import jalview.io.FileFormat;
import jalview.io.FileFormatI;
import jalview.io.FormatAdapter;
+import jalview.io.gff.SequenceOntologyI;
import jalview.util.MapList;
import jalview.util.MappingUtils;
@Test(groups = { "Functional" })
public void testMapProteinAlignmentToCdna_noXrefs() throws IOException
{
- List<SequenceI> protseqs = new ArrayList<SequenceI>();
+ List<SequenceI> protseqs = new ArrayList<>();
protseqs.add(new Sequence("UNIPROT|V12345", "EIQ"));
protseqs.add(new Sequence("UNIPROT|V12346", "EIQ"));
protseqs.add(new Sequence("UNIPROT|V12347", "SAR"));
AlignmentI protein = new Alignment(protseqs.toArray(new SequenceI[3]));
protein.setDataset(null);
- List<SequenceI> dnaseqs = new ArrayList<SequenceI>();
+ List<SequenceI> dnaseqs = new ArrayList<>();
dnaseqs.add(new Sequence("EMBL|A11111", "TCAGCACGC")); // = SAR
dnaseqs.add(new Sequence("EMBL|A22222", "GAGATACAA")); // = EIQ
dnaseqs.add(new Sequence("EMBL|A33333", "GAAATCCAG")); // = EIQ
acf.addMap(dna1.getDatasetSequence(), prot1.getDatasetSequence(), map);
acf.addMap(dna2.getDatasetSequence(), prot2.getDatasetSequence(), map);
acf.addMap(dna3.getDatasetSequence(), prot3.getDatasetSequence(), map);
- ArrayList<AlignedCodonFrame> acfs = new ArrayList<AlignedCodonFrame>();
+ ArrayList<AlignedCodonFrame> acfs = new ArrayList<>();
acfs.add(acf);
protein.setCodonFrames(acfs);
public void testMapProteinAlignmentToCdna_withStartAndStopCodons()
throws IOException
{
- List<SequenceI> protseqs = new ArrayList<SequenceI>();
+ List<SequenceI> protseqs = new ArrayList<>();
protseqs.add(new Sequence("UNIPROT|V12345", "EIQ"));
protseqs.add(new Sequence("UNIPROT|V12346", "EIQ"));
protseqs.add(new Sequence("UNIPROT|V12347", "SAR"));
AlignmentI protein = new Alignment(protseqs.toArray(new SequenceI[3]));
protein.setDataset(null);
- List<SequenceI> dnaseqs = new ArrayList<SequenceI>();
+ List<SequenceI> dnaseqs = new ArrayList<>();
// start + SAR:
dnaseqs.add(new Sequence("EMBL|A11111", "ATGTCAGCACGC"));
// = EIQ + stop
@Test(groups = { "Functional" })
public void testMapProteinAlignmentToCdna_withXrefs() throws IOException
{
- List<SequenceI> protseqs = new ArrayList<SequenceI>();
+ List<SequenceI> protseqs = new ArrayList<>();
protseqs.add(new Sequence("UNIPROT|V12345", "EIQ"));
protseqs.add(new Sequence("UNIPROT|V12346", "EIQ"));
protseqs.add(new Sequence("UNIPROT|V12347", "SAR"));
AlignmentI protein = new Alignment(protseqs.toArray(new SequenceI[3]));
protein.setDataset(null);
- List<SequenceI> dnaseqs = new ArrayList<SequenceI>();
+ List<SequenceI> dnaseqs = new ArrayList<>();
dnaseqs.add(new Sequence("EMBL|A11111", "TCAGCACGC")); // = SAR
dnaseqs.add(new Sequence("EMBL|A22222", "ATGGAGATACAA")); // = start + EIQ
dnaseqs.add(new Sequence("EMBL|A33333", "GAAATCCAG")); // = EIQ
public void testMapProteinAlignmentToCdna_prioritiseXrefs()
throws IOException
{
- List<SequenceI> protseqs = new ArrayList<SequenceI>();
+ List<SequenceI> protseqs = new ArrayList<>();
protseqs.add(new Sequence("UNIPROT|V12345", "EIQ"));
