "##INFO=<ID=AF,Number=A,Type=Float,Description=\"Allele Frequency, for each ALT allele, in the same order as listed\">",
67 "##INFO=<ID=AC_Female,Number=A,Type=Integer,Description=\"Allele count in Female genotypes\"",
68 "##INFO=<ID=AF_AFR,Number=A,Type=Float,Description=\"Allele Frequency among African/African American genotypes\"",
69 "##reference=Homo_sapiens/GRCh38",
70 "#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO",
71 // A/T,C variants in position 2 of gene sequence (precedes transcript)
72 // should create 2 variant features with respective AF values
73 // malformed values for AC_Female and AF_AFR should be ignored
74 "17\t45051611\trs384765\tA\tT,C\t1666.64\tRF;XYZ\tAC=15;AF=5.0e-03,4.0e-03;AC_Female=12,3d;AF_AFR=low,2.3e-4",
75 // SNP G/C in position 4 of gene sequence, position 2 of transcript
76 // insertion G/GA is transferred to nucleotide but not to peptide
77 "17\t45051613\t.\tG\tGA,C\t1666.65\t.\tAC=15;AF=3.0e-03,2.0e-03",
78 // '.' in INFO field should be ignored
79 "17\t45051615\t.\tG\tC\t1666.66\tRF\tAC=16;AF=." };
81 @BeforeClass(alwaysRun = true)
85 * configure to capture all available VCF and VEP (CSQ) fields
87 Cache.loadProperties("test/jalview/io/testProps.jvprops");
88 Cache.setProperty("VCF_FIELDS", ".*");
89 Cache.setProperty("VEP_FIELDS", ".*");
90 Cache.setProperty("VCF_ASSEMBLY", "GRCh38=GRCh38");
94 @BeforeTest(alwaysRun = true)
95 public void setUpBeforeTest()
98 * clear down feature attributes metadata
100 FeatureAttributes.getInstance().clear();
103 @Test(groups = "Functional")
104 public void testDoLoad() throws IOException
106 AlignmentI al = buildAlignment();
108 File f = makeVcfFile();
109 VCFLoader loader = new VCFLoader(f.getPath());
111 loader.doLoad(al.getSequencesArray(), null);
114 * verify variant feature(s) added to gene
115 * NB alleles at a locus may not be processed, and features added,
116 * in the order in which they appear in the VCF record as method
117 * VariantContext.getAlternateAlleles() does not guarantee order
118 * - order of assertions here matches what we find (is not important)
120 List<SequenceFeature> geneFeatures = al.getSequenceAt(0)
121 .getSequenceFeatures();
122 SequenceFeatures.sortFeatures(geneFeatures, true);
123 assertEquals(geneFeatures.size(), 5);
124 SequenceFeature sf = geneFeatures.get(0);
125 assertEquals(sf.getFeatureGroup(), "VCF");
126 assertEquals(sf.getBegin(), 2);
127 assertEquals(sf.getEnd(), 2);
128 assertEquals(sf.getScore(), 0f);
129 assertEquals(sf.getValue("AF"), "4.0e-03");
130 assertEquals(sf.getValue("AF_AFR"), "2.3e-4");
131 assertEquals(sf.getValue(Gff3Helper.ALLELES), "A,C");
132 assertEquals(sf.getType(), SEQUENCE_VARIANT);
133 assertEquals(sf.getValue("POS"), "45051611");
134 assertEquals(sf.getValue("ID"), "rs384765");
135 assertEquals(sf.getValue("QUAL"), "1666.64");
136 assertEquals(sf.getValue("FILTER"), "RF;XYZ");
137 // malformed integer for AC_Female is ignored (JAL-3375)
138 assertNull(sf.getValue("AC_Female"));
140 sf = geneFeatures.get(1);
141 assertEquals(sf.getFeatureGroup(), "VCF");
142 assertEquals(sf.getBegin(), 2);
143 assertEquals(sf.getEnd(), 2);
144 assertEquals(sf.getType(), SEQUENCE_VARIANT);
145 assertEquals(sf.getScore(), 0f);
146 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 5.0e-03,
148 assertEquals(sf.getValue("AC_Female"), "12");
149 // malformed float for AF_AFR is ignored (JAL-3375)
150 assertNull(sf.getValue("AC_AFR"));
151 assertEquals(sf.getValue(Gff3Helper.ALLELES), "A,T");
153 sf = geneFeatures.get(2);
154 assertEquals(sf.getFeatureGroup(), "VCF");
155 assertEquals(sf.getBegin(), 4);
