X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=test%2Fjalview%2Fdatamodel%2FAlignedCodonFrameTest.java;h=2e0793e58b0b4441d34b2a81227ee33a1e60be13;hb=37de9310bec3501cbc6381e0c3dcb282fcaad812;hp=35d92d35af96f9d4b971abdac6709b04aa15e0e6;hpb=fddf3084802b37e5cee17829e32692a4aac3e60d;p=jalview.git
diff --git a/test/jalview/datamodel/AlignedCodonFrameTest.java b/test/jalview/datamodel/AlignedCodonFrameTest.java
index 35d92d3..2e0793e 100644
--- a/test/jalview/datamodel/AlignedCodonFrameTest.java
+++ b/test/jalview/datamodel/AlignedCodonFrameTest.java
@@ -1,11 +1,36 @@
+/*
+ * 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 .
+ * The Jalview Authors are detailed in the 'AUTHORS' file.
+ */
package jalview.datamodel;
import static org.testng.AssertJUnit.assertEquals;
+import static org.testng.AssertJUnit.assertFalse;
import static org.testng.AssertJUnit.assertNull;
+import static org.testng.AssertJUnit.assertSame;
+import static org.testng.AssertJUnit.assertTrue;
+import static org.testng.internal.junit.ArrayAsserts.assertArrayEquals;
import jalview.util.MapList;
import java.util.Arrays;
+import java.util.List;
import org.testng.annotations.Test;
@@ -15,11 +40,10 @@ public class AlignedCodonFrameTest
/**
* Test the method that locates the first aligned sequence that has a mapping.
*/
- @Test(groups ={ "Functional" })
+ @Test(groups = { "Functional" })
public void testFindAlignedSequence()
{
- AlignmentI cdna = new Alignment(new SequenceI[]
- {});
+ AlignmentI cdna = new Alignment(new SequenceI[] {});
final Sequence seq1 = new Sequence("Seq1", "C-G-TA-GC");
seq1.createDatasetSequence();
cdna.addSequence(seq1);
@@ -27,8 +51,7 @@ public class AlignedCodonFrameTest
seq2.createDatasetSequence();
cdna.addSequence(seq2);
- AlignmentI aa = new Alignment(new SequenceI[]
- {});
+ AlignmentI aa = new Alignment(new SequenceI[] {});
final Sequence aseq1 = new Sequence("Seq1", "-P-R");
aseq1.createDatasetSequence();
aa.addSequence(aseq1);
@@ -43,27 +66,26 @@ public class AlignedCodonFrameTest
assertNull(acf.findAlignedSequence(seq1, aa));
- MapList map = new MapList(new int[]
- { 1, 6 }, new int[]
- { 1, 2 }, 3, 1);
+ MapList map = new MapList(new int[] { 1, 6 }, new int[] { 1, 2 }, 3, 1);
acf.addMap(seq1.getDatasetSequence(), aseq2.getDatasetSequence(), map);
/*
* DNA seq1 maps to AA seq2
*/
- assertEquals(aa.getSequenceAt(1),
- acf.findAlignedSequence(cdna
+ assertEquals(aa.getSequenceAt(1), acf.findAlignedSequence(cdna
.getSequenceAt(0).getDatasetSequence(), aa));
+ // can also find this from the dna aligned sequence
+ assertEquals(aa.getSequenceAt(1),
+ acf.findAlignedSequence(cdna.getSequenceAt(0), aa));
- assertEquals(cdna.getSequenceAt(0),
- acf.findAlignedSequence(aa
+ assertEquals(cdna.getSequenceAt(0), acf.findAlignedSequence(aa
.getSequenceAt(1).getDatasetSequence(), cdna));
}
/**
* Test the method that locates the mapped codon for a protein position.
