1 package jalview.io.vcf;
3 import static org.testng.Assert.assertEquals;
4 import static org.testng.Assert.assertSame;
5 import static org.testng.Assert.assertTrue;
7 import jalview.bin.Cache;
8 import jalview.datamodel.AlignmentI;
9 import jalview.datamodel.DBRefEntry;
10 import jalview.datamodel.Mapping;
11 import jalview.datamodel.Sequence;
12 import jalview.datamodel.SequenceFeature;
13 import jalview.datamodel.SequenceI;
14 import jalview.datamodel.features.SequenceFeatures;
15 import jalview.gui.AlignFrame;
16 import jalview.io.DataSourceType;
17 import jalview.io.FileLoader;
18 import jalview.io.gff.Gff3Helper;
19 import jalview.io.gff.SequenceOntologyI;
20 import jalview.util.MapList;
23 import java.io.IOException;
24 import java.io.PrintWriter;
25 import java.util.List;
28 import org.testng.annotations.BeforeClass;
29 import org.testng.annotations.Test;
31 public class VCFLoaderTest
33 private static final float DELTA = 0.00001f;
35 // columns 9717- of gene P30419 from Ensembl (much modified)
36 private static final String FASTA = ""
39 * forward strand 'gene' and 'transcript' with two exons
41 ">gene1/1-25 chromosome:GRCh38:17:45051610:45051634:1\n"
42 + "CAAGCTGGCGGACGAGAGTGTGACA\n"
43 + ">transcript1/1-18\n--AGCTGGCG----AGAGTGTGAC-\n"
46 * reverse strand gene and transcript (reverse complement alleles!)
48 + ">gene2/1-25 chromosome:GRCh38:17:45051610:45051634:-1\n"
49 + "TGTCACACTCTCGTCCGCCAGCTTG\n"
50 + ">transcript2/1-18\n" + "-GTCACACTCT----CGCCAGCT--\n"
53 * 'gene' on chromosome 5 with two transcripts
55 + ">gene3/1-25 chromosome:GRCh38:5:45051610:45051634:1\n"
56 + "CAAGCTGGCGGACGAGAGTGTGACA\n"
57 + ">transcript3/1-18\n--AGCTGGCG----AGAGTGTGAC-\n"
58 + ">transcript4/1-18\n-----TGG-GGACGAGAGTGTGA-A\n";
60 private static final String[] VCF = { "##fileformat=VCFv4.2",
61 "##INFO=<ID=AF,Number=A,Type=Float,Description=\"Allele Frequency, for each ALT allele, in the same order as listed\">",
62 "##reference=Homo_sapiens/GRCh38",
63 "#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO",
64 // A/T,C variants in position 2 of gene sequence (precedes transcript)
65 // should create 2 variant features with respective scores
66 "17\t45051611\t.\tA\tT,C\t1666.64\tRF\tAC=15;AF=5.0e-03,4.0e-03",
67 // SNP G/C in position 4 of gene sequence, position 2 of transcript
68 // insertion G/GA is transferred to nucleotide but not to peptide
69 "17\t45051613\t.\tG\tGA,C\t1666.64\tRF\tAC=15;AF=3.0e-03,2.0e-03" };
71 @BeforeClass(alwaysRun = true)
75 * configure to capture all available VCF and VEP (CSQ) fields
77 Cache.loadProperties("test/jalview/io/testProps.jvprops");
78 Cache.setProperty("VCF_FIELDS", ".*");
79 Cache.setProperty("VEP_FIELDS", ".*");
80 Cache.setProperty("VCF_ASSEMBLY", "GRCh38=GRCh38");
84 @Test(groups = "Functional")
85 public void testDoLoad() throws IOException
87 AlignmentI al = buildAlignment();
90 VCFLoader loader = new VCFLoader(f.getPath());
92 loader.doLoad(al.getSequencesArray(), null);
95 * verify variant feature(s) added to gene
96 * NB alleles at a locus may not be processed, and features added,
97 * in the order in which they appear in the VCF record as method
98 * VariantContext.getAlternateAlleles() does not guarantee order
99 * - order of assertions here matches what we find (is not important)
101 List<SequenceFeature> geneFeatures = al.getSequenceAt(0)
102 .getSequenceFeatures();
103 SequenceFeatures.sortFeatures(geneFeatures, true);
104 assertEquals(geneFeatures.size(), 4);
105 SequenceFeature sf = geneFeatures.get(0);
106 assertEquals(sf.getFeatureGroup(), "VCF");
107 assertEquals(sf.getBegin(), 2);
