{
for (String base : alleles.split(","))
{
- String codon = base + base2 + base3;
- if (addPeptideVariant(peptide, peptidePos, residue, var, codon))
+ if (!base1.equals(base))
{
- count++;
+ String codon = base + base2 + base3;
+ if (addPeptideVariant(peptide, peptidePos, residue, var,
+ codon))
+ {
+ count++;
+ }
}
}
}
{
for (String base : alleles.split(","))
{
- String codon = base1 + base + base3;
- if (addPeptideVariant(peptide, peptidePos, residue, var, codon))
+ if (!base2.equals(base))
{
- count++;
+ String codon = base1 + base + base3;
+ if (addPeptideVariant(peptide, peptidePos, residue, var,
+ codon))
+ {
+ count++;
+ }
}
}
}
{
for (String base : alleles.split(","))
{
- String codon = base1 + base2 + base;
- if (addPeptideVariant(peptide, peptidePos, residue, var, codon))
+ if (!base3.equals(base))
{
- count++;
+ String codon = base1 + base2 + base;
+ if (addPeptideVariant(peptide, peptidePos, residue, var,
+ codon))
+ {
+ count++;
+ }
}
}
}
* e.g. multibase variants or HGMD_MUTATION etc
* are currently ignored here
*/
- String trans = codon.contains("-") ? "-"
+ String trans = codon.contains("-") ? null
: (codon.length() > CODON_LENGTH ? null
: ResidueProperties.codonTranslate(codon));
- if (trans != null && !trans.equals(residue))
+ if (trans == null)
+ {
+ return false;
+ }
+ String desc = codon;
+ String featureType = "";
+ if (trans.equals(residue))
+ {
+ featureType = SequenceOntologyI.SYNONYMOUS_VARIANT;
+ }
+ else
{
String residue3Char = StringUtils
.toSentenceCase(ResidueProperties.aa2Triplet.get(residue));
String trans3Char = StringUtils
.toSentenceCase(ResidueProperties.aa2Triplet.get(trans));
- String desc = "p." + residue3Char + peptidePos + trans3Char;
- SequenceFeature sf = new SequenceFeature(
- SequenceOntologyI.SEQUENCE_VARIANT, desc, peptidePos,
- peptidePos, var.getSource());
- StringBuilder attributes = new StringBuilder(32);
- String id = (String) var.variant.getValue(ID);
- if (id != null)
- {
- if (id.startsWith(SEQUENCE_VARIANT))
- {
- id = id.substring(SEQUENCE_VARIANT.length());
- }
- sf.setValue(ID, id);
- attributes.append(ID).append("=").append(id);
- // TODO handle other species variants JAL-2064
- StringBuilder link = new StringBuilder(32);
- try
- {
- link.append(desc).append(" ").append(id).append(
- "|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=")
- .append(URLEncoder.encode(id, "UTF-8"));
- sf.addLink(link.toString());
- } catch (UnsupportedEncodingException e)
- {
- // as if
- }
- }
- String clinSig = (String) var.variant.getValue(CLINICAL_SIGNIFICANCE);
- if (clinSig != null)
+ desc = "p." + residue3Char + peptidePos + trans3Char;
+ featureType = SequenceOntologyI.NONSYNONYMOUS_VARIANT;
+ }
+ SequenceFeature sf = new SequenceFeature(featureType, desc, peptidePos,
+ peptidePos, var.getSource());
+
+ StringBuilder attributes = new StringBuilder(32);
+ String id = (String) var.variant.getValue(ID);
+ if (id != null)
+ {
+ if (id.startsWith(SEQUENCE_VARIANT))
{
- sf.setValue(CLINICAL_SIGNIFICANCE, clinSig);
- attributes.append(";").append(CLINICAL_SIGNIFICANCE).append("=")
- .append(clinSig);
+ id = id.substring(SEQUENCE_VARIANT.length());
}
- peptide.addSequenceFeature(sf);
- if (attributes.length() > 0)
+ sf.setValue(ID, id);
+ attributes.append(ID).append("=").append(id);
+ // TODO handle other species variants JAL-2064
+ StringBuilder link = new StringBuilder(32);
+ try
+ {
