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.assertTrue;
8 import jalview.bin.Cache;
9 import jalview.bin.Console;
10 import jalview.datamodel.AlignmentI;
11 import jalview.datamodel.DBRefEntry;
12 import jalview.datamodel.Mapping;
13 import jalview.datamodel.Sequence;
14 import jalview.datamodel.SequenceFeature;
15 import jalview.datamodel.SequenceI;
16 import jalview.datamodel.features.FeatureAttributes;
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.util.MapList;
25 import java.io.IOException;
26 import java.io.PrintWriter;
27 import java.util.List;
30 import org.testng.annotations.BeforeClass;
31 import org.testng.annotations.BeforeTest;
32 import org.testng.annotations.Test;
34 public class VCFLoaderTest
36 private static final float DELTA = 0.00001f;
38 // columns 9717- of gene P30419 from Ensembl (much modified)
39 private static final String FASTA = "" +
41 * forward strand 'gene' and 'transcript' with two exons
43 ">gene1/1-25 chromosome:GRCh38:17:45051610:45051634:1\n"
44 + "CAAGCTGGCGGACGAGAGTGTGACA\n"
45 + ">transcript1/1-18\n--AGCTGGCG----AGAGTGTGAC-\n"
48 * reverse strand gene and transcript (reverse complement alleles!)
50 + ">gene2/1-25 chromosome:GRCh38:17:45051610:45051634:-1\n"
51 + "TGTCACACTCTCGTCCGCCAGCTTG\n" + ">transcript2/1-18\n"
52 + "-GTCACACTCT----CGCCAGCT--\n"
55 * 'gene' on chromosome 5 with two transcripts
57 + ">gene3/1-25 chromosome:GRCh38:5:45051610:45051634:1\n"
58 + "CAAGCTGGCGGACGAGAGTGTGACA\n"
59 + ">transcript3/1-18\n--AGCTGGCG----AGAGTGTGAC-\n"
60 + ">transcript4/1-18\n-----TGG-GGACGAGAGTGTGA-A\n";
62 private static final String[] VCF = { "##fileformat=VCFv4.2",
63 // fields other than AF are ignored when parsing as they have no INFO
65 "##INFO=<ID=AF,Number=A,Type=Float,Description=\"Allele Frequency, for each ALT allele, in the same order as listed\">",
66 "##INFO=<ID=AC_Female,Number=A,Type=Integer,Description=\"Allele count in Female genotypes\"",
67 "##INFO=<ID=AF_AFR,Number=A,Type=Float,Description=\"Allele Frequency among African/African American genotypes\"",
68 "##reference=Homo_sapiens/GRCh38",
69 "#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO",
70 // A/T,C variants in position 2 of gene sequence (precedes transcript)
71 // should create 2 variant features with respective AF values
72 // malformed values for AC_Female and AF_AFR should be ignored
73 "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",
74 // SNP G/C in position 4 of gene sequence, position 2 of transcript
75 // insertion G/GA is transferred to nucleotide but not to peptide
76 "17\t45051613\t.\tG\tGA,C\t1666.65\t.\tAC=15;AF=3.0e-03,2.0e-03",
77 // '.' in INFO field should be ignored
78 "17\t45051615\t.\tG\tC\t1666.66\tRF\tAC=16;AF=." };
80 @BeforeClass(alwaysRun = true)
84 * configure to capture all available VCF and VEP (CSQ) fields
86 Cache.loadProperties("test/jalview/io/testProps.jvprops");
87 Cache.setProperty("VCF_FIELDS", ".*");
88 Cache.setProperty("VEP_FIELDS", ".*");
89 Cache.setProperty("VCF_ASSEMBLY", "GRCh38=GRCh38");
93 @BeforeTest(alwaysRun = true)
94 public void setUpBeforeTest()
97 * clear down feature attributes metadata
99 FeatureAttributes.getInstance().clear();
102 @Test(groups = "Functional")
103 public void testDoLoad() throws IOException