108 assertEquals(sf.getEnd(), 2);
109 assertEquals(sf.getScore(), 0f);
110 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 4.0e-03,
112 assertEquals(sf.getValue(Gff3Helper.ALLELES), "A,C");
113 assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
114 sf = geneFeatures.get(1);
115 assertEquals(sf.getFeatureGroup(), "VCF");
116 assertEquals(sf.getBegin(), 2);
117 assertEquals(sf.getEnd(), 2);
118 assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
119 assertEquals(sf.getScore(), 0f);
120 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 5.0e-03,
122 assertEquals(sf.getValue(Gff3Helper.ALLELES), "A,T");
124 sf = geneFeatures.get(2);
125 assertEquals(sf.getFeatureGroup(), "VCF");
126 assertEquals(sf.getBegin(), 4);
127 assertEquals(sf.getEnd(), 4);
128 assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
129 assertEquals(sf.getScore(), 0f);
130 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 2.0e-03,
132 assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,C");
134 sf = geneFeatures.get(3);
135 assertEquals(sf.getFeatureGroup(), "VCF");
136 assertEquals(sf.getBegin(), 4);
137 assertEquals(sf.getEnd(), 4);
138 assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
139 assertEquals(sf.getScore(), 0f);
140 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 3.0e-03,
142 assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,GA");
145 * verify variant feature(s) added to transcript
147 List<SequenceFeature> transcriptFeatures = al.getSequenceAt(1)
148 .getSequenceFeatures();
149 assertEquals(transcriptFeatures.size(), 2);
150 sf = transcriptFeatures.get(0);
151 assertEquals(sf.getFeatureGroup(), "VCF");
152 assertEquals(sf.getBegin(), 2);
153 assertEquals(sf.getEnd(), 2);
154 assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
155 assertEquals(sf.getScore(), 0f);
156 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 2.0e-03,
158 assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,C");
159 sf = transcriptFeatures.get(1);
160 assertEquals(sf.getFeatureGroup(), "VCF");
161 assertEquals(sf.getBegin(), 2);
162 assertEquals(sf.getEnd(), 2);
163 assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
164 assertEquals(sf.getScore(), 0f);
165 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 3.0e-03,
167 assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,GA");
170 * verify SNP variant feature(s) computed and added to protein
171 * first codon AGC varies to ACC giving S/T
173 DBRefEntry[] dbRefs = al.getSequenceAt(1).getDBRefs();
174 SequenceI peptide = null;
175 for (DBRefEntry dbref : dbRefs)
177 if (dbref.getMap().getMap().getFromRatio() == 3)
179 peptide = dbref.getMap().getTo();
182 List<SequenceFeature> proteinFeatures = peptide.getSequenceFeatures();
185 * JAL-3187 don't precompute protein features, do dynamically instead
187 assertTrue(proteinFeatures.isEmpty());
188 // assertEquals(proteinFeatures.size(), 1);
189 // sf = proteinFeatures.get(0);
190 // assertEquals(sf.getFeatureGroup(), "VCF");
191 // assertEquals(sf.getBegin(), 1);
192 // assertEquals(sf.getEnd(), 1);
193 // assertEquals(sf.getType(), SequenceOntologyI.NONSYNONYMOUS_VARIANT);
194 // assertEquals(sf.getDescription(), "p.Ser1Thr");
197 private File makeVcf() throws IOException
199 File f = File.createTempFile("Test", ".vcf");
201 PrintWriter pw = new PrintWriter(f);
202 for (String vcfLine : VCF)
211 * Make a simple alignment with one 'gene' and one 'transcript'
215 private AlignmentI buildAlignment()
217 AlignFrame af = new FileLoader().LoadFileWaitTillLoaded(FASTA,
218 DataSourceType.PASTE);