156 assertEquals(sf.getEnd(), 4);
157 assertEquals(sf.getType(), SEQUENCE_VARIANT);
158 assertEquals(sf.getScore(), 0f);
159 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 2.0e-03,
161 assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,C");
163 sf = geneFeatures.get(3);
164 assertEquals(sf.getFeatureGroup(), "VCF");
165 assertEquals(sf.getBegin(), 4);
166 assertEquals(sf.getEnd(), 4);
167 assertEquals(sf.getType(), SEQUENCE_VARIANT);
168 assertEquals(sf.getScore(), 0f);
169 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 3.0e-03,
171 assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,GA");
172 assertNull(sf.getValue("ID")); // '.' is ignored
173 assertNull(sf.getValue("FILTER")); // '.' is ignored
175 sf = geneFeatures.get(4);
176 assertEquals(sf.getFeatureGroup(), "VCF");
177 assertEquals(sf.getBegin(), 6);
178 assertEquals(sf.getEnd(), 6);
179 assertEquals(sf.getType(), SEQUENCE_VARIANT);
180 assertEquals(sf.getScore(), 0f);
181 // AF=. should not have been captured
182 assertNull(sf.getValue("AF"));
183 assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,C");
186 * verify variant feature(s) added to transcript
188 List<SequenceFeature> transcriptFeatures = al.getSequenceAt(1)
189 .getSequenceFeatures();
190 assertEquals(transcriptFeatures.size(), 3);
191 sf = transcriptFeatures.get(0);
192 assertEquals(sf.getFeatureGroup(), "VCF");
193 assertEquals(sf.getBegin(), 2);
194 assertEquals(sf.getEnd(), 2);
195 assertEquals(sf.getType(), SEQUENCE_VARIANT);
196 assertEquals(sf.getScore(), 0f);
197 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 2.0e-03,
199 assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,C");
200 sf = transcriptFeatures.get(1);
201 assertEquals(sf.getFeatureGroup(), "VCF");
202 assertEquals(sf.getBegin(), 2);
203 assertEquals(sf.getEnd(), 2);
204 assertEquals(sf.getType(), SEQUENCE_VARIANT);
205 assertEquals(sf.getScore(), 0f);
206 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 3.0e-03,
208 assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,GA");
211 * verify SNP variant feature(s) computed and added to protein
212 * first codon AGC varies to ACC giving S/T
214 DBRefEntry[] dbRefs = al.getSequenceAt(1).getDBRefs();
215 SequenceI peptide = null;
216 for (DBRefEntry dbref : dbRefs)
218 if (dbref.getMap().getMap().getFromRatio() == 3)
220 peptide = dbref.getMap().getTo();
223 List<SequenceFeature> proteinFeatures = peptide.getSequenceFeatures();
224 assertEquals(proteinFeatures.size(), 3);
225 sf = proteinFeatures.get(0);
226 assertEquals(sf.getFeatureGroup(), "VCF");
227 assertEquals(sf.getBegin(), 1);
228 assertEquals(sf.getEnd(), 1);
229 assertEquals(sf.getType(), SequenceOntologyI.NONSYNONYMOUS_VARIANT);
230 assertEquals(sf.getDescription(), "p.Ser1Thr");
233 * check that sequence_variant attribute AF has been clocked as
234 * numeric with correct min and max values
235 * (i.e. invalid values have been ignored - JAL-3375)
237 FeatureAttributes fa = FeatureAttributes.getInstance();
238 assertSame(fa.getDatatype(SEQUENCE_VARIANT, "AF"), Datatype.Number);
239 float[] minmax = fa.getMinMax(SEQUENCE_VARIANT, "AF");
240 assertEquals(minmax[0], 0.002f);
241 assertEquals(minmax[1], 0.005f);
244 private File makeVcfFile() throws IOException
246 File f = File.createTempFile("Test", ".vcf");
248 PrintWriter pw = new PrintWriter(f);
249 for (String vcfLine : VCF)
258 * Make a simple alignment with one 'gene' and one 'transcript'
262 private AlignmentI buildAlignment()
264 AlignFrame af = new FileLoader().LoadFileWaitTillLoaded(FASTA,
265 DataSourceType.PASTE);