105 AlignmentI al = buildAlignment();
107 File f = makeVcfFile();
108 VCFLoader loader = new VCFLoader(f.getPath());
110 loader.doLoad(al.getSequencesArray(), null);
113 * verify variant feature(s) added to gene
114 * NB alleles at a locus may not be processed, and features added,
115 * in the order in which they appear in the VCF record as method
116 * VariantContext.getAlternateAlleles() does not guarantee order
117 * - order of assertions here matches what we find (is not important)
119 List<SequenceFeature> geneFeatures = al.getSequenceAt(0)
120 .getSequenceFeatures();
121 SequenceFeatures.sortFeatures(geneFeatures, true);
122 assertEquals(geneFeatures.size(), 5);
123 SequenceFeature sf = geneFeatures.get(0);
124 assertEquals(sf.getFeatureGroup(), "VCF");
125 assertEquals(sf.getBegin(), 2);
126 assertEquals(sf.getEnd(), 2);
127 assertEquals(sf.getScore(), 0f);
128 assertEquals(sf.getValue("AF"), "4.0e-03");
129 assertEquals(sf.getValue("AF_AFR"), "2.3e-4");
130 assertEquals(sf.getValue(Gff3Helper.ALLELES), "A,C");
131 assertEquals(sf.getType(), SEQUENCE_VARIANT);
132 assertEquals(sf.getValue("POS"), "45051611");
133 assertEquals(sf.getValue("ID"), "rs384765");
134 assertEquals(sf.getValue("QUAL"), "1666.64");
135 assertEquals(sf.getValue("FILTER"), "RF;XYZ");
136 // malformed integer for AC_Female is ignored (JAL-3375)
137 assertNull(sf.getValue("AC_Female"));
139 sf = geneFeatures.get(1);
140 assertEquals(sf.getFeatureGroup(), "VCF");
141 assertEquals(sf.getBegin(), 2);
142 assertEquals(sf.getEnd(), 2);
143 assertEquals(sf.getType(), SEQUENCE_VARIANT);
144 assertEquals(sf.getScore(), 0f);
145 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 5.0e-03,
147 assertEquals(sf.getValue("AC_Female"), "12");
148 // malformed float for AF_AFR is ignored (JAL-3375)
149 assertNull(sf.getValue("AC_AFR"));
150 assertEquals(sf.getValue(Gff3Helper.ALLELES), "A,T");
152 sf = geneFeatures.get(2);
153 assertEquals(sf.getFeatureGroup(), "VCF");
154 assertEquals(sf.getBegin(), 4);
155 assertEquals(sf.getEnd(), 4);
156 assertEquals(sf.getType(), SEQUENCE_VARIANT);
157 assertEquals(sf.getScore(), 0f);
158 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 2.0e-03,
160 assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,C");
162 sf = geneFeatures.get(3);
163 assertEquals(sf.getFeatureGroup(), "VCF");
164 assertEquals(sf.getBegin(), 4);
165 assertEquals(sf.getEnd(), 4);
166 assertEquals(sf.getType(), SEQUENCE_VARIANT);
167 assertEquals(sf.getScore(), 0f);
168 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 3.0e-03,
170 assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,GA");
171 assertNull(sf.getValue("ID")); // '.' is ignored
172 assertNull(sf.getValue("FILTER")); // '.' is ignored
174 sf = geneFeatures.get(4);
175 assertEquals(sf.getFeatureGroup(), "VCF");
176 assertEquals(sf.getBegin(), 6);
177 assertEquals(sf.getEnd(), 6);
178 assertEquals(sf.getType(), SEQUENCE_VARIANT);
179 assertEquals(sf.getScore(), 0f);
180 // AF=. should not have been captured
181 assertNull(sf.getValue("AF"));
182 assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,C");
185 * verify variant feature(s) added to transcript
187 List<SequenceFeature> transcriptFeatures = al.getSequenceAt(1)