221 * map gene1 sequence to chromosome (normally done when the sequence is fetched
222 * from Ensembl and transcripts computed)
224 AlignmentI alignment = af.getViewport().getAlignment();
225 SequenceI gene1 = alignment.findName("gene1");
226 int[] to = new int[] { 45051610, 45051634 };
227 int[] from = new int[] { gene1.getStart(), gene1.getEnd() };
228 gene1.setGeneLoci("homo_sapiens", "GRCh38", "17", new MapList(from, to,
232 * map 'transcript1' to chromosome via 'gene1'
233 * transcript1/1-18 is gene1/3-10,15-24
234 * which is chromosome 45051612-45051619,45051624-45051633
236 to = new int[] { 45051612, 45051619, 45051624, 45051633 };
237 SequenceI transcript1 = alignment.findName("transcript1");
238 from = new int[] { transcript1.getStart(), transcript1.getEnd() };
239 transcript1.setGeneLoci("homo_sapiens", "GRCh38", "17", new MapList(
244 * map gene2 to chromosome reverse strand
246 SequenceI gene2 = alignment.findName("gene2");
247 to = new int[] { 45051634, 45051610 };
248 from = new int[] { gene2.getStart(), gene2.getEnd() };
249 gene2.setGeneLoci("homo_sapiens", "GRCh38", "17", new MapList(from, to,
253 * map 'transcript2' to chromosome via 'gene2'
254 * transcript2/1-18 is gene2/2-11,16-23
255 * which is chromosome 45051633-45051624,45051619-45051612
257 to = new int[] { 45051633, 45051624, 45051619, 45051612 };
258 SequenceI transcript2 = alignment.findName("transcript2");
259 from = new int[] { transcript2.getStart(), transcript2.getEnd() };
260 transcript2.setGeneLoci("homo_sapiens", "GRCh38", "17", new MapList(
265 * add a protein product as a DBRef on transcript1
267 SequenceI peptide1 = new Sequence("ENSP001", "SWRECD");
268 MapList mapList = new MapList(new int[] { 1, 18 }, new int[] { 1, 6 },
270 Mapping map = new Mapping(peptide1, mapList);
271 DBRefEntry product = new DBRefEntry("", "", "ENSP001", map);
272 transcript1.addDBRef(product);
275 * add a protein product as a DBRef on transcript2
277 SequenceI peptide2 = new Sequence("ENSP002", "VTLSPA");
278 mapList = new MapList(new int[] { 1, 18 }, new int[] { 1, 6 }, 3, 1);
279 map = new Mapping(peptide2, mapList);
280 product = new DBRefEntry("", "", "ENSP002", map);
281 transcript2.addDBRef(product);
284 * map gene3 to chromosome
286 SequenceI gene3 = alignment.findName("gene3");
287 to = new int[] { 45051610, 45051634 };
288 from = new int[] { gene3.getStart(), gene3.getEnd() };
289 gene3.setGeneLoci("homo_sapiens", "GRCh38", "5", new MapList(from, to,
293 * map 'transcript3' to chromosome
295 SequenceI transcript3 = alignment.findName("transcript3");
296 to = new int[] { 45051612, 45051619, 45051624, 45051633 };
297 from = new int[] { transcript3.getStart(), transcript3.getEnd() };
298 transcript3.setGeneLoci("homo_sapiens", "GRCh38", "5", new MapList(
303 * map 'transcript4' to chromosome
305 SequenceI transcript4 = alignment.findName("transcript4");
306 to = new int[] { 45051615, 45051617, 45051619, 45051632, 45051634,
308 from = new int[] { transcript4.getStart(), transcript4.getEnd() };
309 transcript4.setGeneLoci("homo_sapiens", "GRCh38", "5", new MapList(
314 * add a protein product as a DBRef on transcript3
316 SequenceI peptide3 = new Sequence("ENSP003", "SWRECD");
317 mapList = new MapList(new int[] { 1, 18 }, new int[] { 1, 6 }, 3, 1);
318 map = new Mapping(peptide3, mapList);
319 product = new DBRefEntry("", "", "ENSP003", map);
320 transcript3.addDBRef(product);
326 * Test with 'gene' and 'transcript' mapped to the reverse strand of the
327 * chromosome. The VCF variant positions (in forward coordinates) should get
328 * correctly located on sequence positions.
