1 package jalview.io.vcf;
3 import static org.testng.Assert.assertEquals;
5 import jalview.datamodel.AlignmentI;
6 import jalview.datamodel.DBRefEntry;
7 import jalview.datamodel.Mapping;
8 import jalview.datamodel.Sequence;
9 import jalview.datamodel.SequenceFeature;
10 import jalview.datamodel.SequenceI;
11 import jalview.gui.AlignFrame;
12 import jalview.io.DataSourceType;
13 import jalview.io.FileLoader;
14 import jalview.io.gff.Gff3Helper;
15 import jalview.io.gff.SequenceOntologyI;
16 import jalview.util.MapList;
19 import java.io.IOException;
20 import java.io.PrintWriter;
21 import java.util.List;
23 import org.testng.annotations.Test;
25 public class VCFLoaderTest
27 // columns 9717- of gene P30419 from Ensembl (modified)
28 private static final String FASTA =
29 // forward strand 'gene'
30 ">gene1/1-25 chromosome:GRCh38:17:45051610:45051634:1\n"
31 + "CAAGCTGGCGGACGAGAGTGTGACA\n"
32 // and a 'made up' mini-transcript with two exons
33 + ">transcript1/1-18\n--AGCTGGCG----AGAGTGTGAC-\n"
35 // 'reverse strand' gene (reverse complement)
36 ">gene2/1-25 chromosome:GRCh38:17:45051610:45051634:-1\n"
37 + "TGTCACACTCTCGTCCGCCAGCTTG\n"
38 // and its 'transcript'
39 + ">transcript2/1-18\n"
40 + "-GTCACACTCT----CGCCAGCT--\n";
42 private static final String[] VCF = { "##fileformat=VCFv4.2",
43 "##INFO=<ID=AF,Number=A,Type=Float,Description=\"Allele Frequency, for each ALT allele, in the same order as listed\">",
45 "#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO",
46 // SNP A/T in position 2 of gene sequence (precedes transcript)
47 "17\t45051611\t.\tA\tT\t1666.64\tRF\tAC=15;AF=5.08130e-03",
48 // SNP G/C in position 4 of gene sequence, position 2 of transcript
49 // this is a mixed variant, the insertion G/GA is not transferred
50 "17\t45051613\t.\tG\tGA,C\t1666.64\tRF\tAC=15;AF=3.08130e-03" };
52 @Test(groups = "Functional")
53 public void testLoadVCF() throws IOException
55 AlignmentI al = buildAlignment();
56 VCFLoader loader = new VCFLoader(al);
60 loader.loadVCF(f.getPath(), null);
63 * verify variant feature(s) added to gene
65 List<SequenceFeature> geneFeatures = al.getSequenceAt(0)
66 .getSequenceFeatures();
67 assertEquals(geneFeatures.size(), 2);
68 SequenceFeature sf = geneFeatures.get(0);
69 assertEquals(sf.getFeatureGroup(), "VCF");
70 assertEquals(sf.getBegin(), 2);
71 assertEquals(sf.getEnd(), 2);
72 assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
73 assertEquals(sf.getScore(), 5.08130e-03, 0.000001f);
74 assertEquals(sf.getValue(Gff3Helper.ALLELES), "A,T");
76 sf = geneFeatures.get(1);
77 assertEquals(sf.getFeatureGroup(), "VCF");
78 assertEquals(sf.getBegin(), 4);
79 assertEquals(sf.getEnd(), 4);
80 assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
81 assertEquals(sf.getScore(), 3.08130e-03, 0.000001f);
82 assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,C");
85 * verify variant feature(s) added to transcript
87 List<SequenceFeature> transcriptFeatures = al.getSequenceAt(1)
88 .getSequenceFeatures();
89 assertEquals(transcriptFeatures.size(), 1);
90 sf = transcriptFeatures.get(0);
91 assertEquals(sf.getFeatureGroup(), "VCF");
92 assertEquals(sf.getBegin(), 2);
93 assertEquals(sf.getEnd(), 2);
94 assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
95 assertEquals(sf.getScore(), 3.08130e-03, 0.000001f);
96 assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,C");
99 * verify variant feature(s) computed and added to protein
100 * first codon AGC varies to ACC giving S/T
102 DBRefEntry[] dbRefs = al.getSequenceAt(1).getDBRefs();
103 SequenceI peptide = null;
104 for (DBRefEntry dbref : dbRefs)
106 if (dbref.getMap().getMap().getFromRatio() == 3)
108 peptide = dbref.getMap().getTo();
111 List<SequenceFeature> proteinFeatures = peptide.getSequenceFeatures();
112 assertEquals(proteinFeatures.size(), 1);
113 sf = proteinFeatures.get(0);
114 assertEquals(sf.getFeatureGroup(), "VCF");
115 assertEquals(sf.getBegin(), 1);
116 assertEquals(sf.getEnd(), 1);
117 assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
118 assertEquals(sf.getDescription(), "p.Ser1Thr");
121 private File makeVcf() throws IOException
123 File f = File.createTempFile("Test", ".vcf");
125 PrintWriter pw = new PrintWriter(f);
126 for (String vcfLine : VCF)
135 * Make a simple alignment with one 'gene' and one 'transcript'
139 private AlignmentI buildAlignment()
141 AlignFrame af = new FileLoader().LoadFileWaitTillLoaded(FASTA,
142 DataSourceType.PASTE);
145 * map gene1 sequence to chromosome (normally done when the sequence is fetched
146 * from Ensembl and transcripts computed)
148 AlignmentI alignment = af.getViewport().getAlignment();
149 SequenceI gene1 = alignment.getSequenceAt(0);
150 int[] to = new int[] { 45051610, 45051634 };