188 .getSequenceFeatures();
189 assertEquals(transcriptFeatures.size(), 3);
190 sf = transcriptFeatures.get(0);
191 assertEquals(sf.getFeatureGroup(), "VCF");
192 assertEquals(sf.getBegin(), 2);
193 assertEquals(sf.getEnd(), 2);
194 assertEquals(sf.getType(), SEQUENCE_VARIANT);
195 assertEquals(sf.getScore(), 0f);
196 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 2.0e-03,
198 assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,C");
199 sf = transcriptFeatures.get(1);
200 assertEquals(sf.getFeatureGroup(), "VCF");
201 assertEquals(sf.getBegin(), 2);
202 assertEquals(sf.getEnd(), 2);
203 assertEquals(sf.getType(), SEQUENCE_VARIANT);
204 assertEquals(sf.getScore(), 0f);
205 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 3.0e-03,
207 assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,GA");
210 * verify SNP variant feature(s) computed and added to protein
211 * first codon AGC varies to ACC giving S/T
213 List<DBRefEntry> dbRefs = al.getSequenceAt(1).getDBRefs();
214 SequenceI peptide = null;
215 for (DBRefEntry dbref : dbRefs)
217 if (dbref.getMap().getMap().getFromRatio() == 3)
219 peptide = dbref.getMap().getTo();
222 List<SequenceFeature> proteinFeatures = peptide.getSequenceFeatures();
225 * JAL-3187 don't precompute protein features, do dynamically instead
227 assertTrue(proteinFeatures.isEmpty());
230 private File makeVcfFile() throws IOException
232 File f = File.createTempFile("Test", ".vcf");
234 PrintWriter pw = new PrintWriter(f);
235 for (String vcfLine : VCF)
244 * Make a simple alignment with one 'gene' and one 'transcript'
248 private AlignmentI buildAlignment()
250 AlignFrame af = new FileLoader().LoadFileWaitTillLoaded(FASTA,
251 DataSourceType.PASTE);
254 * map gene1 sequence to chromosome (normally done when the sequence is fetched
255 * from Ensembl and transcripts computed)
257 AlignmentI alignment = af.getViewport().getAlignment();
258 SequenceI gene1 = alignment.findName("gene1");
259 int[] to = new int[] { 45051610, 45051634 };
260 int[] from = new int[] { gene1.getStart(), gene1.getEnd() };
261 gene1.setGeneLoci("homo_sapiens", "GRCh38", "17",
262 new MapList(from, to, 1, 1));
265 * map 'transcript1' to chromosome via 'gene1'
266 * transcript1/1-18 is gene1/3-10,15-24
267 * which is chromosome 45051612-45051619,45051624-45051633
269 to = new int[] { 45051612, 45051619, 45051624, 45051633 };
270 SequenceI transcript1 = alignment.findName("transcript1");
271 from = new int[] { transcript1.getStart(), transcript1.getEnd() };
272 transcript1.setGeneLoci("homo_sapiens", "GRCh38", "17",
273 new MapList(from, to, 1, 1));
276 * map gene2 to chromosome reverse strand
278 SequenceI gene2 = alignment.findName("gene2");
279 to = new int[] { 45051634, 45051610 };
280 from = new int[] { gene2.getStart(), gene2.getEnd() };
281 gene2.setGeneLoci("homo_sapiens", "GRCh38", "17",
282 new MapList(from, to, 1, 1));
285 * map 'transcript2' to chromosome via 'gene2'
286 * transcript2/1-18 is gene2/2-11,16-23
287 * which is chromosome 45051633-45051624,45051619-45051612
289 to = new int[] { 45051633, 45051624, 45051619, 45051612 };
290 SequenceI transcript2 = alignment.findName("transcript2");
291 from = new int[] { transcript2.getStart(), transcript2.getEnd() };