protseqs.add(new Sequence("UNIPROT|V12346", "EIQ"));
AlignmentI protein = new Alignment(
protseqs.toArray(new SequenceI[protseqs.size()]));
protein.setDataset(null);
- List<SequenceI> dnaseqs = new ArrayList<SequenceI>();
+ List<SequenceI> dnaseqs = new ArrayList<>();
dnaseqs.add(new Sequence("EMBL|A11111", "GAAATCCAG")); // = EIQ
dnaseqs.add(new Sequence("EMBL|A22222", "GAAATTCAG")); // = EIQ
AlignmentI cdna = new Alignment(dnaseqs.toArray(new SequenceI[dnaseqs
al.addAnnotation(ann4); // Temp for seq1
al.addAnnotation(ann5); // Temp for seq2
al.addAnnotation(ann6); // Temp for no sequence
- List<String> types = new ArrayList<String>();
- List<SequenceI> scope = new ArrayList<SequenceI>();
+ List<String> types = new ArrayList<>();
+ List<SequenceI> scope = new ArrayList<>();
/*
* Set all sequence related Structure to hidden (ann1, ann2)
map = new MapList(new int[] { 9, 11 }, new int[] { 2, 2 }, 3, 1);
acf.addMap(dna3.getDatasetSequence(), prot3.getDatasetSequence(), map);
- ArrayList<AlignedCodonFrame> acfs = new ArrayList<AlignedCodonFrame>();
+ ArrayList<AlignedCodonFrame> acfs = new ArrayList<>();
acfs.add(acf);
protein.setCodonFrames(acfs);
sf6.setValue("alleles", "g, a"); // should force to upper-case
sf6.setValue("ID", "sequence_variant:rs758803216");
dna.addSequenceFeature(sf6);
+
SequenceFeature sf7 = new SequenceFeature("sequence_variant", "", 15,
15, 0f, null);
sf7.setValue("alleles", "A, T");
* variants:
* GAA -> E source: Ensembl
* CAA -> Q source: dbSNP
+ * TAA -> STOP source: dnSNP
* AAG synonymous source: COSMIC
* AAT -> N source: Ensembl
* ...TTC synonymous source: dbSNP
String ensembl = "Ensembl";
String dbSnp = "dbSNP";
String cosmic = "COSMIC";
+
+ /*
+ * NB setting "id" (as returned by Ensembl for features in JSON format);
+ * previously "ID" (as returned for GFF3 format)
+ */
SequenceFeature sf1 = new SequenceFeature("sequence_variant", "", 1, 1,
0f, ensembl);
- sf1.setValue("alleles", "A,G"); // GAA -> E
- sf1.setValue("ID", "var1.125A>G");
+ sf1.setValue("alleles", "A,G"); // AAA -> GAA -> K/E
+ sf1.setValue("id", "var1.125A>G");
+
SequenceFeature sf2 = new SequenceFeature("sequence_variant", "", 1, 1,
0f, dbSnp);
- sf2.setValue("alleles", "A,C"); // CAA -> Q
- sf2.setValue("ID", "var2");
+ sf2.setValue("alleles", "A,C"); // AAA -> CAA -> K/Q
+ sf2.setValue("id", "var2");
sf2.setValue("clinical_significance", "Dodgy");
- SequenceFeature sf3 = new SequenceFeature("sequence_variant", "", 3, 3,
- 0f, cosmic);
- sf3.setValue("alleles", "A,G"); // synonymous
- sf3.setValue("ID", "var3");
- sf3.setValue("clinical_significance", "None");
+
+ SequenceFeature sf3 = new SequenceFeature("sequence_variant", "", 1, 1,
+ 0f, dbSnp);
+ sf3.setValue("alleles", "A,T"); // AAA -> TAA -> stop codon
+ sf3.setValue("id", "var3");
+ sf3.setValue("clinical_significance", "Bad");
+
SequenceFeature sf4 = new SequenceFeature("sequence_variant", "", 3, 3,
+ 0f, cosmic);
+ sf4.setValue("alleles", "A,G"); // AAA -> AAG synonymous
