package jalview.io.vcf;
+import static jalview.io.gff.SequenceOntologyI.SEQUENCE_VARIANT;
import static org.testng.Assert.assertEquals;
-import static org.testng.Assert.assertSame;
+import static org.testng.Assert.assertNull;
import static org.testng.Assert.assertTrue;
import jalview.bin.Cache;
import jalview.datamodel.Sequence;
import jalview.datamodel.SequenceFeature;
import jalview.datamodel.SequenceI;
+import jalview.datamodel.features.FeatureAttributes;
import jalview.datamodel.features.SequenceFeatures;
import jalview.gui.AlignFrame;
import jalview.io.DataSourceType;
import jalview.io.FileLoader;
import jalview.io.gff.Gff3Helper;
-import jalview.io.gff.SequenceOntologyI;
import jalview.util.MapList;
import java.io.File;
import java.util.Map;
import org.testng.annotations.BeforeClass;
+import org.testng.annotations.BeforeTest;
import org.testng.annotations.Test;
public class VCFLoaderTest
+ ">transcript4/1-18\n-----TGG-GGACGAGAGTGTGA-A\n";
private static final String[] VCF = { "##fileformat=VCFv4.2",
+ // fields other than AF are ignored when parsing as they have no INFO definition
"##INFO=<ID=AF,Number=A,Type=Float,Description=\"Allele Frequency, for each ALT allele, in the same order as listed\">",
+ "##INFO=<ID=AC_Female,Number=A,Type=Integer,Description=\"Allele count in Female genotypes\"",
+ "##INFO=<ID=AF_AFR,Number=A,Type=Float,Description=\"Allele Frequency among African/African American genotypes\"",
"##reference=Homo_sapiens/GRCh38",
"#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO",
// A/T,C variants in position 2 of gene sequence (precedes transcript)
- // should create 2 variant features with respective scores
- "17\t45051611\t.\tA\tT,C\t1666.64\tRF\tAC=15;AF=5.0e-03,4.0e-03",
+ // should create 2 variant features with respective AF values
+ // malformed values for AC_Female and AF_AFR should be ignored
+ "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",
// SNP G/C in position 4 of gene sequence, position 2 of transcript
// insertion G/GA is transferred to nucleotide but not to peptide
- "17\t45051613\t.\tG\tGA,C\t1666.64\tRF\tAC=15;AF=3.0e-03,2.0e-03" };
+ "17\t45051613\t.\tG\tGA,C\t1666.65\t.\tAC=15;AF=3.0e-03,2.0e-03",
+ // '.' in INFO field should be ignored
+ "17\t45051615\t.\tG\tC\t1666.66\tRF\tAC=16;AF=." };
@BeforeClass(alwaysRun = true)
public void setUp()
Cache.initLogger();
}
+ @BeforeTest(alwaysRun = true)
+ public void setUpBeforeTest()
+ {
+ /*
+ * clear down feature attributes metadata
+ */
+ FeatureAttributes.getInstance().clear();
+ }
+
@Test(groups = "Functional")
public void testDoLoad() throws IOException
{
AlignmentI al = buildAlignment();
- File f = makeVcf();
+ File f = makeVcfFile();
VCFLoader loader = new VCFLoader(f.getPath());
loader.doLoad(al.getSequencesArray(), null);
List<SequenceFeature> geneFeatures = al.getSequenceAt(0)
.getSequenceFeatures();
SequenceFeatures.sortFeatures(geneFeatures, true);
- assertEquals(geneFeatures.size(), 4);
+ assertEquals(geneFeatures.size(), 5);
SequenceFeature sf = geneFeatures.get(0);
assertEquals(sf.getFeatureGroup(), "VCF");
assertEquals(sf.getBegin(), 2);
assertEquals(sf.getEnd(), 2);
assertEquals(sf.getScore(), 0f);
- assertEquals(Float.parseFloat((String) sf.getValue("AF")), 4.0e-03,
- DELTA);
+ assertEquals(sf.getValue("AF"), "4.0e-03");
+ assertEquals(sf.getValue("AF_AFR"), "2.3e-4");
assertEquals(sf.getValue(Gff3Helper.ALLELES), "A,C");
- assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
+ assertEquals(sf.getType(), SEQUENCE_VARIANT);
+ assertEquals(sf.getValue("POS"), "45051611");
+ assertEquals(sf.getValue("ID"), "rs384765");