292 transcript2.setGeneLoci("homo_sapiens", "GRCh38", "17",
293 new MapList(from, to, 1, 1));
296 * add a protein product as a DBRef on transcript1
298 SequenceI peptide1 = new Sequence("ENSP001", "SWRECD");
299 MapList mapList = new MapList(new int[] { 1, 18 }, new int[] { 1, 6 },
301 Mapping map = new Mapping(peptide1, mapList);
302 DBRefEntry product = new DBRefEntry("", "", "ENSP001", map);
303 transcript1.addDBRef(product);
306 * add a protein product as a DBRef on transcript2
308 SequenceI peptide2 = new Sequence("ENSP002", "VTLSPA");
309 mapList = new MapList(new int[] { 1, 18 }, new int[] { 1, 6 }, 3, 1);
310 map = new Mapping(peptide2, mapList);
311 product = new DBRefEntry("", "", "ENSP002", map);
312 transcript2.addDBRef(product);
315 * map gene3 to chromosome
317 SequenceI gene3 = alignment.findName("gene3");
318 to = new int[] { 45051610, 45051634 };
319 from = new int[] { gene3.getStart(), gene3.getEnd() };
320 gene3.setGeneLoci("homo_sapiens", "GRCh38", "5",
321 new MapList(from, to, 1, 1));
324 * map 'transcript3' to chromosome
326 SequenceI transcript3 = alignment.findName("transcript3");
327 to = new int[] { 45051612, 45051619, 45051624, 45051633 };
328 from = new int[] { transcript3.getStart(), transcript3.getEnd() };
329 transcript3.setGeneLoci("homo_sapiens", "GRCh38", "5",
330 new MapList(from, to, 1, 1));
333 * map 'transcript4' to chromosome
335 SequenceI transcript4 = alignment.findName("transcript4");
336 to = new int[] { 45051615, 45051617, 45051619, 45051632, 45051634,
338 from = new int[] { transcript4.getStart(), transcript4.getEnd() };
339 transcript4.setGeneLoci("homo_sapiens", "GRCh38", "5",
340 new MapList(from, to, 1, 1));
343 * add a protein product as a DBRef on transcript3
345 SequenceI peptide3 = new Sequence("ENSP003", "SWRECD");
346 mapList = new MapList(new int[] { 1, 18 }, new int[] { 1, 6 }, 3, 1);
347 map = new Mapping(peptide3, mapList);
348 product = new DBRefEntry("", "", "ENSP003", map);
349 transcript3.addDBRef(product);
355 * Test with 'gene' and 'transcript' mapped to the reverse strand of the
356 * chromosome. The VCF variant positions (in forward coordinates) should get
357 * correctly located on sequence positions.
359 * @throws IOException
361 @Test(groups = "Functional")
362 public void testDoLoad_reverseStrand() throws IOException
364 AlignmentI al = buildAlignment();
366 File f = makeVcfFile();
368 VCFLoader loader = new VCFLoader(f.getPath());
370 loader.doLoad(al.getSequencesArray(), null);
373 * verify variant feature(s) added to gene2
374 * gene2/1-25 maps to chromosome 45051634- reverse strand
376 List<SequenceFeature> geneFeatures = al.getSequenceAt(2)
377 .getSequenceFeatures();
378 SequenceFeatures.sortFeatures(geneFeatures, true);
379 assertEquals(geneFeatures.size(), 5);
383 * insertion G/GA at 45051613 maps to an insertion at
384 * the preceding position (21) on reverse strand gene
385 * reference: CAAGC -> GCTTG/21-25
386 * genomic variant: CAAGAC (G/GA)
387 * gene variant: GTCTTG (G/GT at 21)
389 sf = geneFeatures.get(1);
390 assertEquals(sf.getFeatureGroup(), "VCF");
391 assertEquals(sf.getBegin(), 21);
392 assertEquals(sf.getEnd(), 21);
393 assertEquals(sf.getType(), SEQUENCE_VARIANT);
394 assertEquals(sf.getScore(), 0f);