330 * @throws IOException
332 @Test(groups = "Functional")
333 public void testDoLoad_reverseStrand() throws IOException
335 AlignmentI al = buildAlignment();
339 VCFLoader loader = new VCFLoader(f.getPath());
341 loader.doLoad(al.getSequencesArray(), null);
344 * verify variant feature(s) added to gene2
345 * gene2/1-25 maps to chromosome 45051634- reverse strand
347 List<SequenceFeature> geneFeatures = al.getSequenceAt(2)
348 .getSequenceFeatures();
349 SequenceFeatures.sortFeatures(geneFeatures, true);
350 assertEquals(geneFeatures.size(), 4);
353 * variant A/T at 45051611 maps to T/A at gene position 24
355 SequenceFeature sf = geneFeatures.get(3);
356 assertEquals(sf.getFeatureGroup(), "VCF");
357 assertEquals(sf.getBegin(), 24);
358 assertEquals(sf.getEnd(), 24);
359 assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
360 assertEquals(sf.getScore(), 0f);
361 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 5.0e-03,
363 assertEquals(sf.getValue(Gff3Helper.ALLELES), "T,A");
366 * variant A/C at 45051611 maps to T/G at gene position 24
368 sf = geneFeatures.get(2);
369 assertEquals(sf.getFeatureGroup(), "VCF");
370 assertEquals(sf.getBegin(), 24);
371 assertEquals(sf.getEnd(), 24);
372 assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
373 assertEquals(sf.getScore(), 0f);
374 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 4.0e-03,
376 assertEquals(sf.getValue(Gff3Helper.ALLELES), "T,G");
379 * variant G/C at 45051613 maps to C/G at gene position 22
381 sf = geneFeatures.get(1);
382 assertEquals(sf.getFeatureGroup(), "VCF");
383 assertEquals(sf.getBegin(), 22);
384 assertEquals(sf.getEnd(), 22);
385 assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
386 assertEquals(sf.getScore(), 0f);
387 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 2.0e-03,
389 assertEquals(sf.getValue(Gff3Helper.ALLELES), "C,G");
392 * insertion G/GA at 45051613 maps to an insertion at
393 * the preceding position (21) on reverse strand gene
394 * reference: CAAGC -> GCTTG/21-25
395 * genomic variant: CAAGAC (G/GA)
396 * gene variant: GTCTTG (G/GT at 21)
398 sf = geneFeatures.get(0);
399 assertEquals(sf.getFeatureGroup(), "VCF");
400 assertEquals(sf.getBegin(), 21);
401 assertEquals(sf.getEnd(), 21);
402 assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
403 assertEquals(sf.getScore(), 0f);
404 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 3.0e-03,
406 assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,GT");
409 * verify 2 variant features added to transcript2
411 List<SequenceFeature> transcriptFeatures = al.getSequenceAt(3)
412 .getSequenceFeatures();
413 assertEquals(transcriptFeatures.size(), 2);
416 * insertion G/GT at position 21 of gene maps to position 16 of transcript
418 sf = transcriptFeatures.get(0);
419 assertEquals(sf.getFeatureGroup(), "VCF");
420 assertEquals(sf.getBegin(), 16);
421 assertEquals(sf.getEnd(), 16);
422 assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
423 assertEquals(sf.getScore(), 0f);
424 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 3.0e-03,
426 assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,GT");
429 * SNP C/G at position 22 of gene maps to position 17 of transcript
431 sf = transcriptFeatures.get(1);
432 assertEquals(sf.getFeatureGroup(), "VCF");
433 assertEquals(sf.getBegin(), 17);
434 assertEquals(sf.getEnd(), 17);
435 assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
436 assertEquals(sf.getScore(), 0f);
437 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 2.0e-03,
439 assertEquals(sf.getValue(Gff3Helper.ALLELES), "C,G");
442 * verify variant feature(s) computed and added to protein
443 * last codon GCT varies to GGT giving A/G in the last peptide position
