+/*
+ * 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.ext.ensembl;
import static org.testng.AssertJUnit.assertEquals;
import static org.testng.AssertJUnit.assertFalse;
-import static org.testng.AssertJUnit.assertSame;
import static org.testng.AssertJUnit.assertTrue;
import jalview.api.FeatureSettingsModelI;
+import jalview.bin.Cache;
import jalview.datamodel.SequenceDummy;
import jalview.datamodel.SequenceFeature;
import jalview.datamodel.SequenceI;
+import jalview.gui.JvOptionPane;
import jalview.io.gff.SequenceOntologyFactory;
import jalview.io.gff.SequenceOntologyLite;
import jalview.util.MapList;
public class EnsemblGeneTest
{
+
+ @BeforeClass(alwaysRun = true)
+ public void setUpJvOptionPane()
+ {
+ JvOptionPane.setInteractiveMode(false);
+ JvOptionPane.setMockResponse(JvOptionPane.CANCEL_OPTION);
+ }
+
@BeforeClass(alwaysRun = true)
public void setUp()
{
+ Cache.loadProperties("test/jalview/io/testProps.jvprops");
SequenceOntologyFactory.setInstance(new SequenceOntologyLite());
}
genomic.setEnd(50000);
String geneId = "ABC123";
- // gene at (start+10000) length 501
+ // gene at (start+20000) length 501
+ // should be ignored - the first 'gene' found defines the whole range
+ // (note features are found in position order, not addition order)
SequenceFeature sf = new SequenceFeature("gene", "", 20000, 20500, 0f,
null);
sf.setValue("ID", "gene:" + geneId);
genomic.addSequenceFeature(sf);
// gene at (start + 10500) length 101
- // should be ignored - the first 'gene' found defines the whole range
sf = new SequenceFeature("gene", "", 10500, 10600, 0f, null);
sf.setValue("ID", "gene:" + geneId);
sf.setStrand("+");
23);
List<int[]> fromRanges = ranges.getFromRanges();
assertEquals(1, fromRanges.size());
- assertEquals(20000, fromRanges.get(0)[0]);
- assertEquals(20500, fromRanges.get(0)[1]);
+ assertEquals(10500, fromRanges.get(0)[0]);
+ assertEquals(10600, fromRanges.get(0)[1]);
// to range should start from given start numbering
List<int[]> toRanges = ranges.getToRanges();
assertEquals(1, toRanges.size());
assertEquals(23, toRanges.get(0)[0]);
- assertEquals(523, toRanges.get(0)[1]);
+ assertEquals(123, toRanges.get(0)[1]);
}
/**
genomic.setEnd(50000);
String geneId = "ABC123";
- // gene at (start+10000) length 501
+ // gene at (start+20000) length 501
+ // should be ignored - the first 'gene' found defines the whole range
+ // (real data would only have one such feature)
SequenceFeature sf = new SequenceFeature("ncRNA_gene", "", 20000,
20500, 0f, null);
sf.setValue("ID", "gene:" + geneId);
genomic.addSequenceFeature(sf);
// gene at (start + 10500) length 101
- // should be ignored - the first 'gene' found defines the whole range
- // (real data would only have one such feature)
sf = new SequenceFeature("gene", "", 10500, 10600, 0f, null);
sf.setValue("ID", "gene:" + geneId);
sf.setStrand("+");
List<int[]> fromRanges = ranges.getFromRanges();
assertEquals(1, fromRanges.size());
// from range on reverse strand:
- assertEquals(20500, fromRanges.get(0)[0]);
- assertEquals(20000, fromRanges.get(0)[1]);
+ assertEquals(10500, fromRanges.get(0)[0]);
+ assertEquals(10600, fromRanges.get(0)[1]);
// to range should start from given start numbering
List<int[]> toRanges = ranges.getToRanges();
assertEquals(1, toRanges.size());
assertEquals(23, toRanges.get(0)[0]);
- assertEquals(523, toRanges.get(0)[1]);
+ assertEquals(123, toRanges.get(0)[1]);
}
/**
genomic.addSequenceFeature(sf1);
// transcript sub-type feature
- SequenceFeature sf2 = new SequenceFeature("snRNA", "", 20000,
- 20500, 0f, null);
+ SequenceFeature sf2 = new SequenceFeature("snRNA", "", 21000, 21500,
+ 0f, null);
sf2.setValue("Parent", "gene:" + geneId);
sf2.setValue("transcript_id", "transcript2");
genomic.addSequenceFeature(sf2);
// NMD_transcript_variant treated like transcript in Ensembl
SequenceFeature sf3 = new SequenceFeature("NMD_transcript_variant", "",
- 20000, 20500, 0f, null);
- sf3.setValue("Parent", "gene:" + geneId);
+ 22000, 22500, 0f, null);
+ // id matching should not be case-sensitive
+ sf3.setValue("Parent", "gene:" + geneId.toLowerCase());
sf3.setValue("transcript_id", "transcript3");
