+/*
+ * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
+ * Copyright (C) $$Year-Rel$$ The Jalview Authors
+ *
+ * This file is part of Jalview.
+ *
+ * Jalview is free software: you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation, either version 3
+ * of the License, or (at your option) any later version.
+ *
+ * Jalview is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
+ * PURPOSE. See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Jalview. If not, see <http://www.gnu.org/licenses/>.
+ * The Jalview Authors are detailed in the 'AUTHORS' file.
+ */
package jalview.io.vcf;
import static jalview.io.gff.SequenceOntologyI.SEQUENCE_VARIANT;
import static org.testng.Assert.assertEquals;
import static org.testng.Assert.assertNull;
-import static org.testng.Assert.assertSame;
+import static org.testng.Assert.assertTrue;
import jalview.bin.Cache;
+import jalview.bin.Console;
import jalview.datamodel.AlignmentI;
import jalview.datamodel.DBRefEntry;
import jalview.datamodel.Mapping;
import jalview.datamodel.SequenceFeature;
import jalview.datamodel.SequenceI;
import jalview.datamodel.features.FeatureAttributes;
-import jalview.datamodel.features.FeatureAttributes.Datatype;
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;
private static final float DELTA = 0.00001f;
// columns 9717- of gene P30419 from Ensembl (much modified)
- private static final String FASTA = ""
- +
- /*
- * forward strand 'gene' and 'transcript' with two exons
- */
+ private static final String FASTA = "" +
+ /*
+ * forward strand 'gene' and 'transcript' with two exons
+ */
">gene1/1-25 chromosome:GRCh38:17:45051610:45051634:1\n"
+ "CAAGCTGGCGGACGAGAGTGTGACA\n"
+ ">transcript1/1-18\n--AGCTGGCG----AGAGTGTGAC-\n"
* reverse strand gene and transcript (reverse complement alleles!)
*/
+ ">gene2/1-25 chromosome:GRCh38:17:45051610:45051634:-1\n"
- + "TGTCACACTCTCGTCCGCCAGCTTG\n"
- + ">transcript2/1-18\n" + "-GTCACACTCT----CGCCAGCT--\n"
+ + "TGTCACACTCTCGTCCGCCAGCTTG\n" + ">transcript2/1-18\n"
+ + "-GTCACACTCT----CGCCAGCT--\n"
/*
* 'gene' on chromosome 5 with two transcripts
+ ">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
+ // 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\"",
// A/T,C variants in position 2 of gene sequence (precedes transcript)
// should create 2 variant features with respective AF values
// malformed values for AC_Female and AF_AFR should be ignored
- "17\t45051611\t.\tA\tT,C\t1666.64\tRF\tAC=15;AF=5.0e-03,4.0e-03;AC_Female=12,3d;AF_AFR=low,2.3e-4",
+ "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\t1666.65\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=." };
Cache.setProperty("VCF_FIELDS", ".*");
Cache.setProperty("VEP_FIELDS", ".*");
Cache.setProperty("VCF_ASSEMBLY", "GRCh38=GRCh38");
- Cache.initLogger();
+ Console.initLogger();
}
@BeforeTest(alwaysRun = true)
assertEquals(sf.getValue("AF_AFR"), "2.3e-4");
assertEquals(sf.getValue(Gff3Helper.ALLELES), "A,C");
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"));
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");
* 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)
{
}
}
List<SequenceFeature> proteinFeatures = peptide.getSequenceFeatures();
- assertEquals(proteinFeatures.size(), 3);
- 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");
/*
- * check that sequence_variant attribute AF has been clocked as
- * numeric with correct min and max values
- * (i.e. invalid values have been ignored - JAL-3375)
+ * JAL-3187 don't precompute protein features, do dynamically instead
*/
- FeatureAttributes fa = FeatureAttributes.getInstance();
- assertSame(fa.getDatatype(SEQUENCE_VARIANT, "AF"), Datatype.Number);
- float[] minmax = fa.getMinMax(SEQUENCE_VARIANT, "AF");
- assertEquals(minmax[0], 0.002f);
- assertEquals(minmax[1], 0.005f);
+ assertTrue(proteinFeatures.isEmpty());
}
private File makeVcfFile() throws IOException
SequenceI gene1 = alignment.findName("gene1");
int[] to = new int[] { 45051610, 45051634 };
int[] from = new int[] { gene1.getStart(), gene1.getEnd() };
- gene1.setGeneLoci("homo_sapiens", "GRCh38", "17", new MapList(from, to,
- 1, 1));
+ gene1.setGeneLoci("homo_sapiens", "GRCh38", "17",
+ new MapList(from, to, 1, 1));
/*
* map 'transcript1' to chromosome via 'gene1'
to = new int[] { 45051612, 45051619, 45051624, 45051633 };
SequenceI transcript1 = alignment.findName("transcript1");
from = new int[] { transcript1.getStart(), transcript1.getEnd() };
- transcript1.setGeneLoci("homo_sapiens", "GRCh38", "17", new MapList(
- from, to,
- 1, 1));
+ transcript1.setGeneLoci("homo_sapiens", "GRCh38", "17",