445 DBRefEntry[] dbRefs = al.getSequenceAt(3).getDBRefs();
446 SequenceI peptide = null;
447 for (DBRefEntry dbref : dbRefs)
449 if (dbref.getMap().getMap().getFromRatio() == 3)
451 peptide = dbref.getMap().getTo();
454 List<SequenceFeature> proteinFeatures = peptide.getSequenceFeatures();
456 * JAL-3187 don't precompute protein features, do dynamically instead
458 assertTrue(proteinFeatures.isEmpty());
459 // assertEquals(proteinFeatures.size(), 1);
460 // sf = proteinFeatures.get(0);
461 // assertEquals(sf.getFeatureGroup(), "VCF");
462 // assertEquals(sf.getBegin(), 6);
463 // assertEquals(sf.getEnd(), 6);
464 // assertEquals(sf.getType(), SequenceOntologyI.NONSYNONYMOUS_VARIANT);
465 // assertEquals(sf.getDescription(), "p.Ala6Gly");
469 * Tests that if VEP consequence (CSQ) data is present in the VCF data, then
470 * it is added to the variant feature, but restricted where possible to the
471 * consequences for a specific transcript
473 * @throws IOException
475 @Test(groups = "Functional")
476 public void testDoLoad_vepCsq() throws IOException
478 AlignmentI al = buildAlignment();
480 VCFLoader loader = new VCFLoader("test/jalview/io/vcf/testVcf.vcf");
483 * VCF data file with variants at gene3 positions
488 * 17 A/AC (insertion), A/G
490 loader.doLoad(al.getSequencesArray(), null);
493 * verify variant feature(s) added to gene3
495 List<SequenceFeature> geneFeatures = al.findName("gene3")
496 .getSequenceFeatures();
497 SequenceFeatures.sortFeatures(geneFeatures, true);
498 assertEquals(geneFeatures.size(), 7);
499 SequenceFeature sf = geneFeatures.get(0);
500 assertEquals(sf.getBegin(), 1);
501 assertEquals(sf.getEnd(), 1);
502 assertEquals(sf.getScore(), 0f);
503 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.1f, DELTA);
504 assertEquals(sf.getValue("alleles"), "C,A");
505 // gene features include Consequence for all transcripts
506 Map map = (Map) sf.getValue("CSQ");
507 assertEquals(map.size(), 9);
508 assertEquals(map.get("PolyPhen"), "Bad");
510 sf = geneFeatures.get(1);
511 assertEquals(sf.getBegin(), 5);
512 assertEquals(sf.getEnd(), 5);
513 assertEquals(sf.getScore(), 0f);
514 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.2f, DELTA);
515 assertEquals(sf.getValue("alleles"), "C,T");
516 map = (Map) sf.getValue("CSQ");
517 assertEquals(map.size(), 9);
518 assertEquals(map.get("PolyPhen"), "Bad++"); // %3B%3B decoded
520 sf = geneFeatures.get(2);
521 assertEquals(sf.getBegin(), 9);
522 assertEquals(sf.getEnd(), 11); // deletion over 3 positions
523 assertEquals(sf.getScore(), 0f);
524 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.3f, DELTA);
525 assertEquals(sf.getValue("alleles"), "CGG,C");
526 map = (Map) sf.getValue("CSQ");
527 assertEquals(map.size(), 9);
529 sf = geneFeatures.get(3);
530 assertEquals(sf.getBegin(), 13);
531 assertEquals(sf.getEnd(), 13);
532 assertEquals(sf.getScore(), 0f);
533 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.5f, DELTA);
534 assertEquals(sf.getValue("alleles"), "C,T");
535 map = (Map) sf.getValue("CSQ");
536 assertEquals(map.size(), 9);
538 sf = geneFeatures.get(4);
539 assertEquals(sf.getBegin(), 13);
540 assertEquals(sf.getEnd(), 13);
541 assertEquals(sf.getScore(), 0f);
542 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.4f, DELTA);
543 assertEquals(sf.getValue("alleles"), "C,G");
544 map = (Map) sf.getValue("CSQ");
545 assertEquals(map.size(), 9);
547 sf = geneFeatures.get(5);
548 assertEquals(sf.getBegin(), 17);
549 assertEquals(sf.getEnd(), 17);
550 assertEquals(sf.getScore(), 0f);
551 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.7f, DELTA);
552 assertEquals(sf.getValue("alleles"), "A,G");
553 map = (Map) sf.getValue("CSQ");
554 assertEquals(map.size(), 9);
