SequenceI alignFrom = new Sequence("Seq2", alignModel);
alignFrom.createDatasetSequence();
AlignedCodonFrame acf = new AlignedCodonFrame();
- acf.addMap(alignMe.getDatasetSequence(), alignFrom.getDatasetSequence(), map);
+ acf.addMap(alignMe.getDatasetSequence(),
+ alignFrom.getDatasetSequence(), map);
AlignmentUtils.alignSequenceAs(alignMe, alignFrom, acf, "---", '-',
preserveMappedGaps, preserveUnmappedGaps);
/*
* scenario:
* dna1 --> [4, 6] [10,12] --> pep1
- * dna2 --> [1, 3] [7, 9] [13,15] --> pep1
+ * dna2 --> [1, 3] [7, 9] [13,15] --> pep2
*/
SequenceI dna1 = new Sequence("dna1", "aaaGGGcccTTTaaa");
SequenceI dna2 = new Sequence("dna2", "GGGcccTTTaaaCCC");
dna.setDataset(null);
/*
+ * put a variant feature on dna2 base 8
+ * - should transfer to cds2 base 5
+ */
+ dna2.addSequenceFeature(new SequenceFeature("variant", "hgmd", 8, 8,
+ 0f, null));
+
+ /*
* need a sourceDbRef if we are to construct dbrefs to the CDS
* sequence from the dna contig sequences
*/
* CDS sequences are 'discovered' from dna-to-protein mappings on the alignment
* dataset (e.g. added from dbrefs by CrossRef.findXrefSequences)
*/
- MapList mapfordna1 = new MapList(new int[] { 4, 6, 10, 12 },
- new int[] { 1, 2 }, 3, 1);
+ MapList mapfordna1 = new MapList(new int[] { 4, 6, 10, 12 }, new int[] {
+ 1, 2 }, 3, 1);
AlignedCodonFrame acf = new AlignedCodonFrame();
acf.addMap(dna1.getDatasetSequence(), pep1.getDatasetSequence(),
mapfordna1);
dna.addCodonFrame(acf);
MapList mapfordna2 = new MapList(new int[] { 1, 3, 7, 9, 13, 15 },
- new int[] { 1, 3 },
- 3, 1);
+ new int[] { 1, 3 }, 3, 1);
acf = new AlignedCodonFrame();
acf.addMap(dna2.getDatasetSequence(), pep2.getDatasetSequence(),
mapfordna2);
* verify CDS has a dbref with mapping to peptide
*/
assertNotNull(cds1Dss.getDBRefs());
- assertEquals(1, cds1Dss.getDBRefs().length);
+ assertEquals(2, cds1Dss.getDBRefs().length);
dbref = cds1Dss.getDBRefs()[0];
assertEquals(dna1xref.getSource(), dbref.getSource());
// version is via ensembl's primary ref
assertSame(cds2Dss, m.getSequence());
assertEquals(7, m.getStart());
assertEquals(9, m.getEnd());
+
+ /*
+ * check cds2 acquired a variant feature in position 5
+ */
+ SequenceFeature[] sfs = cds2Dss.getSequenceFeatures();
+ assertNotNull(sfs);
+ assertEquals(1, sfs.length);
+ assertEquals("variant", sfs[0].type);
+ assertEquals(5, sfs[0].begin);
+ assertEquals(5, sfs[0].end);
}
/**
.findMappingsForSequence(cds.get(0), dnaMappings);
Mapping mapping = dnaToCds1Mappings.get(0).getMappings().get(0)
.getMapping();
- assertSame(cds.get(0).getDatasetSequence(), mapping
- .getTo());
+ assertSame(cds.get(0).getDatasetSequence(), mapping.getTo());
assertEquals("G(1) in CDS should map to G(4) in DNA", 4, mapping
.getMap().getToPosition(1));
* @throws IOException
*/
@Test(groups = { "Functional" })
- public void testMapCdnaToProtein_forSubsequence()
- throws IOException
+ public void testMapCdnaToProtein_forSubsequence() throws IOException
{
SequenceI prot = new Sequence("UNIPROT|V12345", "E-I--Q", 10, 12);
prot.createDatasetSequence();
@Test(groups = { "Functional" })
public void testAlignSequenceAs_mappedProteinProtein()
{
-
+
SequenceI alignMe = new Sequence("Match", "MGAASEV");
alignMe.createDatasetSequence();
SequenceI alignFrom = new Sequence("Query", "LQTGYMGAASEVMFSPTRR");
MapList map = new MapList(new int[] { 6, 12 }, new int[] { 1, 7 }, 1, 1);