*/
- @Test(groups ={ "Functional" })
+ @Test(groups = { "Functional" })
public void testGetMappedRegion()
{
// introns lower case, exons upper case
@@ -74,7 +96,7 @@ public class AlignedCodonFrameTest
final Sequence aseq1 = new Sequence("Seq1", "-P-R");
aseq1.createDatasetSequence();
- final Sequence aseq2 = new Sequence("Seq2", "-LY-");
+ final Sequence aseq2 = new Sequence("Seq2", "-LY-Q");
aseq2.createDatasetSequence();
/*
@@ -86,24 +108,28 @@ public class AlignedCodonFrameTest
/*
* Set up the mappings for the exons (upper-case bases)
+ * Note residue Q is unmapped
*/
- MapList map = new MapList(new int[]
- { 2, 4, 6, 6, 8, 9 }, new int[]
- { 1, 2 }, 3, 1);
+ MapList map = new MapList(new int[] { 2, 4, 6, 6, 8, 9 }, new int[] {
+ 1, 2 }, 3, 1);
acf.addMap(seq1.getDatasetSequence(), aseq1.getDatasetSequence(), map);
- map = new MapList(new int[]
- { 1, 2, 4, 5, 7, 8 }, new int[]
- { 1, 2 }, 3, 1);
+ map = new MapList(new int[] { 1, 2, 4, 5, 7, 8 }, new int[] { 1, 2 },
+ 3, 1);
acf.addMap(seq2.getDatasetSequence(), aseq2.getDatasetSequence(), map);
- assertEquals("[2, 4]",
- Arrays.toString(acf.getMappedRegion(seq1, aseq1, 1)));
- assertEquals("[6, 6, 8, 9]",
- Arrays.toString(acf.getMappedRegion(seq1, aseq1, 2)));
- assertEquals("[1, 2, 4, 4]",
- Arrays.toString(acf.getMappedRegion(seq2, aseq2, 1)));
- assertEquals("[5, 5, 7, 8]",
- Arrays.toString(acf.getMappedRegion(seq2, aseq2, 2)));
+ assertArrayEquals(new int[] { 2, 4 },
+ acf.getMappedRegion(seq1, aseq1, 1));
+ assertArrayEquals(new int[] { 6, 6, 8, 9 },
+ acf.getMappedRegion(seq1, aseq1, 2));
+ assertArrayEquals(new int[] { 1, 2, 4, 4 },
+ acf.getMappedRegion(seq2, aseq2, 1));
+ assertArrayEquals(new int[] { 5, 5, 7, 8 },
+ acf.getMappedRegion(seq2, aseq2, 2));
+
+ /*
+ * No mapping from seq2 to Q
+ */
+ assertNull(acf.getMappedRegion(seq2, aseq2, 3));
/*
* No mapping from sequence 1 to sequence 2
@@ -111,12 +137,12 @@ public class AlignedCodonFrameTest
assertNull(acf.getMappedRegion(seq1, aseq2, 1));
}
- @Test(groups ={ "Functional" })
- public void testGetMappedCodon()
+ @Test(groups = { "Functional" })
+ public void testGetMappedCodons()
{
final Sequence seq1 = new Sequence("Seq1", "c-G-TA-gC-gT-T");
seq1.createDatasetSequence();
- final Sequence aseq1 = new Sequence("Seq1", "-P-R");
+ final Sequence aseq1 = new Sequence("Seq1", "-V-L");
aseq1.createDatasetSequence();
/*
@@ -124,19 +150,331 @@ public class AlignedCodonFrameTest
*/
AlignedCodonFrame acf = new AlignedCodonFrame();
- assertNull(acf.getMappedCodon(seq1.getDatasetSequence(), 0));
+ assertNull(acf.getMappedCodons(seq1.getDatasetSequence(), 0));
+
+ /*
+ * Set up the mappings for the exons (upper-case bases)
+ */
+ MapList map = new MapList(new int[] { 2, 4, 6, 6, 8, 9 }, new int[] {
+ 1, 2 }, 3, 1);
+ acf.addMap(seq1.getDatasetSequence(), aseq1.getDatasetSequence(), map);
+
+ assertEquals(1, acf.getMappedCodons(aseq1.getDatasetSequence(), 1)
+ .size());
+ assertEquals(
+ "[G, T, A]",
+ Arrays.toString(acf.getMappedCodons(aseq1.getDatasetSequence(),
+ 1).get(0)));
+ assertEquals(
+ "[C, T, T]",
+ Arrays.toString(acf.getMappedCodons(aseq1.getDatasetSequence(),
+ 2).get(0)));
+ }
+
+ /**
+ * Test for the case where there is more than one variant of the DNA mapping
+ * to a protein sequence
+ */
+ @Test(groups = { "Functional" })
+ public void testGetMappedCodons_dnaVariants()
+ {
+ final Sequence seq1 = new Sequence("Seq1", "c-G-TA-gC-gT-T");
+ seq1.createDatasetSequence();