+ new MapList(from, to, 1, 1));
/*
* map gene2 to chromosome reverse strand
SequenceI gene2 = alignment.findName("gene2");
to = new int[] { 45051634, 45051610 };
from = new int[] { gene2.getStart(), gene2.getEnd() };
- gene2.setGeneLoci("homo_sapiens", "GRCh38", "17", new MapList(from, to,
- 1, 1));
+ gene2.setGeneLoci("homo_sapiens", "GRCh38", "17",
+ new MapList(from, to, 1, 1));
/*
* map 'transcript2' to chromosome via 'gene2'
to = new int[] { 45051633, 45051624, 45051619, 45051612 };
SequenceI transcript2 = alignment.findName("transcript2");
from = new int[] { transcript2.getStart(), transcript2.getEnd() };
- transcript2.setGeneLoci("homo_sapiens", "GRCh38", "17", new MapList(
- from, to,
- 1, 1));
+ transcript2.setGeneLoci("homo_sapiens", "GRCh38", "17",
+ new MapList(from, to, 1, 1));
/*
* add a protein product as a DBRef on transcript1
SequenceI gene3 = alignment.findName("gene3");
to = new int[] { 45051610, 45051634 };
from = new int[] { gene3.getStart(), gene3.getEnd() };
- gene3.setGeneLoci("homo_sapiens", "GRCh38", "5", new MapList(from, to,
- 1, 1));
+ gene3.setGeneLoci("homo_sapiens", "GRCh38", "5",
+ new MapList(from, to, 1, 1));
/*
* map 'transcript3' to chromosome
SequenceI transcript3 = alignment.findName("transcript3");
to = new int[] { 45051612, 45051619, 45051624, 45051633 };
from = new int[] { transcript3.getStart(), transcript3.getEnd() };
- transcript3.setGeneLoci("homo_sapiens", "GRCh38", "5", new MapList(
- from, to,
- 1, 1));
+ transcript3.setGeneLoci("homo_sapiens", "GRCh38", "5",
+ new MapList(from, to, 1, 1));
/*
* map 'transcript4' to chromosome
to = new int[] { 45051615, 45051617, 45051619, 45051632, 45051634,
45051634 };
from = new int[] { transcript4.getStart(), transcript4.getEnd() };
- transcript4.setGeneLoci("homo_sapiens", "GRCh38", "5", new MapList(
- from, to,
- 1, 1));
+ transcript4.setGeneLoci("homo_sapiens", "GRCh38", "5",
+ new MapList(from, to, 1, 1));
/*
* add a protein product as a DBRef on transcript3
* 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();
- assertEquals(proteinFeatures.size(), 3);
- 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");
+
+ /*
+ * JAL-3187 don't precompute protein features, do dynamically instead
+ */
+ assertTrue(proteinFeatures.isEmpty());
}
/**
// gene features include Consequence for all transcripts
Map map = (Map) sf.getValue("CSQ");
assertEquals(map.size(), 9);
+ assertEquals(map.get("PolyPhen"), "Bad");
sf = geneFeatures.get(1);
assertEquals(sf.getBegin(), 5);
assertEquals(sf.getValue("alleles"), "C,T");
map = (Map) sf.getValue("CSQ");
assertEquals(map.size(), 9);
+ 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)
{
}
}
List<SequenceFeature> proteinFeatures = peptide.getSequenceFeatures();
- SequenceFeatures.sortFeatures(proteinFeatures, true);
- assertEquals(proteinFeatures.size(), 2);
- sf = proteinFeatures.get(0);
- assertEquals(sf.getFeatureGroup(), "VCF");
- assertEquals(sf.getBegin(), 1);
- assertEquals(sf.getEnd(), 1);
- assertEquals(sf.getType(), SequenceOntologyI.SYNONYMOUS_VARIANT);
- assertEquals(sf.getDescription(), "agC/agT");
- sf = proteinFeatures.get(1);
- assertEquals(sf.getFeatureGroup(), "VCF");
- assertEquals(sf.getBegin(), 4);
- assertEquals(sf.getEnd(), 4);
- assertEquals(sf.getType(), SequenceOntologyI.NONSYNONYMOUS_VARIANT);
- assertEquals(sf.getDescription(), "p.Glu4Gly");
+ /*
+ * JAL-3187 don't precompute protein features, do dynamically instead
+ */
+ assertTrue(proteinFeatures.isEmpty());
+ // SequenceFeatures.sortFeatures(proteinFeatures, true);
+ // assertEquals(proteinFeatures.size(), 2);
+ // sf = proteinFeatures.get(0);
+ // assertEquals(sf.getFeatureGroup(), "VCF");
+ // assertEquals(sf.getBegin(), 1);
+ // assertEquals(sf.getEnd(), 1);
+ // assertEquals(sf.getType(), SequenceOntologyI.SYNONYMOUS_VARIANT);
+ // assertEquals(sf.getDescription(), "agC/agT");
+ // sf = proteinFeatures.get(1);
+ // assertEquals(sf.getFeatureGroup(), "VCF");
+ // assertEquals(sf.getBegin(), 4);
+ // assertEquals(sf.getEnd(), 4);
+ // assertEquals(sf.getType(), SequenceOntologyI.NONSYNONYMOUS_VARIANT);
+ // assertEquals(sf.getDescription(), "p.Glu4Gly");
/*
* verify variant feature(s) added to transcript4
@Test(groups = "Functional")
public void testLoadVCFContig() throws IOException
{
- VCFLoader loader = new VCFLoader(
- "test/jalview/io/vcf/testVcf2.vcf");
+ VCFLoader loader = new VCFLoader("test/jalview/io/vcf/testVcf2.vcf");
SequenceI seq = loader.loadVCFContig("contig123");
assertEquals(seq.getLength(), 15);
git://source.jalview.org / jalview.git / blobdiff