acf.addMap(alignFrom.getDatasetSequence(),
alignMe.getDatasetSequence(), map);
-
+
AlignmentUtils.alignSequenceAs(alignMe, alignFrom, acf, "-", '-', true,
true);
assertEquals("-----MGAASEV-------", alignMe.getSequenceAsString());
{
// map first 3 codons to KPF; G is a trailing unmapped residue
MapList map = new MapList(new int[] { 1, 9 }, new int[] { 1, 3 }, 3, 1);
-
+
checkAlignSequenceAs("AAACCCTTT", "K-PFG", true, true, map,
"AAA---CCCTTT---");
}
MapList map = new MapList(new int[] { 4, 6, 10, 12 },
new int[] { 1, 6 }, 1, 1);
-
+
// [5, 11] maps to [2, 5]
dna.addSequenceFeature(new SequenceFeature("type4", "desc4", 5, 11, 4f,
null));
// [12, 12] maps to [6, 6]
dna.addSequenceFeature(new SequenceFeature("type8", "desc8", 12, 12,
8f, null));
-
+
// desc4 and desc8 are the 'omit these' varargs
AlignmentUtils.transferFeatures(dna, cds, map, null, "type4", "type8");
SequenceFeature[] sfs = cds.getSequenceFeatures();
assertEquals(1, sfs.length);
-
+
SequenceFeature sf = sfs[0];
assertEquals("type5", sf.getType());
assertEquals(1, sf.getBegin());
{
SequenceI dna = new Sequence("dna/20-34", "acgTAGcaaGCCcgt");
SequenceI cds = new Sequence("cds/10-15", "TAGGCC");
-
+
MapList map = new MapList(new int[] { 4, 6, 10, 12 },
new int[] { 1, 6 }, 1, 1);
-
+
// [5, 11] maps to [2, 5]
dna.addSequenceFeature(new SequenceFeature("type4", "desc4", 5, 11, 4f,
null));
// [12, 12] maps to [6, 6]
dna.addSequenceFeature(new SequenceFeature("type8", "desc8", 12, 12,
8f, null));
-
+
// "type5" is the 'select this type' argument
AlignmentUtils.transferFeatures(dna, cds, map, "type5");
SequenceFeature[] sfs = cds.getSequenceFeatures();
assertEquals(1, sfs.length);
-
+
SequenceFeature sf = sfs[0];
assertEquals("type5", sf.getType());
assertEquals(1, sf.getBegin());
AlignmentI dna = new Alignment(new SequenceI[] { dna1, dna2, dna3 });
dna.setDataset(null);
-
+
MapList map = new MapList(new int[] { 4, 12, 16, 18 },
new int[] { 1, 4 }, 3, 1);
AlignedCodonFrame acf = new AlignedCodonFrame();
acf.addMap(dna1.getDatasetSequence(), pep1.getDatasetSequence(), map);
dna.addCodonFrame(acf);
map = new MapList(new int[] { 4, 8, 12, 12, 16, 18 },
- new int[] { 1, 3 },
- 3, 1);
+ new int[] { 1, 3 }, 3, 1);
acf = new AlignedCodonFrame();
acf.addMap(dna2.getDatasetSequence(), pep2.getDatasetSequence(), map);
dna.addCodonFrame(acf);
-
+
AlignmentI cds = AlignmentUtils.makeCdsAlignment(new SequenceI[] {
dna1, dna2, dna3 }, dna.getDataset(), null);
List<SequenceI> cdsSeqs = cds.getSequences();
assertEquals(2, cdsSeqs.size());
assertEquals("GGGCCCTTTGGG", cdsSeqs.get(0).getSequenceAsString());
assertEquals("GGGCCTGGG", cdsSeqs.get(1).getSequenceAsString());
-
+
/*
* verify shared, extended alignment dataset
*/
*/
List<AlignedCodonFrame> mappings = cds.getCodonFrames();
assertEquals(6, mappings.size());
-
+
/*
* 2 mappings involve pep1
*/
pep1CdsMappings);
assertEquals(1, sr.getResults().size());
Match m = sr.getResults().get(0);
- assertEquals(cds.getSequenceAt(0).getDatasetSequence(),
- m.getSequence());
+ assertEquals(cds.getSequenceAt(0).getDatasetSequence(), m.getSequence());
assertEquals(1, m.getStart());
assertEquals(3, m.getEnd());
sr = MappingUtils.buildSearchResults(pep1, 2, pep1CdsMappings);
m = sr.getResults().get(0);
assertEquals(10, m.getStart());
assertEquals(12, m.getEnd());
-
+
/*
* Get mapping of pep2 to cds2 and verify it
* maps GPG in pep2 to 1-3,4-6,7-9 in second CDS sequence