+ final Sequence seq2 = new Sequence("Seq2", "c-G-TT-gT-gT-A");
+ seq2.createDatasetSequence();
+ final Sequence aseq1 = new Sequence("Seq1", "-V-L");
+ aseq1.createDatasetSequence();
+
+ AlignedCodonFrame acf = new AlignedCodonFrame();
/*
* Set up the mappings for the exons (upper-case bases)
*/
- MapList map = new MapList(new int[]
- { 2, 4, 6, 6, 8, 9 }, new int[]
- { 1, 2 }, 3, 1);
+ MapList map = new MapList(new int[] { 2, 4, 6, 6, 8, 9 }, new int[] {
+ 1, 2 }, 3, 1);
+ acf.addMap(seq1.getDatasetSequence(), aseq1.getDatasetSequence(), map);
+ acf.addMap(seq2.getDatasetSequence(), aseq1.getDatasetSequence(), map);
+
+ assertEquals(2, acf.getMappedCodons(aseq1.getDatasetSequence(), 1)
+ .size());
+ List codonsForV = acf.getMappedCodons(
+ aseq1.getDatasetSequence(), 1);
+ assertEquals("[G, T, A]", Arrays.toString(codonsForV.get(0)));
+ assertEquals("[G, T, T]", Arrays.toString(codonsForV.get(1)));
+ List codonsForL = acf.getMappedCodons(
+ aseq1.getDatasetSequence(), 2);
+ assertEquals("[C, T, T]", Arrays.toString(codonsForL.get(0)));
+ assertEquals("[T, T, A]", Arrays.toString(codonsForL.get(1)));
+ }
+
+ /**
+ * Test for the case where sequences have start > 1
+ */
+ @Test(groups = { "Functional" })
+ public void testGetMappedCodons_forSubSequences()
+ {
+ final Sequence seq1 = new Sequence("Seq1", "c-G-TA-gC-gT-T", 27, 35);
+ seq1.createDatasetSequence();
+
+ final Sequence aseq1 = new Sequence("Seq1", "-V-L", 12, 13);
+ aseq1.createDatasetSequence();
+
+ /*
+ * Set up the mappings for the exons (upper-case bases)
+ */
+ AlignedCodonFrame acf = new AlignedCodonFrame();
+ MapList map = new MapList(new int[] { 28, 30, 32, 32, 34, 35 },
+ new int[] { 12, 13 }, 3, 1);
+ acf.addMap(seq1.getDatasetSequence(), aseq1.getDatasetSequence(), map);
+
+ assertEquals(
+ "[G, T, A]",
+ Arrays.toString(acf.getMappedCodons(aseq1.getDatasetSequence(),
+ 12).get(0)));
+ assertEquals(
+ "[C, T, T]",
+ Arrays.toString(acf.getMappedCodons(aseq1.getDatasetSequence(),
+ 13).get(0)));
+ }
+
+ @Test(groups = { "Functional" })
+ public void testCouldReplaceSequence()
+ {
+ SequenceI seq1 = new Sequence("Seq1/10-21", "aaacccgggttt");
+ SequenceI seq1proxy = new SequenceDummy("Seq1");
+
+ // map to region within sequence is ok
+ assertTrue(AlignedCodonFrame.couldRealiseSequence(seq1proxy, seq1, 12,
+ 17));
+ // map to region overlapping sequence is ok
+ assertTrue(AlignedCodonFrame.couldRealiseSequence(seq1proxy, seq1, 5,
+ 10));
+ assertTrue(AlignedCodonFrame.couldRealiseSequence(seq1proxy, seq1, 21,
+ 26));
+ // map to region before sequence is not ok
+ assertFalse(AlignedCodonFrame.couldRealiseSequence(seq1proxy, seq1, 4,
+ 9));
+ // map to region after sequence is not ok
+ assertFalse(AlignedCodonFrame.couldRealiseSequence(seq1proxy, seq1, 22,
+ 27));
+
+ /*
+ * test should fail if name doesn't match
+ */
+ seq1proxy.setName("Seq1a");
+ assertFalse(AlignedCodonFrame.couldRealiseSequence(seq1proxy, seq1, 12,
+ 17));
+ seq1proxy.setName("Seq1");
+ seq1.setName("Seq1a");
+ assertFalse(AlignedCodonFrame.couldRealiseSequence(seq1proxy, seq1, 12,
+ 17));
+
+ /*
+ * a dummy sequence can't replace a real one
+ */
+ assertFalse(AlignedCodonFrame.couldRealiseSequence(seq1, seq1proxy, 12,
+ 17));
+
+ /*
+ * a dummy sequence can't replace a dummy sequence
+ */
+ SequenceI seq1proxy2 = new SequenceDummy("Seq1");
+ assertFalse(AlignedCodonFrame.couldRealiseSequence(seq1proxy,
+ seq1proxy2, 12, 17));
+
+ /*
+ * a real sequence can't replace a real one