395 assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,GT");
396 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 3.0e-03,
400 * variant G/C at 45051613 maps to C/G at gene position 22
402 sf = geneFeatures.get(2);
403 assertEquals(sf.getFeatureGroup(), "VCF");
404 assertEquals(sf.getBegin(), 22);
405 assertEquals(sf.getEnd(), 22);
406 assertEquals(sf.getType(), SEQUENCE_VARIANT);
407 assertEquals(sf.getScore(), 0f);
408 assertEquals(sf.getValue(Gff3Helper.ALLELES), "C,G");
409 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 2.0e-03,
413 * variant A/C at 45051611 maps to T/G at gene position 24
415 sf = geneFeatures.get(3);
416 assertEquals(sf.getFeatureGroup(), "VCF");
417 assertEquals(sf.getBegin(), 24);
418 assertEquals(sf.getEnd(), 24);
419 assertEquals(sf.getType(), SEQUENCE_VARIANT);
420 assertEquals(sf.getScore(), 0f);
421 assertEquals(sf.getValue(Gff3Helper.ALLELES), "T,G");
422 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 4.0e-03,
426 * variant A/T at 45051611 maps to T/A at gene position 24
428 sf = geneFeatures.get(4);
429 assertEquals(sf.getFeatureGroup(), "VCF");
430 assertEquals(sf.getBegin(), 24);
431 assertEquals(sf.getEnd(), 24);
432 assertEquals(sf.getType(), SEQUENCE_VARIANT);
433 assertEquals(sf.getScore(), 0f);
434 assertEquals(sf.getValue(Gff3Helper.ALLELES), "T,A");
435 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 5.0e-03,
439 * verify 3 variant features added to transcript2
441 List<SequenceFeature> transcriptFeatures = al.getSequenceAt(3)
442 .getSequenceFeatures();
443 assertEquals(transcriptFeatures.size(), 3);
446 * insertion G/GT at position 21 of gene maps to position 16 of transcript
448 sf = transcriptFeatures.get(1);
449 assertEquals(sf.getFeatureGroup(), "VCF");
450 assertEquals(sf.getBegin(), 16);
451 assertEquals(sf.getEnd(), 16);
452 assertEquals(sf.getType(), SEQUENCE_VARIANT);
453 assertEquals(sf.getScore(), 0f);
454 assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,GT");
455 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 3.0e-03,
459 * SNP C/G at position 22 of gene maps to position 17 of transcript
461 sf = transcriptFeatures.get(2);
462 assertEquals(sf.getFeatureGroup(), "VCF");
463 assertEquals(sf.getBegin(), 17);
464 assertEquals(sf.getEnd(), 17);
465 assertEquals(sf.getType(), SEQUENCE_VARIANT);
466 assertEquals(sf.getScore(), 0f);
467 assertEquals(sf.getValue(Gff3Helper.ALLELES), "C,G");
468 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 2.0e-03,
472 * verify variant feature(s) computed and added to protein
473 * last codon GCT varies to GGT giving A/G in the last peptide position
475 List<DBRefEntry> dbRefs = al.getSequenceAt(3).getDBRefs();
476 SequenceI peptide = null;
477 for (DBRefEntry dbref : dbRefs)
479 if (dbref.getMap().getMap().getFromRatio() == 3)
481 peptide = dbref.getMap().getTo();
484 List<SequenceFeature> proteinFeatures = peptide.getSequenceFeatures();
487 * JAL-3187 don't precompute protein features, do dynamically instead
489 assertTrue(proteinFeatures.isEmpty());
493 * Tests that if VEP consequence (CSQ) data is present in the VCF data, then
494 * it is added to the variant feature, but restricted where possible to the
495 * consequences for a specific transcript
497 * @throws IOException