sr = MappingUtils.buildSearchResults(pep2, 1, pep2CdsMappings);
assertEquals(1, sr.getResults().size());
m = sr.getResults().get(0);
- assertEquals(cds.getSequenceAt(1).getDatasetSequence(),
- m.getSequence());
+ assertEquals(cds.getSequenceAt(1).getDatasetSequence(), m.getSequence());
assertEquals(1, m.getStart());
assertEquals(3, m.getEnd());
sr = MappingUtils.buildSearchResults(pep2, 2, pep2CdsMappings);
SequenceI dna3 = new Sequence("Seq3", "ccaaa-ttt-GGG-");
AlignmentI dna = new Alignment(new SequenceI[] { dna1, dna2, dna3 });
dna.setDataset(null);
-
+
// prot1 has 'X' for incomplete start codon (not mapped)
SequenceI prot1 = new Sequence("Seq1", "XKFG"); // X for incomplete start
SequenceI prot2 = new Sequence("Seq2", "NG");
AlignmentI protein = new Alignment(new SequenceI[] { prot1, prot2,
prot3 });
protein.setDataset(null);
-
+
// map dna1 [3, 11] to prot1 [2, 4] KFG
MapList map = new MapList(new int[] { 3, 11 }, new int[] { 2, 4 }, 3, 1);
AlignedCodonFrame acf = new AlignedCodonFrame();
SequenceI dnaSeq = new Sequence("dna", "aaagGGCCCaaaTTTttt");
dnaSeq.createDatasetSequence();
SequenceI ds = dnaSeq.getDatasetSequence();
-
+
// CDS for dna 5-6 (incomplete codon), 7-9
SequenceFeature sf = new SequenceFeature("CDS", "", 5, 9, 0f, null);
sf.setPhase("2"); // skip 2 bases to start of next codon
// CDS for dna 13-15
sf = new SequenceFeature("CDS_predicted", "", 13, 15, 0f, null);
ds.addSequenceFeature(sf);
-
+
List<int[]> ranges = AlignmentUtils.findCdsPositions(dnaSeq);
-
+
/*
* check the mapping starts with the first complete codon
*/
SequenceI dnaSeq = new Sequence("dna", "aaaGGGcccAAATTTttt");
dnaSeq.createDatasetSequence();
SequenceI ds = dnaSeq.getDatasetSequence();
-
+
// CDS for dna 10-12
SequenceFeature sf = new SequenceFeature("CDS_predicted", "", 10, 12,
0f, null);
// exon feature should be ignored here
sf = new SequenceFeature("exon", "", 7, 9, 0f, null);
ds.addSequenceFeature(sf);
-
+
List<int[]> ranges = AlignmentUtils.findCdsPositions(dnaSeq);
/*
* verify ranges { [4-6], [12-10] }
public void testComputePeptideVariants()
{
/*
- * scenario: AAATTTCCC codes for KFP, with variants
- * GAA -> E
- * CAA -> Q
- * AAG synonymous
- * AAT -> N
- * TTC synonymous
- * CAC,CGC -> H,R (as one variant)
+ * scenario: AAATTTCCC codes for KFP
+ * variants:
+ * GAA -> E source: Ensembl
+ * CAA -> Q source: dbSNP
+ * AAG synonymous source: COSMIC
+ * AAT -> N source: Ensembl
+ * ...TTC synonymous source: dbSNP
+ * ......CAC,CGC -> H,R source: COSMIC
+ * (one variant with two alleles)
*/
SequenceI peptide = new Sequence("pep/10-12", "KFP");
* two distinct variants for codon 1 position 1
* second one has clinical significance
*/
+ String ensembl = "Ensembl";
+ String dbSnp = "dbSNP";
+ String cosmic = "COSMIC";
SequenceFeature sf1 = new SequenceFeature("sequence_variant", "", 1, 1,
- 0f, null);
+ 0f, ensembl);
sf1.setValue("alleles", "A,G"); // GAA -> E
sf1.setValue("ID", "var1.125A>G");
SequenceFeature sf2 = new SequenceFeature("sequence_variant", "", 1, 1,
- 0f, null);
+ 0f, dbSnp);
sf2.setValue("alleles", "A,C"); // CAA -> Q
sf2.setValue("ID", "var2");
sf2.setValue("clinical_significance", "Dodgy");
SequenceFeature sf3 = new SequenceFeature("sequence_variant", "", 3, 3,
- 0f, null);
+ 0f, cosmic);
sf3.setValue("alleles", "A,G"); // synonymous
sf3.setValue("ID", "var3");
sf3.setValue("clinical_significance", "None");