+ sf4.setValue("id", "var4");
+ sf4.setValue("clinical_significance", "None");
+
+ SequenceFeature sf5 = new SequenceFeature("sequence_variant", "", 3, 3,
0f, ensembl);
- sf4.setValue("alleles", "A,T"); // AAT -> N
- sf4.setValue("ID", "sequence_variant:var4"); // prefix gets stripped off
- sf4.setValue("clinical_significance", "Benign");
- SequenceFeature sf5 = new SequenceFeature("sequence_variant", "", 6, 6,
+ sf5.setValue("alleles", "A,T"); // AAA -> AAT -> K/N
+ sf5.setValue("id", "sequence_variant:var5"); // prefix gets stripped off
+ sf5.setValue("clinical_significance", "Benign");
+
+ SequenceFeature sf6 = new SequenceFeature("sequence_variant", "", 6, 6,
0f, dbSnp);
- sf5.setValue("alleles", "T,C"); // synonymous
- sf5.setValue("ID", "var5");
- sf5.setValue("clinical_significance", "Bad");
- SequenceFeature sf6 = new SequenceFeature("sequence_variant", "", 8, 8,
+ sf6.setValue("alleles", "T,C"); // TTT -> TTC synonymous
+ sf6.setValue("id", "var6");
+
+ SequenceFeature sf7 = new SequenceFeature("sequence_variant", "", 8, 8,
0f, cosmic);
- sf6.setValue("alleles", "C,A,G"); // CAC,CGC -> H,R
- sf6.setValue("ID", "var6");
- sf6.setValue("clinical_significance", "Good");
+ sf7.setValue("alleles", "C,A,G"); // CCC -> CAC,CGC -> P/H/R
+ sf7.setValue("id", "var7");
+ sf7.setValue("clinical_significance", "Good");
+
+ List<DnaVariant> codon1Variants = new ArrayList<>();
+ List<DnaVariant> codon2Variants = new ArrayList<>();
+ List<DnaVariant> codon3Variants = new ArrayList<>();
- List<DnaVariant> codon1Variants = new ArrayList<DnaVariant>();
- List<DnaVariant> codon2Variants = new ArrayList<DnaVariant>();
- List<DnaVariant> codon3Variants = new ArrayList<DnaVariant>();
List<DnaVariant> codonVariants[] = new ArrayList[3];
codonVariants[0] = codon1Variants;
codonVariants[1] = codon2Variants;
*/
codon1Variants.add(new DnaVariant("A", sf1));
codon1Variants.add(new DnaVariant("A", sf2));
+ codon1Variants.add(new DnaVariant("A", sf3));
codon2Variants.add(new DnaVariant("A"));
- codon2Variants.add(new DnaVariant("A"));
- codon3Variants.add(new DnaVariant("A", sf3));
+ // codon2Variants.add(new DnaVariant("A"));
codon3Variants.add(new DnaVariant("A", sf4));
+ codon3Variants.add(new DnaVariant("A", sf5));
AlignmentUtils.computePeptideVariants(peptide, 1, codonVariants);
/*
codon3Variants.clear();
codon1Variants.add(new DnaVariant("T"));
codon2Variants.add(new DnaVariant("T"));
- codon3Variants.add(new DnaVariant("T", sf5));
+ codon3Variants.add(new DnaVariant("T", sf6));
AlignmentUtils.computePeptideVariants(peptide, 2, codonVariants);
/*
codon2Variants.clear();
codon3Variants.clear();
codon1Variants.add(new DnaVariant("C"));
- codon2Variants.add(new DnaVariant("C", sf6));
+ codon2Variants.add(new DnaVariant("C", sf7));
codon3Variants.add(new DnaVariant("C"));
AlignmentUtils.computePeptideVariants(peptide, 3, codonVariants);
* verify added sequence features for
* var1 K -> E Ensembl
* var2 K -> Q dbSNP
- * var4 K -> N Ensembl
- * var6 P -> H COSMIC
- * var6 P -> R COSMIC