+ link.append(desc).append(" ").append(id).append(
+ "|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=")
+ .append(URLEncoder.encode(id, "UTF-8"));
+ sf.addLink(link.toString());
+ } catch (UnsupportedEncodingException e)
{
- sf.setAttributes(attributes.toString());
+ // as if
}
- return true;
}
- return false;
+ String clinSig = (String) var.variant.getValue(CLINICAL_SIGNIFICANCE);
+ if (clinSig != null)
+ {
+ sf.setValue(CLINICAL_SIGNIFICANCE, clinSig);
+ attributes.append(";").append(CLINICAL_SIGNIFICANCE).append("=")
+ .append(clinSig);
+ }
+ peptide.addSequenceFeature(sf);
+ if (attributes.length() > 0)
+ {
+ sf.setAttributes(attributes.toString());
+ }
+ return true;
}
/**
@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";
+
SequenceFeature sf1 = new SequenceFeature("sequence_variant", "", 1, 1,
0f, ensembl);
- sf1.setValue("alleles", "A,G"); // GAA -> E
+ 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("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
+
+ 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", "None");
+ 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,
- 0f, cosmic);
- sf6.setValue("alleles", "C,A,G"); // CAC,CGC -> H,R
+ sf6.setValue("alleles", "T,C"); // TTT -> TTC synonymous
sf6.setValue("ID", "var6");
- sf6.setValue("clinical_significance", "Good");
- List<DnaVariant> codon1Variants = new ArrayList<DnaVariant>();
- List<DnaVariant> codon2Variants = new ArrayList<DnaVariant>();
- List<DnaVariant> codon3Variants = new ArrayList<DnaVariant>();
+ SequenceFeature sf7 = new SequenceFeature("sequence_variant", "", 8, 8,
+ 0f, cosmic);
+ 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> 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 -> TAA -> stop codon
sf = sfs.get(1);
assertEquals(1, sf.getBegin());
assertEquals(1, sf.getEnd());
+ assertEquals("nonsynonymous_variant", sf.getType());
+ assertEquals("p.Lys1null", sf.getDescription()); // stop codon badly handled
+ 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(
+ "p.Lys1null var3|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var3",
+ sf.links.get(0));
+ assertEquals(dbSnp, sf.getFeatureGroup());
+
+ // AAA -> CAA -> K/Q
+ sf = sfs.get(2);
+ assertEquals(1, sf.getBegin());
+ assertEquals(1, sf.getEnd());
+ assertEquals("nonsynonymous_variant", sf.getType());
assertEquals("p.Lys1Gln", sf.getDescription());
assertEquals("var2", sf.getValue("ID"));
assertEquals("Dodgy", sf.getValue("clinical_significance"));
sf.links.get(0));
assertEquals(dbSnp, sf.getFeatureGroup());
- sf = sfs.get(2);
+ // AAA -> GAA -> K/E
+ sf = sfs.get(3);
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"));
assertNull(sf.getValue("clinical_significance"));
sf.links.get(0));
assertEquals(ensembl, sf.getFeatureGroup());
- sf = sfs.get(3);
+ // AAA -> AAG synonymous
+ sf = sfs.get(4);
+ assertEquals(1, sf.getBegin());
+ assertEquals(1, sf.getEnd());
+ assertEquals("synonymous_variant", sf.getType());
+ assertEquals("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(
+ "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("TTC", sf.getDescription());
+ assertEquals("var6", sf.getValue("ID"));
+ assertNull(sf.getValue("clinical_significance"));
+ assertEquals("ID=var6", sf.getAttributes());
+ assertEquals(1, sf.links.size());
+ assertEquals(
+ "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);
/*
git://source.jalview.org / jalview.git / commitdiff