SequenceFeature sf4 = new SequenceFeature("sequence_variant", "", 3, 3,
- 0f, null);
+ 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,
- 0f, null);
+ 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, null);
+ 0f, cosmic);
sf6.setValue("alleles", "C,A,G"); // CAC,CGC -> H,R
sf6.setValue("ID", "var6");
sf6.setValue("clinical_significance", "Good");
/*
* verify added sequence features for
- * var1 K -> E
- * var2 K -> Q
- * var4 K -> N
- * var6 P -> H
- * var6 P -> R
+ * var1 K -> E Ensembl
+ * var2 K -> Q dbSNP
+ * var4 K -> N Ensembl
+ * var6 P -> H COSMIC
+ * var6 P -> R COSMIC
*/
SequenceFeature[] sfs = peptide.getSequenceFeatures();
assertEquals(5, sfs.length);
+
SequenceFeature sf = sfs[0];
assertEquals(1, sf.getBegin());
assertEquals(1, sf.getEnd());
assertEquals(
"p.Lys1Glu var1.125A>G|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var1.125A%3EG",
sf.links.get(0));
- assertEquals("Jalview", sf.getFeatureGroup());
+ assertEquals(ensembl, sf.getFeatureGroup());
+
sf = sfs[1];
assertEquals(1, sf.getBegin());
assertEquals(1, sf.getEnd());
assertEquals(
"p.Lys1Gln var2|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var2",
sf.links.get(0));
- assertEquals("Jalview", sf.getFeatureGroup());
+ assertEquals(dbSnp, sf.getFeatureGroup());
+
sf = sfs[2];
assertEquals(1, sf.getBegin());
assertEquals(1, sf.getEnd());
assertEquals(
"p.Lys1Asn var4|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var4",
sf.links.get(0));
- assertEquals("Jalview", sf.getFeatureGroup());
+ assertEquals(ensembl, sf.getFeatureGroup());
+
+ // var5 generates two distinct protein variant features
sf = sfs[3];
assertEquals(3, sf.getBegin());
assertEquals(3, sf.getEnd());
assertEquals(
"p.Pro3His var6|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var6",
sf.links.get(0));
- // var5 generates two distinct protein variant features
- assertEquals("Jalview", sf.getFeatureGroup());
+ assertEquals(cosmic, sf.getFeatureGroup());
+
sf = sfs[4];
assertEquals(3, sf.getBegin());
assertEquals(3, sf.getEnd());
assertEquals(
"p.Pro3Arg var6|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var6",
sf.links.get(0));
- assertEquals("Jalview", sf.getFeatureGroup());
+ assertEquals(cosmic, sf.getFeatureGroup());
}
/**
SequenceI dnaSeq = new Sequence("dna", "aaaGGGcccAAATTTttt");
dnaSeq.createDatasetSequence();
SequenceI ds = dnaSeq.getDatasetSequence();
-
+
// CDS for dna 4-6
SequenceFeature sf = new SequenceFeature("CDS", "", 4, 6, 0f, null);
sf.setStrand("-");
sf = new SequenceFeature("CDS_predicted", "", 10, 12, 0f, null);
sf.setStrand("-");
ds.addSequenceFeature(sf);
-
+
List<int[]> ranges = AlignmentUtils.findCdsPositions(dnaSeq);
/*
* verify ranges { [12-10], [6-4] }
SequenceI dnaSeq = new Sequence("dna", "aaagGGCCCaaaTTTttt");
dnaSeq.createDatasetSequence();
SequenceI ds = dnaSeq.getDatasetSequence();
-
+
// CDS for dna 5-9
SequenceFeature sf = new SequenceFeature("CDS", "", 5, 9, 0f, null);
sf.setStrand("-");
sf.setStrand("-");
sf.setPhase("2"); // skip 2 bases to start of next codon
ds.addSequenceFeature(sf);
-
+
List<int[]> ranges = AlignmentUtils.findCdsPositions(dnaSeq);
-
+
/*
* check the mapping starts with the first complete codon
* expect ranges [13, 13], [9, 5]
from.createDatasetSequence();
seq1.createDatasetSequence();
Mapping mapping = new Mapping(seq1, new MapList(
- new int[] { 3, 6, 9, 10 },