+ * var3 K -> stop
+ * var4 synonymous
+ * var5 K -> N Ensembl
+ * var6 synonymous
+ * var7 P -> H COSMIC
+ * var8 P -> R COSMIC
*/
List<SequenceFeature> sfs = peptide.getSequenceFeatures();
SequenceFeatures.sortFeatures(sfs, true);
- assertEquals(5, sfs.size());
+ assertEquals(8, sfs.size());
/*
* features are sorted by start position ascending, but in no
* particular order where start positions match; asserts here
* simply match the data returned (the order is not important)
*/
+ // AAA -> AAT -> K/N
SequenceFeature sf = sfs.get(0);
assertEquals(1, sf.getBegin());
assertEquals(1, sf.getEnd());
+ assertEquals("nonsynonymous_variant", sf.getType());
assertEquals("p.Lys1Asn", sf.getDescription());
- assertEquals("var4", sf.getValue("ID"));
+ assertEquals("var5", sf.getValue("id"));
assertEquals("Benign", sf.getValue("clinical_significance"));
- assertEquals("ID=var4;clinical_significance=Benign", sf.getAttributes());
+ assertEquals("id=var5;clinical_significance=Benign",
+ sf.getAttributes());
assertEquals(1, sf.links.size());
assertEquals(
- "p.Lys1Asn var4|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var4",
+ "p.Lys1Asn var5|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var5",
sf.links.get(0));
assertEquals(ensembl, sf.getFeatureGroup());
+ // AAA -> CAA -> K/Q
sf = sfs.get(1);
assertEquals(1, sf.getBegin());
assertEquals(1, sf.getEnd());
+ assertEquals("nonsynonymous_variant", sf.getType());
assertEquals("p.Lys1Gln", sf.getDescription());
- assertEquals("var2", sf.getValue("ID"));
+ assertEquals("var2", sf.getValue("id"));
assertEquals("Dodgy", sf.getValue("clinical_significance"));
- assertEquals("ID=var2;clinical_significance=Dodgy", sf.getAttributes());
+ assertEquals("id=var2;clinical_significance=Dodgy", sf.getAttributes());
assertEquals(1, sf.links.size());
assertEquals(
"p.Lys1Gln var2|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var2",
sf.links.get(0));
assertEquals(dbSnp, sf.getFeatureGroup());
+ // AAA -> GAA -> K/E
sf = sfs.get(2);
assertEquals(1, sf.getBegin());
assertEquals(1, sf.getEnd());
+ assertEquals("nonsynonymous_variant", sf.getType());
assertEquals("p.Lys1Glu", sf.getDescription());
- assertEquals("var1.125A>G", sf.getValue("ID"));
+ assertEquals("var1.125A>G", sf.getValue("id"));
assertNull(sf.getValue("clinical_significance"));
- assertEquals("ID=var1.125A>G", sf.getAttributes());
+ assertEquals("id=var1.125A>G", sf.getAttributes());
assertEquals(1, sf.links.size());
// link to variation is urlencoded
assertEquals(
sf.links.get(0));
assertEquals(ensembl, sf.getFeatureGroup());
+ // AAA -> TAA -> stop codon
sf = sfs.get(3);
+ assertEquals(1, sf.getBegin());
+ assertEquals(1, sf.getEnd());
+ assertEquals("stop_gained", sf.getType());
+ assertEquals("Aaa/Taa", sf.getDescription());
+ assertEquals("var3", sf.getValue("id"));
+ assertEquals("Bad", sf.getValue("clinical_significance"));
+ assertEquals("id=var3;clinical_significance=Bad", sf.getAttributes());
+ assertEquals(1, sf.links.size());
+ assertEquals(