499 @Test(groups = "Functional")
500 public void testDoLoad_vepCsq() throws IOException
502 AlignmentI al = buildAlignment();
504 VCFLoader loader = new VCFLoader("test/jalview/io/vcf/testVcf.vcf");
507 * VCF data file with variants at gene3 positions
512 * 17 A/AC (insertion), A/G
514 loader.doLoad(al.getSequencesArray(), null);
517 * verify variant feature(s) added to gene3
519 List<SequenceFeature> geneFeatures = al.findName("gene3")
520 .getSequenceFeatures();
521 SequenceFeatures.sortFeatures(geneFeatures, true);
522 assertEquals(geneFeatures.size(), 7);
523 SequenceFeature sf = geneFeatures.get(0);
524 assertEquals(sf.getBegin(), 1);
525 assertEquals(sf.getEnd(), 1);
526 assertEquals(sf.getScore(), 0f);
527 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.1f, DELTA);
528 assertEquals(sf.getValue("alleles"), "C,A");
529 // gene features include Consequence for all transcripts
530 Map map = (Map) sf.getValue("CSQ");
531 assertEquals(map.size(), 9);
532 assertEquals(map.get("PolyPhen"), "Bad");
534 sf = geneFeatures.get(1);
535 assertEquals(sf.getBegin(), 5);
536 assertEquals(sf.getEnd(), 5);
537 assertEquals(sf.getScore(), 0f);
538 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.2f, DELTA);
539 assertEquals(sf.getValue("alleles"), "C,T");
540 map = (Map) sf.getValue("CSQ");
541 assertEquals(map.size(), 9);
542 assertEquals(map.get("PolyPhen"), "Bad;;"); // %3B%3B decoded
544 sf = geneFeatures.get(2);
545 assertEquals(sf.getBegin(), 9);
546 assertEquals(sf.getEnd(), 11); // deletion over 3 positions
547 assertEquals(sf.getScore(), 0f);
548 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.3f, DELTA);
549 assertEquals(sf.getValue("alleles"), "CGG,C");
550 map = (Map) sf.getValue("CSQ");
551 assertEquals(map.size(), 9);
553 sf = geneFeatures.get(3);
554 assertEquals(sf.getBegin(), 13);
555 assertEquals(sf.getEnd(), 13);
556 assertEquals(sf.getScore(), 0f);
557 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.5f, DELTA);
558 assertEquals(sf.getValue("alleles"), "C,T");
559 map = (Map) sf.getValue("CSQ");
560 assertEquals(map.size(), 9);
562 sf = geneFeatures.get(4);
563 assertEquals(sf.getBegin(), 13);
564 assertEquals(sf.getEnd(), 13);
565 assertEquals(sf.getScore(), 0f);
566 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.4f, DELTA);
567 assertEquals(sf.getValue("alleles"), "C,G");
568 map = (Map) sf.getValue("CSQ");
569 assertEquals(map.size(), 9);
571 sf = geneFeatures.get(5);
572 assertEquals(sf.getBegin(), 17);
573 assertEquals(sf.getEnd(), 17);
574 assertEquals(sf.getScore(), 0f);
575 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.7f, DELTA);
576 assertEquals(sf.getValue("alleles"), "A,G");
577 map = (Map) sf.getValue("CSQ");
578 assertEquals(map.size(), 9);
580 sf = geneFeatures.get(6);
581 assertEquals(sf.getBegin(), 17);
582 assertEquals(sf.getEnd(), 17); // insertion
583 assertEquals(sf.getScore(), 0f);
584 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.6f, DELTA);
585 assertEquals(sf.getValue("alleles"), "A,AC");
586 map = (Map) sf.getValue("CSQ");
587 assertEquals(map.size(), 9);
590 * verify variant feature(s) added to transcript3
591 * at columns 5 (1), 17 (2), positions 3, 11
592 * note the deletion at columns 9-11 is not transferred since col 11