genomic.addSequenceFeature(sf3);
// transcript for a different gene - ignored
- SequenceFeature sf4 = new SequenceFeature("snRNA", "", 20000, 20500,
+ SequenceFeature sf4 = new SequenceFeature("snRNA", "", 23000, 23500,
0f, null);
sf4.setValue("Parent", "gene:XYZ");
sf4.setValue("transcript_id", "transcript4");
List<SequenceFeature> features = testee.getTranscriptFeatures(geneId,
genomic);
assertEquals(3, features.size());
- assertSame(sf1, features.get(0));
- assertSame(sf2, features.get(1));
- assertSame(sf3, features.get(2));
+ assertTrue(features.contains(sf1));
+ assertTrue(features.contains(sf2));
+ assertTrue(features.contains(sf3));
}
/**
{
String geneId = "ABC123";
EnsemblGene testee = new EnsemblGene();
- SequenceFeature sf = new SequenceFeature("gene", "", 20000,
- 20500, 0f, null);
+ SequenceFeature sf = new SequenceFeature("gene", "", 20000, 20500, 0f,
+ null);
sf.setValue("ID", "gene:" + geneId);
assertFalse(testee.retainFeature(sf, geneId));
- sf.setType("transcript");
+ sf = new SequenceFeature("transcript", "", 20000, 20500, 0f, null);
sf.setValue("Parent", "gene:" + geneId);
assertTrue(testee.retainFeature(sf, geneId));
- sf.setType("mature_transcript");
+ sf = new SequenceFeature("mature_transcript", "", 20000, 20500, 0f,
+ null);
sf.setValue("Parent", "gene:" + geneId);
assertTrue(testee.retainFeature(sf, geneId));
- sf.setType("NMD_transcript_variant");
+ sf = new SequenceFeature("NMD_transcript_variant", "", 20000, 20500,
+ 0f, null);
sf.setValue("Parent", "gene:" + geneId);
assertTrue(testee.retainFeature(sf, geneId));
sf.setValue("Parent", "gene:XYZ");
assertFalse(testee.retainFeature(sf, geneId));
- sf.setType("anything");
+ sf = new SequenceFeature("anything", "", 20000, 20500, 0f, null);
assertTrue(testee.retainFeature(sf, geneId));
}
{
String accId = "ABC123";
EnsemblGene testee = new EnsemblGene();
-
+
// gene with no ID not valid
SequenceFeature sf = new SequenceFeature("gene", "", 1, 2, 0f, null);
assertFalse(testee.identifiesSequence(sf, accId));
-
+
// gene with wrong ID not valid
sf.setValue("ID", "gene:XYZ");
assertFalse(testee.identifiesSequence(sf, accId));
-
+
// gene with right ID is valid
sf.setValue("ID", "gene:" + accId);
assertTrue(testee.identifiesSequence(sf, accId));
-
+
// gene sub-type with right ID is valid
- sf.setType("snRNA_gene");
+ sf = new SequenceFeature("snRNA_gene", "", 1, 2, 0f, null);
+ sf.setValue("ID", "gene:" + accId);
assertTrue(testee.identifiesSequence(sf, accId));
-
+
+ // test is not case-sensitive
+ assertTrue(testee.identifiesSequence(sf, accId.toLowerCase()));
+
// transcript not valid:
- sf.setType("transcript");
+ sf = new SequenceFeature("transcript", "", 1, 2, 0f, null);
+ sf.setValue("ID", "gene:" + accId);
assertFalse(testee.identifiesSequence(sf, accId));
-
+
// exon not valid:
- sf.setType("exon");
+ sf = new SequenceFeature("exon", "", 1, 2, 0f, null);
+ sf.setValue("ID", "gene:" + accId);
assertFalse(testee.identifiesSequence(sf, accId));
}
assertEquals(-1, fc.compare("coding_exon", "feature_variant"));
assertEquals(1f, fc.getTransparency());
}
+
+ @Test(groups = "Network")
+ public void testGetGeneIds()
+ {
+ /*
+ * ENSG00000158828 gene id PINK1 human
+ * ENST00000321556 transcript for the same gene - should not be duplicated
+ * P30419 Uniprot identifier for ENSG00000136448
+ * ENST00000592782 transcript for Uniprot gene - should not be duplicated
+ * BRAF - gene name resolvabe (at time of writing) for 6 model species
+ */
+ String ids = "ENSG00000158828 ENST00000321556 P30419 ENST00000592782 BRAF";
+ EnsemblGene testee = new EnsemblGene();
+ List<String> geneIds = testee.getGeneIds(ids);
+ assertEquals(8, geneIds.size());
+ assertTrue(geneIds.contains("ENSG00000158828"));
+ assertTrue(geneIds.contains("ENSG00000136448"));
+ assertTrue(geneIds.contains("ENSG00000157764")); // BRAF human
+ assertTrue(geneIds.contains("ENSMUSG00000002413")); // mouse
+ assertTrue(geneIds.contains("ENSRNOG00000010957")); // rat
+ assertTrue(geneIds.contains("ENSXETG00000004845")); // xenopus
+ assertTrue(geneIds.contains("ENSDARG00000017661")); // zebrafish
+ assertTrue(geneIds.contains("ENSGALG00000012865")); // chicken
+ }
}