+ "Aaa/Taa var3|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var3",
+ sf.links.get(0));
+ assertEquals(dbSnp, sf.getFeatureGroup());
+
+ // AAA -> AAG synonymous
+ sf = sfs.get(4);
+ assertEquals(1, sf.getBegin());
+ assertEquals(1, sf.getEnd());
+ assertEquals("synonymous_variant", sf.getType());
+ assertEquals("aaA/aaG", sf.getDescription());
+ assertEquals("var4", sf.getValue("id"));
+ assertEquals("None", sf.getValue("clinical_significance"));
+ assertEquals("id=var4;clinical_significance=None", sf.getAttributes());
+ assertEquals(1, sf.links.size());
+ assertEquals(
+ "aaA/aaG var4|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var4",
+ sf.links.get(0));
+ assertEquals(cosmic, sf.getFeatureGroup());
+
+ // TTT -> TTC synonymous
+ sf = sfs.get(5);
+ assertEquals(2, sf.getBegin());
+ assertEquals(2, sf.getEnd());
+ assertEquals("synonymous_variant", sf.getType());
+ assertEquals("ttT/ttC", sf.getDescription());
+ assertEquals("var6", sf.getValue("id"));
+ assertNull(sf.getValue("clinical_significance"));
+ assertEquals("id=var6", sf.getAttributes());
+ assertEquals(1, sf.links.size());
+ assertEquals(
+ "ttT/ttC var6|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var6",
+ sf.links.get(0));
+ assertEquals(dbSnp, sf.getFeatureGroup());
+
+ // var7 generates two distinct protein variant features (two alleles)
+ // CCC -> CGC -> P/R
+ sf = sfs.get(6);
assertEquals(3, sf.getBegin());
assertEquals(3, sf.getEnd());
+ assertEquals("nonsynonymous_variant", sf.getType());
assertEquals("p.Pro3Arg", sf.getDescription());
- assertEquals("var6", sf.getValue("ID"));
+ assertEquals("var7", sf.getValue("id"));
assertEquals("Good", sf.getValue("clinical_significance"));
- assertEquals("ID=var6;clinical_significance=Good", sf.getAttributes());
+ assertEquals("id=var7;clinical_significance=Good", sf.getAttributes());
assertEquals(1, sf.links.size());
assertEquals(
- "p.Pro3Arg var6|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var6",
+ "p.Pro3Arg var7|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var7",
sf.links.get(0));
assertEquals(cosmic, sf.getFeatureGroup());
- // var5 generates two distinct protein variant features
- sf = sfs.get(4);
+ // CCC -> CAC -> P/H
+ sf = sfs.get(7);
assertEquals(3, sf.getBegin());
assertEquals(3, sf.getEnd());
+ assertEquals("nonsynonymous_variant", sf.getType());
assertEquals("p.Pro3His", sf.getDescription());
- assertEquals("var6", sf.getValue("ID"));
+ assertEquals("var7", sf.getValue("id"));
assertEquals("Good", sf.getValue("clinical_significance"));
- assertEquals("ID=var6;clinical_significance=Good", sf.getAttributes());
+ assertEquals("id=var7;clinical_significance=Good", sf.getAttributes());
assertEquals(1, sf.links.size());
assertEquals(
- "p.Pro3His var6|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var6",
+ "p.Pro3His var7|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var7",
sf.links.get(0));
assertEquals(cosmic, sf.getFeatureGroup());
}
seq1.createDatasetSequence();