593 * has no mapping to transcript 3
595 List<SequenceFeature> transcriptFeatures = al.findName("transcript3")
596 .getSequenceFeatures();
597 SequenceFeatures.sortFeatures(transcriptFeatures, true);
598 assertEquals(transcriptFeatures.size(), 3);
599 sf = transcriptFeatures.get(0);
600 assertEquals(sf.getBegin(), 3);
601 assertEquals(sf.getEnd(), 3);
602 assertEquals(sf.getScore(), 0f);
603 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.2f, DELTA);
604 assertEquals(sf.getValue("alleles"), "C,T");
605 // transcript features only have Consequence for that transcripts
606 map = (Map) sf.getValue("CSQ");
607 assertEquals(map.size(), 9);
608 assertEquals(sf.getValueAsString("CSQ", "Feature"), "transcript3");
610 sf = transcriptFeatures.get(1);
611 assertEquals(sf.getBegin(), 11);
612 assertEquals(sf.getEnd(), 11);
613 assertEquals(sf.getScore(), 0f);
614 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.7f, DELTA);
615 assertEquals(sf.getValue("alleles"), "A,G");
616 assertEquals(map.size(), 9);
617 assertEquals(sf.getValueAsString("CSQ", "Feature"), "transcript3");
619 sf = transcriptFeatures.get(2);
620 assertEquals(sf.getBegin(), 11);
621 assertEquals(sf.getEnd(), 11);
622 assertEquals(sf.getScore(), 0f);
623 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.6f, DELTA);
624 assertEquals(sf.getValue("alleles"), "A,AC");
625 assertEquals(map.size(), 9);
626 assertEquals(sf.getValueAsString("CSQ", "Feature"), "transcript3");
629 * verify variants computed on protein product for transcript3
631 * codon variants are AGC/AGT position 1 which is synonymous
632 * and GAG/GGG which is E/G in position 4
633 * the insertion variant is not transferred to the peptide
635 List<DBRefEntry> dbRefs = al.findName("transcript3").getDBRefs();
636 SequenceI peptide = null;
637 for (DBRefEntry dbref : dbRefs)
639 if (dbref.getMap().getMap().getFromRatio() == 3)
641 peptide = dbref.getMap().getTo();
644 List<SequenceFeature> proteinFeatures = peptide.getSequenceFeatures();
646 * JAL-3187 don't precompute protein features, do dynamically instead
648 assertTrue(proteinFeatures.isEmpty());
649 // SequenceFeatures.sortFeatures(proteinFeatures, true);
650 // assertEquals(proteinFeatures.size(), 2);
651 // sf = proteinFeatures.get(0);
652 // assertEquals(sf.getFeatureGroup(), "VCF");
653 // assertEquals(sf.getBegin(), 1);
654 // assertEquals(sf.getEnd(), 1);
655 // assertEquals(sf.getType(), SequenceOntologyI.SYNONYMOUS_VARIANT);
656 // assertEquals(sf.getDescription(), "agC/agT");
657 // sf = proteinFeatures.get(1);
658 // assertEquals(sf.getFeatureGroup(), "VCF");
659 // assertEquals(sf.getBegin(), 4);
660 // assertEquals(sf.getEnd(), 4);
661 // assertEquals(sf.getType(), SequenceOntologyI.NONSYNONYMOUS_VARIANT);
662 // assertEquals(sf.getDescription(), "p.Glu4Gly");
665 * verify variant feature(s) added to transcript4
666 * at columns 13 (2) and 17 (2), positions 7 and 11
668 transcriptFeatures = al.findName("transcript4").getSequenceFeatures();
669 SequenceFeatures.sortFeatures(transcriptFeatures, true);
670 assertEquals(transcriptFeatures.size(), 4);
671 sf = transcriptFeatures.get(0);
672 assertEquals(sf.getBegin(), 7);
673 assertEquals(sf.getEnd(), 7);
674 assertEquals(sf.getScore(), 0f);