268 * map gene1 sequence to chromosome (normally done when the sequence is fetched
269 * from Ensembl and transcripts computed)
271 AlignmentI alignment = af.getViewport().getAlignment();
272 SequenceI gene1 = alignment.findName("gene1");
273 int[] to = new int[] { 45051610, 45051634 };
274 int[] from = new int[] { gene1.getStart(), gene1.getEnd() };
275 gene1.setGeneLoci("homo_sapiens", "GRCh38", "17", new MapList(from, to,
279 * map 'transcript1' to chromosome via 'gene1'
280 * transcript1/1-18 is gene1/3-10,15-24
281 * which is chromosome 45051612-45051619,45051624-45051633
283 to = new int[] { 45051612, 45051619, 45051624, 45051633 };
284 SequenceI transcript1 = alignment.findName("transcript1");
285 from = new int[] { transcript1.getStart(), transcript1.getEnd() };
286 transcript1.setGeneLoci("homo_sapiens", "GRCh38", "17", new MapList(
291 * map gene2 to chromosome reverse strand
293 SequenceI gene2 = alignment.findName("gene2");
294 to = new int[] { 45051634, 45051610 };
295 from = new int[] { gene2.getStart(), gene2.getEnd() };
296 gene2.setGeneLoci("homo_sapiens", "GRCh38", "17", new MapList(from, to,
300 * map 'transcript2' to chromosome via 'gene2'
301 * transcript2/1-18 is gene2/2-11,16-23
302 * which is chromosome 45051633-45051624,45051619-45051612
304 to = new int[] { 45051633, 45051624, 45051619, 45051612 };
305 SequenceI transcript2 = alignment.findName("transcript2");
306 from = new int[] { transcript2.getStart(), transcript2.getEnd() };
307 transcript2.setGeneLoci("homo_sapiens", "GRCh38", "17", new MapList(
312 * add a protein product as a DBRef on transcript1
314 SequenceI peptide1 = new Sequence("ENSP001", "SWRECD");
315 MapList mapList = new MapList(new int[] { 1, 18 }, new int[] { 1, 6 },
317 Mapping map = new Mapping(peptide1, mapList);
318 DBRefEntry product = new DBRefEntry("", "", "ENSP001", map);
319 transcript1.addDBRef(product);
322 * add a protein product as a DBRef on transcript2
324 SequenceI peptide2 = new Sequence("ENSP002", "VTLSPA");
325 mapList = new MapList(new int[] { 1, 18 }, new int[] { 1, 6 }, 3, 1);
326 map = new Mapping(peptide2, mapList);
327 product = new DBRefEntry("", "", "ENSP002", map);
328 transcript2.addDBRef(product);
331 * map gene3 to chromosome
333 SequenceI gene3 = alignment.findName("gene3");
334 to = new int[] { 45051610, 45051634 };
335 from = new int[] { gene3.getStart(), gene3.getEnd() };
336 gene3.setGeneLoci("homo_sapiens", "GRCh38", "5", new MapList(from, to,
340 * map 'transcript3' to chromosome
342 SequenceI transcript3 = alignment.findName("transcript3");
343 to = new int[] { 45051612, 45051619, 45051624, 45051633 };
344 from = new int[] { transcript3.getStart(), transcript3.getEnd() };
345 transcript3.setGeneLoci("homo_sapiens", "GRCh38", "5", new MapList(
350 * map 'transcript4' to chromosome
352 SequenceI transcript4 = alignment.findName("transcript4");
353 to = new int[] { 45051615, 45051617, 45051619, 45051632, 45051634,
355 from = new int[] { transcript4.getStart(), transcript4.getEnd() };
356 transcript4.setGeneLoci("homo_sapiens", "GRCh38", "5", new MapList(
361 * add a protein product as a DBRef on transcript3
363 SequenceI peptide3 = new Sequence("ENSP003", "SWRECD");
364 mapList = new MapList(new int[] { 1, 18 }, new int[] { 1, 6 }, 3, 1);
365 map = new Mapping(peptide3, mapList);
366 product = new DBRefEntry("", "", "ENSP003", map);
367 transcript3.addDBRef(product);
373 * Test with 'gene' and 'transcript' mapped to the reverse strand of the
374 * chromosome. The VCF variant positions (in forward coordinates) should get
375 * correctly located on sequence positions.