Mapping mapping = new Mapping(seq1, new MapList(
new int[] { 3, 6, 9, 10 }, new int[] { 1, 6 }, 1, 1));
- Map<Integer, Map<SequenceI, Character>> map = new TreeMap<Integer, Map<SequenceI, Character>>();
+ Map<Integer, Map<SequenceI, Character>> map = new TreeMap<>();
AlignmentUtils.addMappedPositions(seq1, from, mapping, map);
/*
seq1.createDatasetSequence();
Mapping mapping = new Mapping(seq1, new MapList(
new int[] { 3, 6, 9, 10 }, new int[] { 1, 6 }, 1, 1));
- Map<Integer, Map<SequenceI, Character>> map = new TreeMap<Integer, Map<SequenceI, Character>>();
+ Map<Integer, Map<SequenceI, Character>> map = new TreeMap<>();
AlignmentUtils.addMappedPositions(seq1, from, mapping, map);
/*
assertEquals(2, toMap.getFromRanges().get(0).length);
assertEquals(1, toMap.getFromRanges().get(0)[0]);
assertEquals(12, toMap.getFromRanges().get(0)[1]);
- assertEquals(1, toMap.getToRanges().size());
- assertEquals(4, toMap.getToRanges().get(0).length);
+ assertEquals(2, toMap.getToRanges().size());
+ assertEquals(2, toMap.getToRanges().get(0).length);
assertEquals(158, toMap.getToRanges().get(0)[0]);
assertEquals(164, toMap.getToRanges().get(0)[1]);
- assertEquals(210, toMap.getToRanges().get(0)[2]);
- assertEquals(214, toMap.getToRanges().get(0)[3]);
+ assertEquals(210, toMap.getToRanges().get(1)[0]);
+ assertEquals(214, toMap.getToRanges().get(1)[1]);
// or summarised as (but toString might change in future):
- assertEquals("[ [1, 12] ] 1:1 to [ [158, 164, 210, 214] ]",
+ assertEquals("[ [1, 12] ] 1:1 to [ [158, 164] [210, 214] ]",
toMap.toString());
/*
assertEquals("GRCh38", toLoci.getAssemblyId());
assertEquals("7", toLoci.getChromosomeId());
toMap = toLoci.getMap();
- assertEquals("[ [1, 12] ] 1:1 to [ [158, 164, 210, 214] ]",
+ assertEquals("[ [1, 12] ] 1:1 to [ [158, 164] [210, 214] ]",
toMap.toString());
}
* Case 2: CDS 3 times length of peptide + stop codon
* (note code does not currently check trailing codon is a stop codon)
*/
- dna = new Sequence("dna", "AACGacgtCTCCTTGA");
+ dna = new Sequence("dna", "AACGacgtCTCCTCCC");
dna.createDatasetSequence();
dna.addSequenceFeature(new SequenceFeature("CDS", "", 1, 4, null));
dna.addSequenceFeature(new SequenceFeature("CDS", "", 9, 16, null));
Arrays.deepToString(ml.getFromRanges().toArray()));
/*
- * Case 3: CDS not 3 times length of peptide - no mapping is made
+ * Case 3: CDS longer than 3 * peptide + stop codon - no mapping is made
+ */
+ dna = new Sequence("dna", "AACGacgtCTCCTTGATCA");
+ dna.createDatasetSequence();
+ dna.addSequenceFeature(new SequenceFeature("CDS", "", 1, 4, null));
+ dna.addSequenceFeature(new SequenceFeature("CDS", "", 9, 19, null));
+ ml = AlignmentUtils.mapCdsToProtein(dna, peptide);
+ assertNull(ml);
+
+ /*
+ * Case 4: CDS shorter than 3 * peptide - no mapping is made
+ */
+ dna = new Sequence("dna", "AACGacgtCTCC");
+ dna.createDatasetSequence();
+ dna.addSequenceFeature(new SequenceFeature("CDS", "", 1, 4, null));
+ dna.addSequenceFeature(new SequenceFeature("CDS", "", 9, 12, null));