+ assertEquals(sf.getValue("QUAL"), "1666.64");
+ assertEquals(sf.getValue("FILTER"), "RF;XYZ");
+ // malformed integer for AC_Female is ignored (JAL-3375)
+ assertNull(sf.getValue("AC_Female"));
+
sf = geneFeatures.get(1);
assertEquals(sf.getFeatureGroup(), "VCF");
assertEquals(sf.getBegin(), 2);
assertEquals(sf.getEnd(), 2);
- assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
+ assertEquals(sf.getType(), SEQUENCE_VARIANT);
assertEquals(sf.getScore(), 0f);
assertEquals(Float.parseFloat((String) sf.getValue("AF")), 5.0e-03,
DELTA);
+ assertEquals(sf.getValue("AC_Female"), "12");
+ // malformed float for AF_AFR is ignored (JAL-3375)
+ assertNull(sf.getValue("AC_AFR"));
assertEquals(sf.getValue(Gff3Helper.ALLELES), "A,T");
sf = geneFeatures.get(2);
assertEquals(sf.getFeatureGroup(), "VCF");
assertEquals(sf.getBegin(), 4);
assertEquals(sf.getEnd(), 4);
- assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
+ assertEquals(sf.getType(), SEQUENCE_VARIANT);
assertEquals(sf.getScore(), 0f);
assertEquals(Float.parseFloat((String) sf.getValue("AF")), 2.0e-03,
DELTA);
assertEquals(sf.getFeatureGroup(), "VCF");
assertEquals(sf.getBegin(), 4);
assertEquals(sf.getEnd(), 4);
- assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
+ assertEquals(sf.getType(), SEQUENCE_VARIANT);
assertEquals(sf.getScore(), 0f);
assertEquals(Float.parseFloat((String) sf.getValue("AF")), 3.0e-03,
DELTA);
assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,GA");
+ assertNull(sf.getValue("ID")); // '.' is ignored
+ assertNull(sf.getValue("FILTER")); // '.' is ignored
+
+ sf = geneFeatures.get(4);
+ assertEquals(sf.getFeatureGroup(), "VCF");
+ assertEquals(sf.getBegin(), 6);
+ assertEquals(sf.getEnd(), 6);
+ assertEquals(sf.getType(), SEQUENCE_VARIANT);
+ assertEquals(sf.getScore(), 0f);
+ // AF=. should not have been captured
+ assertNull(sf.getValue("AF"));
+ assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,C");
/*
* verify variant feature(s) added to transcript
*/
List<SequenceFeature> transcriptFeatures = al.getSequenceAt(1)
.getSequenceFeatures();
- assertEquals(transcriptFeatures.size(), 2);
+ assertEquals(transcriptFeatures.size(), 3);
sf = transcriptFeatures.get(0);
assertEquals(sf.getFeatureGroup(), "VCF");
assertEquals(sf.getBegin(), 2);
assertEquals(sf.getEnd(), 2);
- assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
+ assertEquals(sf.getType(), SEQUENCE_VARIANT);
assertEquals(sf.getScore(), 0f);
assertEquals(Float.parseFloat((String) sf.getValue("AF")), 2.0e-03,
DELTA);
assertEquals(sf.getFeatureGroup(), "VCF");
assertEquals(sf.getBegin(), 2);
assertEquals(sf.getEnd(), 2);
- assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
+ assertEquals(sf.getType(), SEQUENCE_VARIANT);
assertEquals(sf.getScore(), 0f);
assertEquals(Float.parseFloat((String) sf.getValue("AF")), 3.0e-03,
DELTA);
* verify SNP variant feature(s) computed and added to protein
* first codon AGC varies to ACC giving S/T
*/
- DBRefEntry[] dbRefs = al.getSequenceAt(1).getDBRefs();
+ List<DBRefEntry> dbRefs = al.getSequenceAt(1).getDBRefs();
SequenceI peptide = null;
for (DBRefEntry dbref : dbRefs)
{
* JAL-3187 don't precompute protein features, do dynamically instead
*/
assertTrue(proteinFeatures.isEmpty());
- // assertEquals(proteinFeatures.size(), 1);
- // sf = proteinFeatures.get(0);
- // assertEquals(sf.getFeatureGroup(), "VCF");
- // assertEquals(sf.getBegin(), 1);
- // assertEquals(sf.getEnd(), 1);
- // assertEquals(sf.getType(), SequenceOntologyI.NONSYNONYMOUS_VARIANT);
- // assertEquals(sf.getDescription(), "p.Ser1Thr");
}
- private File makeVcf() throws IOException
