+/*
+ * 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.assertNull;
+import static org.testng.AssertJUnit.assertTrue;
import jalview.datamodel.SequenceDummy;
import jalview.datamodel.SequenceFeature;
import java.util.List;
+import org.testng.Assert;
+import org.testng.annotations.AfterClass;
+import org.testng.annotations.BeforeClass;
import org.testng.annotations.Test;
public class EnsemblCdnaTest
{
+ @BeforeClass(alwaysRun = true)
+ public void setUp()
+ {
+ SequenceOntologyFactory.setInstance(new SequenceOntologyLite());
+ }
+
+ @AfterClass(alwaysRun = true)
+ public void tearDown()
+ {
+ SequenceOntologyFactory.setInstance(null);
+ }
+
/**
* Test that the cdna part of genomic sequence is correctly identified by
* 'exon' features (or subtypes) - reverse strand case.
*/
@Test(groups = "Functional")
- public void getGenomicRangesFromFeatures_reverseStrand()
+ public void testGetGenomicRangesFromFeatures_reverseStrand()
{
EnsemblCdna testee = new EnsemblCdna();
SequenceI genomic = new SequenceDummy("chr7");
sf = new SequenceFeature("transcript", "", 10000, 50000, 0f, null);
genomic.addSequenceFeature(sf);
- SequenceOntologyFactory.setInstance(new SequenceOntologyLite());
-
MapList ranges = testee.getGenomicRangesFromFeatures(genomic,
transcriptId, 23);
List<int[]> fromRanges = ranges.getFromRanges();
/**
* Test that the cdna part of genomic sequence is correctly identified by
- * 'exon' features (or subtypes).
+ * 'exon' features (or subtypes) with the desired transcript as parent
*/
@Test(groups = "Functional")
- public void getGenomicRangesFromFeatures()
+ public void testGetGenomicRangesFromFeatures()
{
EnsemblCdna testee = new EnsemblCdna();
SequenceI genomic = new SequenceDummy("chr7");
genomic.setStart(10000);
genomic.setEnd(50000);
String transcriptId = "ABC123";
-
+
// exon at (start+10000) length 501
SequenceFeature sf = new SequenceFeature("exon", "", 20000, 20500, 0f,
null);
sf.setValue("Parent", "transcript:" + transcriptId);
sf.setStrand("+");
genomic.addSequenceFeature(sf);
-
+
// exon (sub-type) at (start + exon_variant) length 101
sf = new SequenceFeature("coding_exon", "", 10500, 10600, 0f, null);
sf.setValue("Parent", "transcript:" + transcriptId);
sf.setStrand("+");
genomic.addSequenceFeature(sf);
-
+
// exon belonging to a different transcript doesn't count
sf = new SequenceFeature("exon", "", 11500, 12600, 0f, null);
sf.setValue("Parent", "transcript:anotherOne");
genomic.addSequenceFeature(sf);
-
+
// transcript feature doesn't count
sf = new SequenceFeature("transcript", "", 10000, 50000, 0f, null);
sf.setStrand("-"); // weird but ignored
genomic.addSequenceFeature(sf);
-
- SequenceOntologyFactory.setInstance(new SequenceOntologyLite());
-
+
MapList ranges = testee.getGenomicRangesFromFeatures(genomic,
transcriptId, 23);
List<int[]> fromRanges = ranges.getFromRanges();
* reverse strands are present in the features of interest
*/
@Test(groups = "Functional")
- public void getGenomicRangesFromFeatures_mixedStrand()
+ public void testGetGenomicRangesFromFeatures_mixedStrand()
{
EnsemblCdna testee = new EnsemblCdna();
SequenceI genomic = new SequenceDummy("chr7");
genomic.setStart(10000);
genomic.setEnd(50000);
String transcriptId = "ABC123";
-
+
SequenceFeature sf = new SequenceFeature("exon", "", 20000, 20500, 0f,
null);
sf.setValue("Parent", "transcript:" + transcriptId);
sf.setStrand("-");
genomic.addSequenceFeature(sf);
-
+
sf = new SequenceFeature("coding_exon", "", 10500, 10600, 0f, null);
sf.setValue("Parent", "transcript:" + transcriptId);
sf.setStrand("+");
genomic.addSequenceFeature(sf);
-
- SequenceOntologyFactory.setInstance(new SequenceOntologyLite());
-
+
MapList ranges = testee.getGenomicRangesFromFeatures(genomic,
transcriptId, 23);
assertNull(ranges);
}
+
+ /**
+ * Test the method that retains features except for 'transcript' (or
+ * subtypes), or features with parent other than the given id
+ */
+ @Test(groups = "Functional")
+ public void testRetainFeature()
+ {
+ String accId = "ABC123";
+ EnsemblCdna testee = new EnsemblCdna();
+
+ SequenceFeature sf = new SequenceFeature("transcript", "", 20000,
+ 20500, 0f, null);
+ assertFalse(testee.retainFeature(sf, accId));
+
+ sf.setType("aberrant_processed_transcript");
+ assertFalse(testee.retainFeature(sf, accId));
+
+ sf.setType("NMD_transcript_variant");
+ assertFalse(testee.retainFeature(sf, accId));
+
+ // other feature with no parent is retained
+ sf.setType("sequence_variant");
+ assertTrue(testee.retainFeature(sf, accId));
+
+ // other feature with desired parent is retained
+ sf.setValue("Parent", "transcript:" + accId);
+ assertTrue(testee.retainFeature(sf, accId));
+
+ // feature with wrong parent is not retained
+ sf.setValue("Parent", "transcript:XYZ");
+ assertFalse(testee.retainFeature(sf, accId));
+ }
+
+ /**
+ * Test the method that picks out 'exon' (or subtype) features with the
+ * accession id as parent
+ */
+ @Test(groups = "Functional")
+ public void testIdentifiesSequence()
+ {
+ String accId = "ABC123";
+ EnsemblCdna testee = new EnsemblCdna();
+
+ // exon with no parent not valid
+ SequenceFeature sf = new SequenceFeature("exon", "", 1, 2, 0f, null);
+ assertFalse(testee.identifiesSequence(sf, accId));
+
+ // exon with wrong parent not valid
+ sf.setValue("Parent", "transcript:XYZ");
+ assertFalse(testee.identifiesSequence(sf, accId));
+
+ // exon with right parent is valid
+ sf.setValue("Parent", "transcript:" + accId);
+ assertTrue(testee.identifiesSequence(sf, accId));
+
+ // exon sub-type with right parent is valid
+ sf.setType("coding_exon");
+ assertTrue(testee.identifiesSequence(sf, accId));
+
+ // transcript not valid:
+ sf.setType("transcript");
+ assertFalse(testee.identifiesSequence(sf, accId));
+
+ // CDS not valid:
+ sf.setType("CDS");
+ assertFalse(testee.identifiesSequence(sf, accId));
+ }
+
+ @Test(groups = "Functional")
+ public void testIsValidReference() throws Exception
+ {
+ EnsemblSequenceFetcher esq = new EnsemblCdna();
+ Assert.assertTrue(esq.isValidReference("CCDS5863.1"));
+ Assert.assertTrue(esq.isValidReference("ENST00000288602"));
+ Assert.assertTrue(esq.isValidReference("ENSG00000288602"));
+ Assert.assertFalse(esq.isValidReference("ENSP00000288602"));
+ Assert.assertFalse(esq.isValidReference("ENST0000288602"));
+ // non-human species having a 3 character identifier included:
+ Assert.assertTrue(esq.isValidReference("ENSMUSG00000099398"));
+ }
}
git://source.jalview.org / jalview.git / blobdiff