377 * @throws IOException
379 @Test(groups = "Functional")
380 public void testDoLoad_reverseStrand() throws IOException
382 AlignmentI al = buildAlignment();
384 File f = makeVcfFile();
386 VCFLoader loader = new VCFLoader(f.getPath());
388 loader.doLoad(al.getSequencesArray(), null);
391 * verify variant feature(s) added to gene2
392 * gene2/1-25 maps to chromosome 45051634- reverse strand
394 List<SequenceFeature> geneFeatures = al.getSequenceAt(2)
395 .getSequenceFeatures();
396 SequenceFeatures.sortFeatures(geneFeatures, true);
397 assertEquals(geneFeatures.size(), 5);
401 * insertion G/GA at 45051613 maps to an insertion at
402 * the preceding position (21) on reverse strand gene
403 * reference: CAAGC -> GCTTG/21-25
404 * genomic variant: CAAGAC (G/GA)
405 * gene variant: GTCTTG (G/GT at 21)
407 sf = geneFeatures.get(1);
408 assertEquals(sf.getFeatureGroup(), "VCF");
409 assertEquals(sf.getBegin(), 21);
410 assertEquals(sf.getEnd(), 21);
411 assertEquals(sf.getType(), SEQUENCE_VARIANT);
412 assertEquals(sf.getScore(), 0f);
413 assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,GT");
414 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 3.0e-03,
418 * variant G/C at 45051613 maps to C/G at gene position 22
420 sf = geneFeatures.get(2);
421 assertEquals(sf.getFeatureGroup(), "VCF");
422 assertEquals(sf.getBegin(), 22);
423 assertEquals(sf.getEnd(), 22);
424 assertEquals(sf.getType(), SEQUENCE_VARIANT);
425 assertEquals(sf.getScore(), 0f);
426 assertEquals(sf.getValue(Gff3Helper.ALLELES), "C,G");
427 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 2.0e-03,
431 * variant A/C at 45051611 maps to T/G at gene position 24
433 sf = geneFeatures.get(3);
434 assertEquals(sf.getFeatureGroup(), "VCF");
435 assertEquals(sf.getBegin(), 24);
436 assertEquals(sf.getEnd(), 24);
437 assertEquals(sf.getType(), SEQUENCE_VARIANT);
438 assertEquals(sf.getScore(), 0f);
439 assertEquals(sf.getValue(Gff3Helper.ALLELES), "T,G");
440 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 4.0e-03,
444 * variant A/T at 45051611 maps to T/A at gene position 24
446 sf = geneFeatures.get(4);
447 assertEquals(sf.getFeatureGroup(), "VCF");
448 assertEquals(sf.getBegin(), 24);
449 assertEquals(sf.getEnd(), 24);
450 assertEquals(sf.getType(), SEQUENCE_VARIANT);
451 assertEquals(sf.getScore(), 0f);
452 assertEquals(sf.getValue(Gff3Helper.ALLELES), "T,A");
453 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 5.0e-03,
457 * verify 3 variant features added to transcript2
459 List<SequenceFeature> transcriptFeatures = al.getSequenceAt(3)
460 .getSequenceFeatures();
461 assertEquals(transcriptFeatures.size(), 3);
464 * insertion G/GT at position 21 of gene maps to position 16 of transcript
466 sf = transcriptFeatures.get(1);
467 assertEquals(sf.getFeatureGroup(), "VCF");
468 assertEquals(sf.getBegin(), 16);
469 assertEquals(sf.getEnd(), 16);
470 assertEquals(sf.getType(), SEQUENCE_VARIANT);
471 assertEquals(sf.getScore(), 0f);
472 assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,GT");
473 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 3.0e-03,
477 * SNP C/G at position 22 of gene maps to position 17 of transcript
479 sf = transcriptFeatures.get(2);
480 assertEquals(sf.getFeatureGroup(), "VCF");
481 assertEquals(sf.getBegin(), 17);
482 assertEquals(sf.getEnd(), 17);
483 assertEquals(sf.getType(), SEQUENCE_VARIANT);
484 assertEquals(sf.getScore(), 0f);
485 assertEquals(sf.getValue(Gff3Helper.ALLELES), "C,G");
486 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 2.0e-03,