+ */
+ SequenceI seq1a = new Sequence("Seq1/10-21", "aaacccgggttt");
+ assertFalse(AlignedCodonFrame.couldRealiseSequence(seq1, seq1a, 12, 17));
+ }
+
+ /**
+ * Tests for the method that tests whether any mapping to a dummy sequence can
+ * be 'realised' to a given real sequence
+ */
+ @Test(groups = { "Functional" })
+ public void testIsRealisableWith()
+ {
+ SequenceI seq1 = new Sequence("Seq1", "tttaaaCCCGGGtttaaa");
+ SequenceI seq2 = new Sequence("Seq2", "PG");
+ SequenceI seq1proxy = new SequenceDummy("Seq1");
+ seq1.createDatasetSequence();
+ seq2.createDatasetSequence();
+ MapList mapList = new MapList(new int[] { 7, 12 }, new int[] { 2, 3 },
+ 3, 1);
+ AlignedCodonFrame acf = new AlignedCodonFrame();
+ acf.addMap(seq1proxy, seq2, mapList);
+
+ /*
+ * Seq2 is mapped to SequenceDummy seq1proxy bases 4-9
+ * This is 'realisable' from real sequence Seq1
+ */
+ assertTrue(acf.isRealisableWith(seq1));
+
+ /*
+ * test should fail if name doesn't match
+ */
+ seq1proxy.setName("Seq1a");
+ assertFalse(acf.isRealisableWith(seq1));
+ seq1proxy.setName("Seq1");
+
+ SequenceI seq1ds = seq1.getDatasetSequence();
+ seq1ds.setName("Seq1a");
+ assertFalse(acf.isRealisableWith(seq1));
+ seq1ds.setName("Seq1");
+
+ /*
+ * test should fail if no sequence overlap with mapping of bases 7-12
+ * use artificial start/end values to test this
+ */
+ seq1ds.setStart(1);
+ seq1ds.setEnd(6);
+ // seq1 precedes mapped region:
+ assertFalse(acf.isRealisableWith(seq1));
+ seq1ds.setEnd(7);
+ // seq1 includes first mapped base:
+ assertTrue(acf.isRealisableWith(seq1));
+ seq1ds.setStart(13);
+ seq1ds.setEnd(18);
+ // seq1 follows mapped region:
+ assertFalse(acf.isRealisableWith(seq1));
+ seq1ds.setStart(12);
+ // seq1 includes last mapped base:
+ assertTrue(acf.isRealisableWith(seq1));
+ }
+
+ /**
+ * Tests for the method that converts mappings to a dummy sequence to mappings
+ * to a compatible real sequence
+ */
+ @Test(groups = { "Functional" })
+ public void testRealiseWith()
+ {
+ SequenceI seq1 = new Sequence("Seq1", "tttCAACCCGGGtttaaa");
+ SequenceI seq2 = new Sequence("Seq2", "QPG");
+ SequenceI seq2a = new Sequence("Seq2a", "QPG");
+ SequenceI seq1proxy = new SequenceDummy("Seq1");
+ seq1.createDatasetSequence();
+ seq2.createDatasetSequence();
+ seq2a.createDatasetSequence();
+
+ /*
+ * Make mappings from Seq2 and Seq2a peptides to dummy sequence Seq1
+ */
+ AlignedCodonFrame acf = new AlignedCodonFrame();
+
+ // map PG to codons 7-12 (CCCGGG)
+ MapList mapping1 = new MapList(new int[] { 7, 12 }, new int[] { 2, 3 },
+ 3, 1);
+ acf.addMap(seq1proxy, seq2, mapping1);
+ acf.addMap(seq1proxy, seq2a, mapping1);
+
+ // map QP to codons 4-9 (CAACCC)
+ MapList mapping2 = new MapList(new int[] { 4, 9 }, new int[] { 1, 2 },
+ 3, 1);
+ acf.addMap(seq1proxy, seq2, mapping2);
+ acf.addMap(seq1proxy, seq2a, mapping2);
+
+ /*
+ * acf now has two mappings one from Seq1 to Seq2, one from Seq1 to Seq2a
+ */
+ assertEquals(2, acf.getdnaSeqs().length);
+ assertSame(seq1proxy, acf.getdnaSeqs()[0]);
+ assertSame(seq1proxy, acf.getdnaSeqs()[1]);
+ assertEquals(2, acf.getProtMappings().length);
+
+ // 'realise' these mappings with the compatible sequence seq1
+ // two mappings should be updated:
+ assertEquals(2, acf.realiseWith(seq1));
+ assertSame(seq1.getDatasetSequence(), acf.getdnaSeqs()[0]);
+ assertSame(seq1.getDatasetSequence(), acf.getdnaSeqs()[1]);
+ }
+
+ /**
+ * Test the method that locates the mapped codon for a protein position.