+ ml = AlignmentUtils.mapCdsToProtein(dna, peptide);
+ assertNull(ml);
+
+ /*
+ * Case 5: CDS 3 times length of peptide + part codon - mapping is truncated
*/
dna = new Sequence("dna", "AACGacgtCTCCTTG");
dna.createDatasetSequence();
dna.addSequenceFeature(new SequenceFeature("CDS", "", 1, 4, null));
dna.addSequenceFeature(new SequenceFeature("CDS", "", 9, 15, null));
ml = AlignmentUtils.mapCdsToProtein(dna, peptide);
- assertNull(ml);
+ assertEquals(3, ml.getFromRatio());
+ assertEquals(1, ml.getToRatio());
+ assertEquals("[[1, 3]]",
+ Arrays.deepToString(ml.getToRanges().toArray()));
+ assertEquals("[[1, 4], [9, 13]]",
+ Arrays.deepToString(ml.getFromRanges().toArray()));
/*
- * Case 4: incomplete start codon corresponding to X in peptide
+ * Case 6: incomplete start codon corresponding to X in peptide
*/
dna = new Sequence("dna", "ACGacgtCTCCTTGG");
dna.createDatasetSequence();
assertEquals("[[3, 3], [8, 12]]",
Arrays.deepToString(ml.getFromRanges().toArray()));
}
+
+ /**
+ * Tests for the method that locates the CDS sequence that has a mapping to
+ * the given protein. That is, given a transcript-to-peptide mapping, find the
+ * cds-to-peptide mapping that relates to both, and return the CDS sequence.
+ */
+ @Test
+ public void testFindCdsForProtein()
+ {
+ List<AlignedCodonFrame> mappings = new ArrayList<>();
+ AlignedCodonFrame acf1 = new AlignedCodonFrame();
+ mappings.add(acf1);
+
+ SequenceI dna1 = new Sequence("dna1", "cgatATcgGCTATCTATGacg");
+ dna1.createDatasetSequence();
+
+ // NB we currently exclude STOP codon from CDS sequences
+ // the test would need to change if this changes in future
+ SequenceI cds1 = new Sequence("cds1", "ATGCTATCT");
+ cds1.createDatasetSequence();
+
+ SequenceI pep1 = new Sequence("pep1", "MLS");
+ pep1.createDatasetSequence();
+ List<AlignedCodonFrame> seqMappings = new ArrayList<>();
+ MapList mapList = new MapList(
+ new int[]
+ { 5, 6, 9, 15 }, new int[] { 1, 3 }, 3, 1);
+ Mapping dnaToPeptide = new Mapping(pep1.getDatasetSequence(), mapList);
+
+ // add dna to peptide mapping
+ seqMappings.add(acf1);
+ acf1.addMap(dna1.getDatasetSequence(), pep1.getDatasetSequence(),
+ mapList);
+
+ /*
+ * first case - no dna-to-CDS mapping exists - search fails
+ */
+ SequenceI seq = AlignmentUtils.findCdsForProtein(mappings, dna1,
+ seqMappings, dnaToPeptide);
+ assertNull(seq);
+
+ /*
+ * second case - CDS-to-peptide mapping exists but no dna-to-CDS
+ * - search fails
+ */
+ // todo this test fails if the mapping is added to acf1, not acf2
+ // need to tidy up use of lists of mappings in AlignedCodonFrame
+ AlignedCodonFrame acf2 = new AlignedCodonFrame();
+ mappings.add(acf2);
+ MapList cdsToPeptideMapping = new MapList(new int[]
+ { 1, 9 }, new int[] { 1, 3 }, 3, 1);
+ acf2.addMap(cds1.getDatasetSequence(), pep1.getDatasetSequence(),
+ cdsToPeptideMapping);
+ assertNull(AlignmentUtils.findCdsForProtein(mappings, dna1, seqMappings,
+ dnaToPeptide));
+
+ /*
+ * third case - add dna-to-CDS mapping - CDS is now found!