556 sf = geneFeatures.get(6);
557 assertEquals(sf.getBegin(), 17);
558 assertEquals(sf.getEnd(), 17); // insertion
559 assertEquals(sf.getScore(), 0f);
560 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.6f, DELTA);
561 assertEquals(sf.getValue("alleles"), "A,AC");
562 map = (Map) sf.getValue("CSQ");
563 assertEquals(map.size(), 9);
566 * verify variant feature(s) added to transcript3
567 * at columns 5 (1), 17 (2), positions 3, 11
568 * note the deletion at columns 9-11 is not transferred since col 11
569 * has no mapping to transcript 3
571 List<SequenceFeature> transcriptFeatures = al.findName("transcript3")
572 .getSequenceFeatures();
573 SequenceFeatures.sortFeatures(transcriptFeatures, true);
574 assertEquals(transcriptFeatures.size(), 3);
575 sf = transcriptFeatures.get(0);
576 assertEquals(sf.getBegin(), 3);
577 assertEquals(sf.getEnd(), 3);
578 assertEquals(sf.getScore(), 0f);
579 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.2f, DELTA);
580 assertEquals(sf.getValue("alleles"), "C,T");
581 // transcript features only have Consequence for that transcripts
582 map = (Map) sf.getValue("CSQ");
583 assertEquals(map.size(), 9);
584 assertEquals(sf.getValueAsString("CSQ", "Feature"), "transcript3");
586 sf = transcriptFeatures.get(1);
587 assertEquals(sf.getBegin(), 11);
588 assertEquals(sf.getEnd(), 11);
589 assertEquals(sf.getScore(), 0f);
590 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.7f, DELTA);
591 assertEquals(sf.getValue("alleles"), "A,G");
592 assertEquals(map.size(), 9);
593 assertEquals(sf.getValueAsString("CSQ", "Feature"), "transcript3");
595 sf = transcriptFeatures.get(2);
596 assertEquals(sf.getBegin(), 11);
597 assertEquals(sf.getEnd(), 11);
598 assertEquals(sf.getScore(), 0f);
599 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.6f, DELTA);
600 assertEquals(sf.getValue("alleles"), "A,AC");
601 assertEquals(map.size(), 9);
602 assertEquals(sf.getValueAsString("CSQ", "Feature"), "transcript3");
605 * verify variants computed on protein product for transcript3
607 * codon variants are AGC/AGT position 1 which is synonymous
608 * and GAG/GGG which is E/G in position 4
609 * the insertion variant is not transferred to the peptide
611 DBRefEntry[] dbRefs = al.findName("transcript3").getDBRefs();
612 SequenceI peptide = null;
613 for (DBRefEntry dbref : dbRefs)
615 if (dbref.getMap().getMap().getFromRatio() == 3)
617 peptide = dbref.getMap().getTo();
620 List<SequenceFeature> proteinFeatures = peptide.getSequenceFeatures();
622 * JAL-3187 don't precompute protein features, do dynamically instead
624 assertTrue(proteinFeatures.isEmpty());
625 // SequenceFeatures.sortFeatures(proteinFeatures, true);
626 // assertEquals(proteinFeatures.size(), 2);
627 // sf = proteinFeatures.get(0);
628 // assertEquals(sf.getFeatureGroup(), "VCF");
629 // assertEquals(sf.getBegin(), 1);
630 // assertEquals(sf.getEnd(), 1);
631 // assertEquals(sf.getType(), SequenceOntologyI.SYNONYMOUS_VARIANT);
632 // assertEquals(sf.getDescription(), "agC/agT");
633 // sf = proteinFeatures.get(1);
634 // assertEquals(sf.getFeatureGroup(), "VCF");
635 // assertEquals(sf.getBegin(), 4);
636 // assertEquals(sf.getEnd(), 4);
637 // assertEquals(sf.getType(), SequenceOntologyI.NONSYNONYMOUS_VARIANT);
638 // assertEquals(sf.getDescription(), "p.Glu4Gly");
641 * verify variant feature(s) added to transcript4
642 * at columns 13 (2) and 17 (2), positions 7 and 11
644 transcriptFeatures = al.findName("transcript4").getSequenceFeatures();
645 SequenceFeatures.sortFeatures(transcriptFeatures, true);
646 assertEquals(transcriptFeatures.size(), 4);
647 sf = transcriptFeatures.get(0);
648 assertEquals(sf.getBegin(), 7);
649 assertEquals(sf.getEnd(), 7);