+ */
+ @Test(groups = { "Functional" })
+ public void testGetMappedRegion_eitherWay()
+ {
+ final Sequence seq1 = new Sequence("Seq1", "AAACCCGGGTTT");
+ seq1.createDatasetSequence();
+ final Sequence seq2 = new Sequence("Seq2", "KPGF");
+ seq2.createDatasetSequence();
+ final Sequence seq3 = new Sequence("Seq3", "QYKPGFSW");
+ seq3.createDatasetSequence();
+
+ /*
+ * map Seq1 to all of Seq2 and part of Seq3
+ */
+ AlignedCodonFrame acf = new AlignedCodonFrame();
+ MapList map = new MapList(new int[] { 1, 12 }, new int[] { 1, 4 }, 3, 1);
+ acf.addMap(seq1.getDatasetSequence(), seq2.getDatasetSequence(), map);
+ map = new MapList(new int[] { 1, 12 }, new int[] { 3, 6 }, 3, 1);
+ acf.addMap(seq1.getDatasetSequence(), seq3.getDatasetSequence(), map);
+
+ /*
+ * map part of Seq3 to Seq2
+ */
+ map = new MapList(new int[] { 3, 6 }, new int[] { 1, 4 }, 1, 1);
+ acf.addMap(seq3.getDatasetSequence(), seq2.getDatasetSequence(), map);
+
+ /*
+ * original case - locate mapped codon for protein position
+ */
+ assertArrayEquals(new int[] { 4, 6 },
+ acf.getMappedRegion(seq1, seq2, 2));
+ assertArrayEquals(new int[] { 7, 9 },
+ acf.getMappedRegion(seq1, seq3, 5));
+ assertNull(acf.getMappedRegion(seq1, seq3, 1));
+
+ /*
+ * locate mapped protein for protein position
+ */
+ assertArrayEquals(new int[] { 4, 4 },
+ acf.getMappedRegion(seq3, seq2, 2));
+
+ /*
+ * reverse location protein-to-protein
+ */
+ assertArrayEquals(new int[] { 2, 2 },
+ acf.getMappedRegion(seq2, seq3, 4));
+
+ /*
+ * reverse location protein-from-nucleotide
+ * any of codon [4, 5, 6] positions map to seq2/2
+ */
+ assertArrayEquals(new int[] { 2, 2 },
+ acf.getMappedRegion(seq2, seq1, 4));
+ assertArrayEquals(new int[] { 2, 2 },
+ acf.getMappedRegion(seq2, seq1, 5));
+ assertArrayEquals(new int[] { 2, 2 },
+ acf.getMappedRegion(seq2, seq1, 6));
+ }
+
+ /**
+ * Tests for addMap. See also tests for MapList.addMapList
+ */
+ @Test(groups = { "Functional" })
+ public void testAddMap()
+ {
+ final Sequence seq1 = new Sequence("Seq1", "c-G-TA-gC-gT-T");
+ seq1.createDatasetSequence();
+ final Sequence aseq1 = new Sequence("Seq1", "-V-L");
+ aseq1.createDatasetSequence();
+
+ AlignedCodonFrame acf = new AlignedCodonFrame();
+ MapList map = new MapList(new int[] { 2, 4, 6, 6, 8, 9 }, new int[] {
+ 1, 2 }, 3, 1);
+ acf.addMap(seq1.getDatasetSequence(), aseq1.getDatasetSequence(), map);
+ assertEquals(1, acf.getMappingsFromSequence(seq1).size());
+ Mapping before = acf.getMappingsFromSequence(seq1).get(0);
+
+ /*
+ * add the same map again, verify it doesn't get duplicated
+ */
acf.addMap(seq1.getDatasetSequence(), aseq1.getDatasetSequence(), map);
-
- assertEquals("[G, T, A]", Arrays.toString(acf.getMappedCodon(
- aseq1.getDatasetSequence(), 1)));
- assertEquals("[C, T, T]", Arrays.toString(acf.getMappedCodon(
- aseq1.getDatasetSequence(), 2)));
+ assertEquals(1, acf.getMappingsFromSequence(seq1).size());
+ assertSame(before, acf.getMappingsFromSequence(seq1).get(0));
}
}