- new int[] { 1, 6 }, 1, 1));
+ new int[] { 3, 6, 9, 10 }, new int[] { 1, 6 }, 1, 1));
Map<Integer, Map<SequenceI, Character>> map = new TreeMap<Integer, Map<SequenceI, Character>>();
AlignmentUtils.addMappedPositions(seq1, from, mapping, map);
from.createDatasetSequence();
seq1.createDatasetSequence();
Mapping mapping = new Mapping(seq1, new MapList(
- new int[] { 3, 6, 9, 10 },
- new int[] { 1, 6 }, 1, 1));
+ new int[] { 3, 6, 9, 10 }, new int[] { 1, 6 }, 1, 1));
Map<Integer, Map<SequenceI, Character>> map = new TreeMap<Integer, Map<SequenceI, Character>>();
AlignmentUtils.addMappedPositions(seq1, from, mapping, map);
-
+
/*
* verify map has seq1 residues in columns 3,4,6,7,11,12
*/
dna.setDataset(null);
AlignmentI emblPeptides = new Alignment(new SequenceI[] { pep3, pep4 });
emblPeptides.setDataset(null);
-
+
AlignedCodonFrame acf = new AlignedCodonFrame();
MapList map = new MapList(new int[] { 4, 6, 10, 12 },
new int[] { 1, 2 }, 3, 1);
acf.addMap(dna2.getDatasetSequence(), pep2.getDatasetSequence(), map);
acf.addMap(dna2.getDatasetSequence(), pep4.getDatasetSequence(), map);
dna.addCodonFrame(acf);
-
+
/*
* execute method under test to find CDS for EMBL peptides only
*/
AlignmentI cds = AlignmentUtils.makeCdsAlignment(new SequenceI[] {
dna1, dna2 }, dna.getDataset(), emblPeptides.getSequencesArray());
-
+
assertEquals(2, cds.getSequences().size());
assertEquals("GGGTTT", cds.getSequenceAt(0).getSequenceAsString());
assertEquals("GGGTTTCCC", cds.getSequenceAt(1).getSequenceAsString());
-
+
/*
* verify shared, extended alignment dataset
*/
.contains(cds.getSequenceAt(0).getDatasetSequence()));
assertTrue(dna.getDataset().getSequences()
.contains(cds.getSequenceAt(1).getDatasetSequence()));
-
+
/*
* Verify mappings from CDS to peptide, cDNA to CDS, and cDNA to peptide
* the mappings are on the shared alignment dataset
* 6 mappings, 2*(DNA->CDS), 2*(DNA->Pep), 2*(CDS->Pep)
*/
assertEquals(6, cdsMappings.size());
-
+
/*
* verify that mapping sets for dna and cds alignments are different
* [not current behaviour - all mappings are on the alignment dataset]
// Assert.assertNotSame(dna.getCodonFrames(), cds.getCodonFrames());
// assertEquals(4, dna.getCodonFrames().size());
// assertEquals(4, cds.getCodonFrames().size());
-
+
/*
* Two mappings involve pep3 (dna to pep3, cds to pep3)
* Mapping from pep3 to GGGTTT in first new exon sequence
List<AlignedCodonFrame> mappings = MappingUtils
.findMappingsForSequence(cds.getSequenceAt(0), pep3Mappings);
assertEquals(1, mappings.size());
-
+
// map G to GGG
SearchResults sr = MappingUtils.buildSearchResults(pep3, 1, mappings);
assertEquals(1, sr.getResults().size());
assertSame(cds.getSequenceAt(0).getDatasetSequence(), m.getSequence());
assertEquals(4, m.getStart());
assertEquals(6, m.getEnd());
-
+
/*
* Two mappings involve pep4 (dna to pep4, cds to pep4)
* Verify mapping from pep4 to GGGTTTCCC in second new exon sequence
dna4.setSequence(seq2);
AlignmentI al2 = new Alignment(new SequenceI[] { dna3, dna4 });
((Alignment) al2).createDatasetAlignment();
-
+
assertTrue(AlignmentUtils.alignAsSameSequences(al1, al2));
assertEquals(seq1, al1.getSequenceAt(0).getSequenceAsString());
assertEquals(seq2, al1.getSequenceAt(1).getSequenceAsString());
assertEquals(s_as2, uas2.getSequenceAsString());
assertEquals(s_as3, uas3.getSequenceAsString());
}
-
+
}
git://source.jalview.org / jalview.git / blobdiff