490 * verify variant feature(s) computed and added to protein
491 * last codon GCT varies to GGT giving A/G in the last peptide position
493 DBRefEntry[] dbRefs = al.getSequenceAt(3).getDBRefs();
494 SequenceI peptide = null;
495 for (DBRefEntry dbref : dbRefs)
497 if (dbref.getMap().getMap().getFromRatio() == 3)
499 peptide = dbref.getMap().getTo();
502 List<SequenceFeature> proteinFeatures = peptide.getSequenceFeatures();
503 assertEquals(proteinFeatures.size(), 3);
504 sf = proteinFeatures.get(0);
505 assertEquals(sf.getFeatureGroup(), "VCF");
506 assertEquals(sf.getBegin(), 6);
507 assertEquals(sf.getEnd(), 6);
508 assertEquals(sf.getType(), SequenceOntologyI.NONSYNONYMOUS_VARIANT);
509 assertEquals(sf.getDescription(), "p.Ala6Gly");
513 * Tests that if VEP consequence (CSQ) data is present in the VCF data, then
514 * it is added to the variant feature, but restricted where possible to the
515 * consequences for a specific transcript
517 * @throws IOException
519 @Test(groups = "Functional")
520 public void testDoLoad_vepCsq() throws IOException
522 AlignmentI al = buildAlignment();
524 VCFLoader loader = new VCFLoader("test/jalview/io/vcf/testVcf.vcf");
527 * VCF data file with variants at gene3 positions
532 * 17 A/AC (insertion), A/G
534 loader.doLoad(al.getSequencesArray(), null);
537 * verify variant feature(s) added to gene3
539 List<SequenceFeature> geneFeatures = al.findName("gene3")
540 .getSequenceFeatures();
541 SequenceFeatures.sortFeatures(geneFeatures, true);
542 assertEquals(geneFeatures.size(), 7);
543 SequenceFeature sf = geneFeatures.get(0);
544 assertEquals(sf.getBegin(), 1);
545 assertEquals(sf.getEnd(), 1);
546 assertEquals(sf.getScore(), 0f);
547 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.1f, DELTA);
548 assertEquals(sf.getValue("alleles"), "C,A");
549 // gene features include Consequence for all transcripts
550 Map map = (Map) sf.getValue("CSQ");
551 assertEquals(map.size(), 9);
553 sf = geneFeatures.get(1);
554 assertEquals(sf.getBegin(), 5);
555 assertEquals(sf.getEnd(), 5);
556 assertEquals(sf.getScore(), 0f);
557 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.2f, DELTA);
558 assertEquals(sf.getValue("alleles"), "C,T");
559 map = (Map) sf.getValue("CSQ");
560 assertEquals(map.size(), 9);
562 sf = geneFeatures.get(2);
563 assertEquals(sf.getBegin(), 9);
564 assertEquals(sf.getEnd(), 11); // deletion over 3 positions
565 assertEquals(sf.getScore(), 0f);
566 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.3f, DELTA);
567 assertEquals(sf.getValue("alleles"), "CGG,C");
568 map = (Map) sf.getValue("CSQ");
569 assertEquals(map.size(), 9);
571 sf = geneFeatures.get(3);
572 assertEquals(sf.getBegin(), 13);
573 assertEquals(sf.getEnd(), 13);
574 assertEquals(sf.getScore(), 0f);
575 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.5f, DELTA);
576 assertEquals(sf.getValue("alleles"), "C,T");
577 map = (Map) sf.getValue("CSQ");
578 assertEquals(map.size(), 9);
580 sf = geneFeatures.get(4);
581 assertEquals(sf.getBegin(), 13);
582 assertEquals(sf.getEnd(), 13);
583 assertEquals(sf.getScore(), 0f);
584 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.4f, DELTA);
585 assertEquals(sf.getValue("alleles"), "C,G");
586 map = (Map) sf.getValue("CSQ");
587 assertEquals(map.size(), 9);
589 sf = geneFeatures.get(5);
590 assertEquals(sf.getBegin(), 17);
591 assertEquals(sf.getEnd(), 17);
592 assertEquals(sf.getScore(), 0f);
593 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.7f, DELTA);