+ private File makeVcfFile() throws IOException
{
File f = File.createTempFile("Test", ".vcf");
f.deleteOnExit();
{
AlignmentI al = buildAlignment();
- File f = makeVcf();
+ File f = makeVcfFile();
VCFLoader loader = new VCFLoader(f.getPath());
List<SequenceFeature> geneFeatures = al.getSequenceAt(2)
.getSequenceFeatures();
SequenceFeatures.sortFeatures(geneFeatures, true);
- assertEquals(geneFeatures.size(), 4);
+ assertEquals(geneFeatures.size(), 5);
+ SequenceFeature sf;
/*
- * variant A/T at 45051611 maps to T/A at gene position 24
+ * insertion G/GA at 45051613 maps to an insertion at
+ * the preceding position (21) on reverse strand gene
+ * reference: CAAGC -> GCTTG/21-25
+ * genomic variant: CAAGAC (G/GA)
+ * gene variant: GTCTTG (G/GT at 21)
*/
- SequenceFeature sf = geneFeatures.get(3);
+ sf = geneFeatures.get(1);
assertEquals(sf.getFeatureGroup(), "VCF");
- assertEquals(sf.getBegin(), 24);
- assertEquals(sf.getEnd(), 24);
- assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
+ assertEquals(sf.getBegin(), 21);
+ assertEquals(sf.getEnd(), 21);
+ assertEquals(sf.getType(), SEQUENCE_VARIANT);
assertEquals(sf.getScore(), 0f);
- assertEquals(Float.parseFloat((String) sf.getValue("AF")), 5.0e-03,
+ assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,GT");
+ assertEquals(Float.parseFloat((String) sf.getValue("AF")), 3.0e-03,
DELTA);
- assertEquals(sf.getValue(Gff3Helper.ALLELES), "T,A");
/*
- * variant A/C at 45051611 maps to T/G at gene position 24
+ * variant G/C at 45051613 maps to C/G at gene position 22
*/
sf = geneFeatures.get(2);
assertEquals(sf.getFeatureGroup(), "VCF");
- assertEquals(sf.getBegin(), 24);
- assertEquals(sf.getEnd(), 24);
- assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
+ assertEquals(sf.getBegin(), 22);
+ assertEquals(sf.getEnd(), 22);
+ assertEquals(sf.getType(), SEQUENCE_VARIANT);
assertEquals(sf.getScore(), 0f);
- assertEquals(Float.parseFloat((String) sf.getValue("AF")), 4.0e-03,
+ assertEquals(sf.getValue(Gff3Helper.ALLELES), "C,G");
+ assertEquals(Float.parseFloat((String) sf.getValue("AF")), 2.0e-03,
DELTA);
- assertEquals(sf.getValue(Gff3Helper.ALLELES), "T,G");
/*
- * variant G/C at 45051613 maps to C/G at gene position 22
+ * variant A/C at 45051611 maps to T/G at gene position 24
*/
- sf = geneFeatures.get(1);
+ sf = geneFeatures.get(3);
assertEquals(sf.getFeatureGroup(), "VCF");
- assertEquals(sf.getBegin(), 22);
- assertEquals(sf.getEnd(), 22);
- assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
+ assertEquals(sf.getBegin(), 24);
+ assertEquals(sf.getEnd(), 24);
+ assertEquals(sf.getType(), SEQUENCE_VARIANT);
assertEquals(sf.getScore(), 0f);
- assertEquals(Float.parseFloat((String) sf.getValue("AF")), 2.0e-03,
+ assertEquals(sf.getValue(Gff3Helper.ALLELES), "T,G");
+ assertEquals(Float.parseFloat((String) sf.getValue("AF")), 4.0e-03,
DELTA);
- assertEquals(sf.getValue(Gff3Helper.ALLELES), "C,G");
/*
- * insertion G/GA at 45051613 maps to an insertion at
- * the preceding position (21) on reverse strand gene
- * reference: CAAGC -> GCTTG/21-25
- * genomic variant: CAAGAC (G/GA)
- * gene variant: GTCTTG (G/GT at 21)
+ * variant A/T at 45051611 maps to T/A at gene position 24
*/
- sf = geneFeatures.get(0);
+ sf = geneFeatures.get(4);
assertEquals(sf.getFeatureGroup(), "VCF");
- assertEquals(sf.getBegin(), 21);
- assertEquals(sf.getEnd(), 21);
- assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
+ assertEquals(sf.getBegin(), 24);
+ assertEquals(sf.getEnd(), 24);
+ assertEquals(sf.getType(), SEQUENCE_VARIANT);
assertEquals(sf.getScore(), 0f);
- assertEquals(Float.parseFloat((String) sf.getValue("AF")), 3.0e-03,