+ */
+ MapList dnaToCdsMapping = new MapList(new int[] { 5, 6, 9, 15 },
+ new int[]
+ { 1, 9 }, 1, 1);
+ acf1.addMap(dna1.getDatasetSequence(), cds1.getDatasetSequence(),
+ dnaToCdsMapping);
+ seq = AlignmentUtils.findCdsForProtein(mappings, dna1, seqMappings,
+ dnaToPeptide);
+ assertSame(seq, cds1.getDatasetSequence());
+ }
+
+ /**
+ * Tests for the method that locates the CDS sequence that has a mapping to
+ * the given protein. That is, given a transcript-to-peptide mapping, find the
+ * cds-to-peptide mapping that relates to both, and return the CDS sequence.
+ * This test is for the case where transcript and CDS are the same length.
+ */
+ @Test
+ public void testFindCdsForProtein_noUTR()
+ {
+ List<AlignedCodonFrame> mappings = new ArrayList<>();
+ AlignedCodonFrame acf1 = new AlignedCodonFrame();
+ mappings.add(acf1);
+
+ SequenceI dna1 = new Sequence("dna1", "ATGCTATCTTAA");
+ dna1.createDatasetSequence();
+
+ // NB we currently exclude STOP codon from CDS sequences
+ // the test would need to change if this changes in future
+ SequenceI cds1 = new Sequence("cds1", "ATGCTATCT");
+ cds1.createDatasetSequence();
+
+ SequenceI pep1 = new Sequence("pep1", "MLS");
+ pep1.createDatasetSequence();
+ List<AlignedCodonFrame> seqMappings = new ArrayList<>();
+ MapList mapList = new MapList(
+ new int[]
+ { 1, 9 }, new int[] { 1, 3 }, 3, 1);
+ Mapping dnaToPeptide = new Mapping(pep1.getDatasetSequence(), mapList);
+
+ // add dna to peptide mapping
+ seqMappings.add(acf1);
+ acf1.addMap(dna1.getDatasetSequence(), pep1.getDatasetSequence(),
+ mapList);
+
+ /*
+ * first case - transcript lacks CDS features - it appears to be
+ * the CDS sequence and is returned
+ */
+ SequenceI seq = AlignmentUtils.findCdsForProtein(mappings, dna1,
+ seqMappings, dnaToPeptide);
+ assertSame(seq, dna1.getDatasetSequence());
+
+ /*
+ * second case - transcript has CDS feature - this means it is
+ * not returned as a match for CDS (CDS sequences don't have CDS features)
+ */
+ dna1.addSequenceFeature(
+ new SequenceFeature(SequenceOntologyI.CDS, "cds", 1, 12, null));
+ seq = AlignmentUtils.findCdsForProtein(mappings, dna1, seqMappings,
+ dnaToPeptide);
+ assertNull(seq);
+
+ /*
+ * third case - CDS-to-peptide mapping exists but no dna-to-CDS
+ * - search fails
+ */
+ // todo this test fails if the mapping is added to acf1, not acf2
+ // need to tidy up use of lists of mappings in AlignedCodonFrame
+ AlignedCodonFrame acf2 = new AlignedCodonFrame();
+ mappings.add(acf2);
+ MapList cdsToPeptideMapping = new MapList(new int[]
+ { 1, 9 }, new int[] { 1, 3 }, 3, 1);
+ acf2.addMap(cds1.getDatasetSequence(), pep1.getDatasetSequence(),
+ cdsToPeptideMapping);
+ assertNull(AlignmentUtils.findCdsForProtein(mappings, dna1, seqMappings,
+ dnaToPeptide));
+
+ /*
+ * fourth case - add dna-to-CDS mapping - CDS is now found!
+ */
+ MapList dnaToCdsMapping = new MapList(new int[] { 1, 9 },
+ new int[]
+ { 1, 9 }, 1, 1);
+ acf1.addMap(dna1.getDatasetSequence(), cds1.getDatasetSequence(),
+ dnaToCdsMapping);
+ seq = AlignmentUtils.findCdsForProtein(mappings, dna1, seqMappings,
+ dnaToPeptide);
+ assertSame(seq, cds1.getDatasetSequence());
+ }
}
git://source.jalview.org / jalview.git / blobdiff