594 assertEquals(sf.getValue("alleles"), "A,G");
595 map = (Map) sf.getValue("CSQ");
596 assertEquals(map.size(), 9);
598 sf = geneFeatures.get(6);
599 assertEquals(sf.getBegin(), 17);
600 assertEquals(sf.getEnd(), 17); // insertion
601 assertEquals(sf.getScore(), 0f);
602 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.6f, DELTA);
603 assertEquals(sf.getValue("alleles"), "A,AC");
604 map = (Map) sf.getValue("CSQ");
605 assertEquals(map.size(), 9);
608 * verify variant feature(s) added to transcript3
609 * at columns 5 (1), 17 (2), positions 3, 11
610 * note the deletion at columns 9-11 is not transferred since col 11
611 * has no mapping to transcript 3
613 List<SequenceFeature> transcriptFeatures = al.findName("transcript3")
614 .getSequenceFeatures();
615 SequenceFeatures.sortFeatures(transcriptFeatures, true);
616 assertEquals(transcriptFeatures.size(), 3);
617 sf = transcriptFeatures.get(0);
618 assertEquals(sf.getBegin(), 3);
619 assertEquals(sf.getEnd(), 3);
620 assertEquals(sf.getScore(), 0f);
621 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.2f, DELTA);
622 assertEquals(sf.getValue("alleles"), "C,T");
623 // transcript features only have Consequence for that transcripts
624 map = (Map) sf.getValue("CSQ");
625 assertEquals(map.size(), 9);
626 assertEquals(sf.getValueAsString("CSQ", "Feature"), "transcript3");
628 sf = transcriptFeatures.get(1);
629 assertEquals(sf.getBegin(), 11);
630 assertEquals(sf.getEnd(), 11);
631 assertEquals(sf.getScore(), 0f);
632 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.7f, DELTA);
633 assertEquals(sf.getValue("alleles"), "A,G");
634 assertEquals(map.size(), 9);
635 assertEquals(sf.getValueAsString("CSQ", "Feature"), "transcript3");
637 sf = transcriptFeatures.get(2);
638 assertEquals(sf.getBegin(), 11);
639 assertEquals(sf.getEnd(), 11);
640 assertEquals(sf.getScore(), 0f);
641 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.6f, DELTA);
642 assertEquals(sf.getValue("alleles"), "A,AC");
643 assertEquals(map.size(), 9);
644 assertEquals(sf.getValueAsString("CSQ", "Feature"), "transcript3");
647 * verify variants computed on protein product for transcript3
649 * codon variants are AGC/AGT position 1 which is synonymous
650 * and GAG/GGG which is E/G in position 4
651 * the insertion variant is not transferred to the peptide
653 DBRefEntry[] dbRefs = al.findName("transcript3").getDBRefs();
654 SequenceI peptide = null;
655 for (DBRefEntry dbref : dbRefs)
657 if (dbref.getMap().getMap().getFromRatio() == 3)
659 peptide = dbref.getMap().getTo();
662 List<SequenceFeature> proteinFeatures = peptide.getSequenceFeatures();
663 SequenceFeatures.sortFeatures(proteinFeatures, true);
664 assertEquals(proteinFeatures.size(), 2);
665 sf = proteinFeatures.get(0);
666 assertEquals(sf.getFeatureGroup(), "VCF");
667 assertEquals(sf.getBegin(), 1);
668 assertEquals(sf.getEnd(), 1);
669 assertEquals(sf.getType(), SequenceOntologyI.SYNONYMOUS_VARIANT);
670 assertEquals(sf.getDescription(), "agC/agT");
671 sf = proteinFeatures.get(1);
672 assertEquals(sf.getFeatureGroup(), "VCF");
673 assertEquals(sf.getBegin(), 4);
674 assertEquals(sf.getEnd(), 4);
675 assertEquals(sf.getType(), SequenceOntologyI.NONSYNONYMOUS_VARIANT);
676 assertEquals(sf.getDescription(), "p.Glu4Gly");
679 * verify variant feature(s) added to transcript4
680 * at columns 13 (2) and 17 (2), positions 7 and 11
682 transcriptFeatures = al.findName("transcript4").getSequenceFeatures();