+ assertEquals(sf.getValue(Gff3Helper.ALLELES), "T,A");
+ assertEquals(Float.parseFloat((String) sf.getValue("AF")), 5.0e-03,
DELTA);
- assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,GT");
/*
- * verify 2 variant features added to transcript2
+ * verify 3 variant features added to transcript2
*/
List<SequenceFeature> transcriptFeatures = al.getSequenceAt(3)
.getSequenceFeatures();
- assertEquals(transcriptFeatures.size(), 2);
+ assertEquals(transcriptFeatures.size(), 3);
/*
* insertion G/GT at position 21 of gene maps to position 16 of transcript
*/
- sf = transcriptFeatures.get(0);
+ sf = transcriptFeatures.get(1);
assertEquals(sf.getFeatureGroup(), "VCF");
assertEquals(sf.getBegin(), 16);
assertEquals(sf.getEnd(), 16);
- assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
+ assertEquals(sf.getType(), SEQUENCE_VARIANT);
assertEquals(sf.getScore(), 0f);
+ assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,GT");
assertEquals(Float.parseFloat((String) sf.getValue("AF")), 3.0e-03,
DELTA);
- assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,GT");
/*
* SNP C/G at position 22 of gene maps to position 17 of transcript
*/
- sf = transcriptFeatures.get(1);
+ sf = transcriptFeatures.get(2);
assertEquals(sf.getFeatureGroup(), "VCF");
assertEquals(sf.getBegin(), 17);
assertEquals(sf.getEnd(), 17);
- assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
+ assertEquals(sf.getType(), SEQUENCE_VARIANT);
assertEquals(sf.getScore(), 0f);
+ assertEquals(sf.getValue(Gff3Helper.ALLELES), "C,G");
assertEquals(Float.parseFloat((String) sf.getValue("AF")), 2.0e-03,
DELTA);
- assertEquals(sf.getValue(Gff3Helper.ALLELES), "C,G");
/*
* verify variant feature(s) computed and added to protein
* last codon GCT varies to GGT giving A/G in the last peptide position
*/
- DBRefEntry[] dbRefs = al.getSequenceAt(3).getDBRefs();
+ List<DBRefEntry> dbRefs = al.getSequenceAt(3).getDBRefs();
SequenceI peptide = null;
for (DBRefEntry dbref : dbRefs)
{
}
}
List<SequenceFeature> proteinFeatures = peptide.getSequenceFeatures();
+
/*
* JAL-3187 don't precompute protein features, do dynamically instead
*/
assertTrue(proteinFeatures.isEmpty());
- // assertEquals(proteinFeatures.size(), 1);
- // sf = proteinFeatures.get(0);
- // assertEquals(sf.getFeatureGroup(), "VCF");
- // assertEquals(sf.getBegin(), 6);
- // assertEquals(sf.getEnd(), 6);
- // assertEquals(sf.getType(), SequenceOntologyI.NONSYNONYMOUS_VARIANT);
- // assertEquals(sf.getDescription(), "p.Ala6Gly");
}
/**
assertEquals(sf.getValue("alleles"), "C,T");
map = (Map) sf.getValue("CSQ");
assertEquals(map.size(), 9);
- assertEquals(map.get("PolyPhen"), "Bad++"); // %3B%3B decoded
+ assertEquals(map.get("PolyPhen"), "Bad;;"); // %3B%3B decoded
sf = geneFeatures.get(2);
assertEquals(sf.getBegin(), 9);
* and GAG/GGG which is E/G in position 4
* the insertion variant is not transferred to the peptide
*/
- DBRefEntry[] dbRefs = al.findName("transcript3").getDBRefs();
+ List<DBRefEntry> dbRefs = al.findName("transcript3").getDBRefs();
SequenceI peptide = null;
for (DBRefEntry dbref : dbRefs)
{
assertEquals(sf.getEnd(), 15);
assertEquals(sf.getDescription(), "T,C");
}
-
- @Test(groups = "Functional")
- public void testDecodeSpecialCharacters() throws IOException
- {
- String encoded = "hello world";
- String decoded = VCFLoader.decodeSpecialCharacters(encoded);
- assertSame(encoded, decoded); // no change needed
-
- encoded = "ab%3Acd%3Bef%3Dgh%25ij%2Ckl%3A";
- decoded = VCFLoader.decodeSpecialCharacters(encoded);
- assertEquals(decoded, "ab:cd;ef=gh%ij,kl:");
- }
}
\ No newline at end of file