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.GeneLoci;
8 import jalview.datamodel.Mapping;
9 import jalview.datamodel.Sequence;
10 import jalview.datamodel.SequenceFeature;
11 import jalview.datamodel.SequenceI;
12 import jalview.gui.AlignFrame;
13 import jalview.io.DataSourceType;
14 import jalview.io.FileLoader;
15 import jalview.io.gff.Gff3Helper;
16 import jalview.io.gff.SequenceOntologyI;
17 import jalview.util.MapList;
20 import java.io.IOException;
21 import java.io.PrintWriter;
22 import java.util.Arrays;
23 import java.util.List;
25 import org.testng.annotations.Test;
27 public class VCFLoaderTest
29 // columns 9717- of gene P30419 from Ensembl (modified)
30 private static final String FASTA = ">ENSG00000136448/1-25 chromosome:GRCh38:17:45051610:45051634:1\n"
31 + "CAAGCTGGCGGACGAGAGTGTGACA\n"
32 // and a 'made up' mini-transcript with two exons
33 + ">ENST00000592782/1-18\n--AGCTGGCG----AGAGTGTGAC-\n";
35 private static final String[] VCF = { "##fileformat=VCFv4.2",
36 "##INFO=<ID=AF,Number=A,Type=Float,Description=\"Allele Frequency, for each ALT allele, in the same order as listed\">",
38 "#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO",
39 // SNP A/T in position 2 of gene sequence (precedes transcript)
40 "17\t45051611\t.\tA\tT\t1666.64\tRF\tAC=15;AF=5.08130e-03",
41 // SNP G/C in position 4 of gene sequence, position 2 of transcript
42 // this is a mixed variant, the insertion G/GA is not transferred
43 "17\t45051613\t.\tG\tGA,C\t1666.64\tRF\tAC=15;AF=3.08130e-03" };
45 @Test(groups = "Functional")
46 public void testLoadVCF() throws IOException
48 AlignmentI al = buildAlignment();
49 VCFLoader loader = new VCFLoader(al);
53 loader.loadVCF(f.getPath(), null);
56 * verify variant feature(s) added to gene
58 List<SequenceFeature> geneFeatures = al.getSequenceAt(0).findFeatures(
60 assertEquals(geneFeatures.size(), 1);
61 SequenceFeature sf = geneFeatures.get(0);
62 assertEquals(sf.getFeatureGroup(), "VCF");
63 assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
64 assertEquals(sf.getScore(), 5.08130e-03, 0.000001f);
65 assertEquals("A,T", sf.getValue(Gff3Helper.ALLELES));
68 * verify variant feature(s) added to transcript
70 List<SequenceFeature> transcriptFeatures = al.getSequenceAt(1)
72 assertEquals(transcriptFeatures.size(), 1);
73 sf = transcriptFeatures.get(0);
74 assertEquals(sf.getFeatureGroup(), "VCF");
75 assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
76 assertEquals(sf.getScore(), 3.08130e-03, 0.000001f);
77 assertEquals("G,C", sf.getValue(Gff3Helper.ALLELES));
80 * verify variant feature(s) computed and added to protein
81 * first codon AGC varies to ACC giving S/T
83 SequenceI peptide = al.getSequenceAt(1)
84 .getDBRefs()[0].getMap().getTo();
85 List<SequenceFeature> proteinFeatures = peptide.findFeatures(1, 6);
86 assertEquals(proteinFeatures.size(), 1);
87 sf = proteinFeatures.get(0);
88 assertEquals(sf.getFeatureGroup(), "VCF");
89 assertEquals(sf.getBegin(), 2);
90 assertEquals(sf.getEnd(), 2);
91 assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
92 assertEquals(sf.getDescription(), "p.Ser1Thr");
95 private File makeVcf() throws IOException
97 File f = File.createTempFile("Test", ".vcf");
99 PrintWriter pw = new PrintWriter(f);
100 for (String vcfLine : VCF)
109 * Make a simple alignment with one 'gene' and one 'transcript'
113 private AlignmentI buildAlignment()
115 AlignFrame af = new FileLoader().LoadFileWaitTillLoaded(FASTA,
116 DataSourceType.PASTE);
119 * map gene sequence to chromosome (normally done when the sequence is fetched
120 * from Ensembl and transcripts computed)
122 AlignmentI alignment = af.getViewport().getAlignment();
123 int[][] to = new int[][] { new int[] { 45051610, 45051634 } };
124 List<int[]> toRanges = Arrays.asList(to);
125 SequenceI gene = alignment.getSequenceAt(0);
126 List<int[]> fromRanges = Arrays.asList(new int[][] { new int[] {
127 gene.getStart(), gene.getEnd() } });
128 ((Sequence) gene).setGeneLoci(new GeneLoci("human", "GRCh38", "17",
129 new MapList(fromRanges, toRanges, 1, 1)));
132 * map 'transcript' to chromosome via 'gene'
133 * transcript/1-18 is gene/3-10,15-24
134 * which is chromosome 45051612-45051619,45051624-45051633
136 to = new int[][] { new int[] { 45051612, 45051619 },
137 new int[] { 45051624, 45051633 } };
138 toRanges = Arrays.asList(to);
139 SequenceI transcript = alignment.getSequenceAt(1);
140 fromRanges = Arrays.asList(new int[][] { new int[] {
141 transcript.getStart(), transcript.getEnd() } });
142 ((Sequence) transcript).setGeneLoci(new GeneLoci("human", "GRCh38",
143 "17", new MapList(fromRanges, toRanges, 1, 1)));
146 * add a protein product as a DBRef on the transcript
148 SequenceI peptide = new Sequence("ENSP001", "SWRECD");
149 MapList mapList = new MapList(new int[] { 1, 18 }, new int[] { 1, 6 },
151 Mapping map = new Mapping(peptide, mapList);
152 DBRefEntry product = new DBRefEntry("", "", "ENSP001", map);
153 transcript.addDBRef(product);
158 @Test(groups = "Functional")
159 public void testLoadVCF_reverseStrand() throws IOException
161 // TODO a test with reverse strand mapping of
162 // gene and transcript to chromosome