683 SequenceFeatures.sortFeatures(transcriptFeatures, true);
684 assertEquals(transcriptFeatures.size(), 4);
685 sf = transcriptFeatures.get(0);
686 assertEquals(sf.getBegin(), 7);
687 assertEquals(sf.getEnd(), 7);
688 assertEquals(sf.getScore(), 0f);
689 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.5f, DELTA);
690 assertEquals(sf.getValue("alleles"), "C,T");
691 assertEquals(map.size(), 9);
692 assertEquals(sf.getValueAsString("CSQ", "Feature"), "transcript4");
694 sf = transcriptFeatures.get(1);
695 assertEquals(sf.getBegin(), 7);
696 assertEquals(sf.getEnd(), 7);
697 assertEquals(sf.getScore(), 0f);
698 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.4f, DELTA);
699 assertEquals(sf.getValue("alleles"), "C,G");
700 assertEquals(map.size(), 9);
701 assertEquals(sf.getValueAsString("CSQ", "Feature"), "transcript4");
703 sf = transcriptFeatures.get(2);
704 assertEquals(sf.getBegin(), 11);
705 assertEquals(sf.getEnd(), 11);
706 assertEquals(sf.getScore(), 0f);
707 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.7f, DELTA);
708 assertEquals(sf.getValue("alleles"), "A,G");
709 assertEquals(map.size(), 9);
710 assertEquals(sf.getValueAsString("CSQ", "Feature"), "transcript4");
712 sf = transcriptFeatures.get(3);
713 assertEquals(sf.getBegin(), 11);
714 assertEquals(sf.getEnd(), 11);
715 assertEquals(sf.getScore(), 0f);
716 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.6f, DELTA);
717 assertEquals(sf.getValue("alleles"), "A,AC");
718 assertEquals(map.size(), 9);
719 assertEquals(sf.getValueAsString("CSQ", "Feature"), "transcript4");
723 * A test that demonstrates loading a contig sequence from an indexed sequence
724 * database which is the reference for a VCF file
726 * @throws IOException
728 @Test(groups = "Functional")
729 public void testLoadVCFContig() throws IOException
731 VCFLoader loader = new VCFLoader(
732 "test/jalview/io/vcf/testVcf2.vcf");
734 SequenceI seq = loader.loadVCFContig("contig123");
735 assertEquals(seq.getLength(), 15);
736 assertEquals(seq.getSequenceAsString(), "AAAAACCCCCGGGGG");
737 List<SequenceFeature> features = seq.getSequenceFeatures();
738 SequenceFeatures.sortFeatures(features, true);
739 assertEquals(features.size(), 2);
740 SequenceFeature sf = features.get(0);
741 assertEquals(sf.getBegin(), 8);
742 assertEquals(sf.getEnd(), 8);
743 assertEquals(sf.getDescription(), "C,A");
744 sf = features.get(1);
745 assertEquals(sf.getBegin(), 12);
746 assertEquals(sf.getEnd(), 12);
747 assertEquals(sf.getDescription(), "G,T");
749 seq = loader.loadVCFContig("contig789");
750 assertEquals(seq.getLength(), 25);
751 assertEquals(seq.getSequenceAsString(), "GGGGGTTTTTAAAAACCCCCGGGGG");
752 features = seq.getSequenceFeatures();
753 SequenceFeatures.sortFeatures(features, true);
754 assertEquals(features.size(), 2);
755 sf = features.get(0);
756 assertEquals(sf.getBegin(), 2);
757 assertEquals(sf.getEnd(), 2);
758 assertEquals(sf.getDescription(), "G,T");
759 sf = features.get(1);
760 assertEquals(sf.getBegin(), 21);
761 assertEquals(sf.getEnd(), 21);
762 assertEquals(sf.getDescription(), "G,A");
764 seq = loader.loadVCFContig("contig456");
765 assertEquals(seq.getLength(), 20);
766 assertEquals(seq.getSequenceAsString(), "CCCCCGGGGGTTTTTAAAAA");
767 features = seq.getSequenceFeatures();
768 SequenceFeatures.sortFeatures(features, true);
769 assertEquals(features.size(), 1);
770 sf = features.get(0);
771 assertEquals(sf.getBegin(), 15);
772 assertEquals(sf.getEnd(), 15);
773 assertEquals(sf.getDescription(), "T,C");