151 int[] from = new int[] { gene1.getStart(), gene1.getEnd() };
152 gene1.setGeneLoci("human", "GRCh38", "17", new MapList(from, to, 1, 1));
155 * map 'transcript1' to chromosome via 'gene1'
156 * transcript1/1-18 is gene1/3-10,15-24
157 * which is chromosome 45051612-45051619,45051624-45051633
159 to = new int[] { 45051612, 45051619, 45051624, 45051633 };
160 SequenceI transcript1 = alignment.getSequenceAt(1);
161 from = new int[] { transcript1.getStart(), transcript1.getEnd() };
162 transcript1.setGeneLoci("human", "GRCh38", "17", new MapList(from, to,
166 * map gene2 to chromosome reverse strand
168 SequenceI gene2 = alignment.getSequenceAt(2);
169 to = new int[] { 45051634, 45051610 };
170 from = new int[] { gene2.getStart(), gene2.getEnd() };
171 gene2.setGeneLoci("human", "GRCh38", "17", new MapList(from, to, 1, 1));
174 * map 'transcript2' to chromosome via 'gene2'
175 * transcript2/1-18 is gene2/2-11,16-23
176 * which is chromosome 45051633-45051624,45051619-45051612
178 to = new int[] { 45051633, 45051624, 45051619, 45051612 };
179 SequenceI transcript2 = alignment.getSequenceAt(3);
180 from = new int[] { transcript2.getStart(), transcript2.getEnd() };
181 transcript2.setGeneLoci("human", "GRCh38", "17", new MapList(from, to,
185 * add a protein product as a DBRef on transcript1
187 SequenceI peptide1 = new Sequence("ENSP001", "SWRECD");
188 MapList mapList = new MapList(new int[] { 1, 18 }, new int[] { 1, 6 },
190 Mapping map = new Mapping(peptide1, mapList);
191 DBRefEntry product = new DBRefEntry("", "", "ENSP001", map);
192 transcript1.addDBRef(product);
195 * add a protein product as a DBRef on transcript2
197 SequenceI peptide2 = new Sequence("ENSP002", "VTLSPA");
198 mapList = new MapList(new int[] { 1, 18 }, new int[] { 1, 6 }, 3, 1);
199 map = new Mapping(peptide2, mapList);
200 product = new DBRefEntry("", "", "ENSP002", map);
201 transcript2.addDBRef(product);
207 * Test with 'gene' and 'transcript' mapped to the reverse strand of the
208 * chromosome. The VCF variant positions (in forward coordinates) should get
209 * correctly located on sequence positions.
211 * @throws IOException
213 @Test(groups = "Functional")
214 public void testLoadVCF_reverseStrand() throws IOException
216 AlignmentI al = buildAlignment();
218 VCFLoader loader = new VCFLoader(al);
222 loader.loadVCF(f.getPath(), null);
225 * verify variant feature(s) added to gene2
226 * gene/1-25 maps to chromosome 45051634- reverse strand
227 * variants A/T at 45051611 and G/C at 45051613 map to
228 * T/A and C/G at gene positions 24 and 22 respectively
230 List<SequenceFeature> geneFeatures = al.getSequenceAt(2)
231 .getSequenceFeatures();
232 assertEquals(geneFeatures.size(), 2);
233 SequenceFeature sf = geneFeatures.get(0);
234 assertEquals(sf.getFeatureGroup(), "VCF");
235 assertEquals(sf.getBegin(), 22);
236 assertEquals(sf.getEnd(), 22);
237 assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
238 assertEquals(sf.getScore(), 3.08130e-03, 0.000001f);
239 assertEquals("C,G", sf.getValue(Gff3Helper.ALLELES));
241 sf = geneFeatures.get(1);
242 assertEquals(sf.getFeatureGroup(), "VCF");
243 assertEquals(sf.getBegin(), 24);
244 assertEquals(sf.getEnd(), 24);
245 assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
246 assertEquals(sf.getScore(), 5.08130e-03, 0.000001f);
247 assertEquals("T,A", sf.getValue(Gff3Helper.ALLELES));
250 * verify variant feature(s) added to transcript2
251 * variant C/G at position 22 of gene overlaps and maps to
252 * position 17 of transcript
254 List<SequenceFeature> transcriptFeatures = al.getSequenceAt(3)
255 .getSequenceFeatures();
256 assertEquals(transcriptFeatures.size(), 1);
257 sf = transcriptFeatures.get(0);
258 assertEquals(sf.getFeatureGroup(), "VCF");
259 assertEquals(sf.getBegin(), 17);
260 assertEquals(sf.getEnd(), 17);
261 assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
262 assertEquals(sf.getScore(), 3.08130e-03, 0.000001f);
263 assertEquals("C,G", sf.getValue(Gff3Helper.ALLELES));
266 * verify variant feature(s) computed and added to protein
267 * last codon GCT varies to GGT giving A/G in the last peptide position
269 DBRefEntry[] dbRefs = al.getSequenceAt(3).getDBRefs();
270 SequenceI peptide = null;
271 for (DBRefEntry dbref : dbRefs)
273 if (dbref.getMap().getMap().getFromRatio() == 3)
275 peptide = dbref.getMap().getTo();
278 List<SequenceFeature> proteinFeatures = peptide.getSequenceFeatures();
279 assertEquals(proteinFeatures.size(), 1);
280 sf = proteinFeatures.get(0);
281 assertEquals(sf.getFeatureGroup(), "VCF");
282 assertEquals(sf.getBegin(), 6);
283 assertEquals(sf.getEnd(), 6);
284 assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
285 assertEquals(sf.getDescription(), "p.Ala6Gly");