675 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.5f, DELTA);
676 assertEquals(sf.getValue("alleles"), "C,T");
677 assertEquals(map.size(), 9);
678 assertEquals(sf.getValueAsString("CSQ", "Feature"), "transcript4");
680 sf = transcriptFeatures.get(1);
681 assertEquals(sf.getBegin(), 7);
682 assertEquals(sf.getEnd(), 7);
683 assertEquals(sf.getScore(), 0f);
684 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.4f, DELTA);
685 assertEquals(sf.getValue("alleles"), "C,G");
686 assertEquals(map.size(), 9);
687 assertEquals(sf.getValueAsString("CSQ", "Feature"), "transcript4");
689 sf = transcriptFeatures.get(2);
690 assertEquals(sf.getBegin(), 11);
691 assertEquals(sf.getEnd(), 11);
692 assertEquals(sf.getScore(), 0f);
693 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.7f, DELTA);
694 assertEquals(sf.getValue("alleles"), "A,G");
695 assertEquals(map.size(), 9);
696 assertEquals(sf.getValueAsString("CSQ", "Feature"), "transcript4");
698 sf = transcriptFeatures.get(3);
699 assertEquals(sf.getBegin(), 11);
700 assertEquals(sf.getEnd(), 11);
701 assertEquals(sf.getScore(), 0f);
702 assertEquals(Float.parseFloat((String) sf.getValue("AF")), 0.6f, DELTA);
703 assertEquals(sf.getValue("alleles"), "A,AC");
704 assertEquals(map.size(), 9);
705 assertEquals(sf.getValueAsString("CSQ", "Feature"), "transcript4");
709 * A test that demonstrates loading a contig sequence from an indexed sequence
710 * database which is the reference for a VCF file
712 * @throws IOException
714 @Test(groups = "Functional")
715 public void testLoadVCFContig() throws IOException
717 VCFLoader loader = new VCFLoader("test/jalview/io/vcf/testVcf2.vcf");
719 SequenceI seq = loader.loadVCFContig("contig123");
720 assertEquals(seq.getLength(), 15);
721 assertEquals(seq.getSequenceAsString(), "AAAAACCCCCGGGGG");
722 List<SequenceFeature> features = seq.getSequenceFeatures();
723 SequenceFeatures.sortFeatures(features, true);
724 assertEquals(features.size(), 2);
725 SequenceFeature sf = features.get(0);
726 assertEquals(sf.getBegin(), 8);
727 assertEquals(sf.getEnd(), 8);
728 assertEquals(sf.getDescription(), "C,A");
729 sf = features.get(1);
730 assertEquals(sf.getBegin(), 12);
731 assertEquals(sf.getEnd(), 12);
732 assertEquals(sf.getDescription(), "G,T");
734 seq = loader.loadVCFContig("contig789");
735 assertEquals(seq.getLength(), 25);
736 assertEquals(seq.getSequenceAsString(), "GGGGGTTTTTAAAAACCCCCGGGGG");
737 features = seq.getSequenceFeatures();
738 SequenceFeatures.sortFeatures(features, true);
739 assertEquals(features.size(), 2);
740 sf = features.get(0);
741 assertEquals(sf.getBegin(), 2);
742 assertEquals(sf.getEnd(), 2);
743 assertEquals(sf.getDescription(), "G,T");
744 sf = features.get(1);
745 assertEquals(sf.getBegin(), 21);
746 assertEquals(sf.getEnd(), 21);
747 assertEquals(sf.getDescription(), "G,A");
749 seq = loader.loadVCFContig("contig456");
750 assertEquals(seq.getLength(), 20);
751 assertEquals(seq.getSequenceAsString(), "CCCCCGGGGGTTTTTAAAAA");
752 features = seq.getSequenceFeatures();
753 SequenceFeatures.sortFeatures(features, true);
754 assertEquals(features.size(), 1);
755 sf = features.get(0);
756 assertEquals(sf.getBegin(), 15);
757 assertEquals(sf.getEnd(), 15);
758 assertEquals(sf.getDescription(), "T,C");