650 assertEquals(sf.getScore(), 0f);
651 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.5f, DELTA);
652 assertEquals(sf.getValue("alleles"), "C,T");
653 assertEquals(map.size(), 9);
654 assertEquals(sf.getValueAsString("CSQ", "Feature"), "transcript4");
656 sf = transcriptFeatures.get(1);
657 assertEquals(sf.getBegin(), 7);
658 assertEquals(sf.getEnd(), 7);
659 assertEquals(sf.getScore(), 0f);
660 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.4f, DELTA);
661 assertEquals(sf.getValue("alleles"), "C,G");
662 assertEquals(map.size(), 9);
663 assertEquals(sf.getValueAsString("CSQ", "Feature"), "transcript4");
665 sf = transcriptFeatures.get(2);
666 assertEquals(sf.getBegin(), 11);
667 assertEquals(sf.getEnd(), 11);
668 assertEquals(sf.getScore(), 0f);
669 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.7f, DELTA);
670 assertEquals(sf.getValue("alleles"), "A,G");
671 assertEquals(map.size(), 9);
672 assertEquals(sf.getValueAsString("CSQ", "Feature"), "transcript4");
674 sf = transcriptFeatures.get(3);
675 assertEquals(sf.getBegin(), 11);
676 assertEquals(sf.getEnd(), 11);
677 assertEquals(sf.getScore(), 0f);
678 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.6f, DELTA);
679 assertEquals(sf.getValue("alleles"), "A,AC");
680 assertEquals(map.size(), 9);
681 assertEquals(sf.getValueAsString("CSQ", "Feature"), "transcript4");
685 * A test that demonstrates loading a contig sequence from an indexed sequence
686 * database which is the reference for a VCF file
688 * @throws IOException
690 @Test(groups = "Functional")
691 public void testLoadVCFContig() throws IOException
693 VCFLoader loader = new VCFLoader(
694 "test/jalview/io/vcf/testVcf2.vcf");
696 SequenceI seq = loader.loadVCFContig("contig123");
697 assertEquals(seq.getLength(), 15);
698 assertEquals(seq.getSequenceAsString(), "AAAAACCCCCGGGGG");
699 List<SequenceFeature> features = seq.getSequenceFeatures();
700 SequenceFeatures.sortFeatures(features, true);
701 assertEquals(features.size(), 2);
702 SequenceFeature sf = features.get(0);
703 assertEquals(sf.getBegin(), 8);
704 assertEquals(sf.getEnd(), 8);
705 assertEquals(sf.getDescription(), "C,A");
706 sf = features.get(1);
707 assertEquals(sf.getBegin(), 12);
708 assertEquals(sf.getEnd(), 12);
709 assertEquals(sf.getDescription(), "G,T");
711 seq = loader.loadVCFContig("contig789");
712 assertEquals(seq.getLength(), 25);
713 assertEquals(seq.getSequenceAsString(), "GGGGGTTTTTAAAAACCCCCGGGGG");
714 features = seq.getSequenceFeatures();
715 SequenceFeatures.sortFeatures(features, true);
716 assertEquals(features.size(), 2);
717 sf = features.get(0);
718 assertEquals(sf.getBegin(), 2);
719 assertEquals(sf.getEnd(), 2);
720 assertEquals(sf.getDescription(), "G,T");
721 sf = features.get(1);
722 assertEquals(sf.getBegin(), 21);
723 assertEquals(sf.getEnd(), 21);
724 assertEquals(sf.getDescription(), "G,A");
726 seq = loader.loadVCFContig("contig456");
727 assertEquals(seq.getLength(), 20);
728 assertEquals(seq.getSequenceAsString(), "CCCCCGGGGGTTTTTAAAAA");
729 features = seq.getSequenceFeatures();
730 SequenceFeatures.sortFeatures(features, true);
731 assertEquals(features.size(), 1);
732 sf = features.get(0);
733 assertEquals(sf.getBegin(), 15);
734 assertEquals(sf.getEnd(), 15);
735 assertEquals(sf.getDescription(), "T,C");
738 @Test(groups = "Functional")
739 public void testDecodeSpecialCharacters() throws IOException
741 String encoded = "hello world";
742 String decoded = VCFLoader.decodeSpecialCharacters(encoded);
743 assertSame(encoded, decoded); // no change needed
745 encoded = "ab%3Acd%3Bef%3Dgh%25ij%2Ckl%3A";
746 decoded = VCFLoader.decodeSpecialCharacters(encoded);
747 assertEquals(decoded, "ab:cd;ef=gh%ij,kl:");