/*
* Author: Daniel Cameron
*/
@Test
public void testCaseEquivalence() {
DNACompoundSet dnacs = DNACompoundSet.getDNACompoundSet();
SubstitutionMatrix<NucleotideCompound> dnaTest =
new SimpleSubstitutionMatrix<NucleotideCompound>(
dnacs, "# Test\nA C G T\nA 5 0 0 0\nC 0 5 0 0\nG 0 0 5 0\nT 0 0 0 1\n", "DNA Test");
@SuppressWarnings("unused")
short[][] matrix = dnaTest.getMatrix();
assertEquals(
dnaTest.getValue(dnacs.getCompoundForString("G"), dnacs.getCompoundForString("g")), 5);
assertEquals(
dnaTest.getValue(dnacs.getCompoundForString("A"), dnacs.getCompoundForString("g")), 0);
assertEquals(
dnaTest.getValue(dnacs.getCompoundForString("g"), dnacs.getCompoundForString("G")), 5);
assertEquals(
dnaTest.getValue(dnacs.getCompoundForString("g"), dnacs.getCompoundForString("A")), 0);
}
@Test
public void testToString() {
SubstitutionMatrix<NucleotideCompound> matrix =
new SimpleSubstitutionMatrix<NucleotideCompound>(
DNACompoundSet.getDNACompoundSet(),
"# Test\nA C G T\nA 5 0 0 0\nC 0 5 0 0 \nG 0 0 5 0\n T 0 0 0 1\n",
"DNAtest");
assertEquals(matrix.toString().substring(0, 6), "# Test");
assertEquals(
matrix.toString(),
String.format("# Test%n A C G T%nA 5 0 0 0%nC 0 5 0 0%nG 0 0 5 0%nT 0 0 0 1%n"));
}
@Test
public void test() throws CompoundNotFoundException {
NucleotideCompound A = new DNASequence("A").getCompoundAt(1);
NucleotideCompound a = new DNASequence("a").getCompoundAt(1);
NucleotideCompound c = new DNASequence("c").getCompoundAt(1);
SubstitutionMatrix<NucleotideCompound> matrix =
new SimpleSubstitutionMatrix<NucleotideCompound>(
DNACompoundSet.getDNACompoundSet(), (short) 1, (short) 0);
assertEquals(1, (matrix.getValue(A, A)));
assertEquals(1, (matrix.getValue(a, a)));
assertEquals(1, (matrix.getValue(A, a)));
assertEquals(0, (matrix.getValue(a, c)));
}
@Test
public void testSimpleSubstitutionMatrixCompoundSetOfCStringString() {
DNACompoundSet dnacs = DNACompoundSet.getDNACompoundSet();
SubstitutionMatrix<NucleotideCompound> dnaTest =
new SimpleSubstitutionMatrix<NucleotideCompound>(
dnacs, "# Test\nA C G T\nA 5 0 0 0\nC 0 5 0 0\nG 0 0 5 0\nT 0 0 0 1\n", "DNA Test");
short[][] matrix = dnaTest.getMatrix();
assertEquals(matrix[1][1], 5);
assertEquals(matrix[3][3], 1);
assertEquals(matrix[3][1], 0);
assertEquals(dnaTest.getMatrixAsString().substring(2, 9), "A C G T");
assertEquals(
dnaTest.getValue(dnacs.getCompoundForString("G"), dnacs.getCompoundForString("G")), 5);
assertEquals(
dnaTest.getValue(dnacs.getCompoundForString("A"), dnacs.getCompoundForString("G")), 0);
}
/** Test of process method, of class GenbankReader. */
@Test
public void testProcess() throws Throwable {
/*
* Method 1: With the GenbankProxySequenceReader
*/
// Try with the GenbankProxySequenceReader
GenbankProxySequenceReader<AminoAcidCompound> genbankProteinReader =
new GenbankProxySequenceReader<AminoAcidCompound>(
System.getProperty("java.io.tmpdir"),
"NP_000257",
AminoAcidCompoundSet.getAminoAcidCompoundSet());
ProteinSequence proteinSequence = new ProteinSequence(genbankProteinReader);
genbankProteinReader
.getHeaderParser()
.parseHeader(genbankProteinReader.getHeader(), proteinSequence);
logger.info(
"Sequence({},{}) = {}...",
proteinSequence.getAccession(),
proteinSequence.getLength(),
proteinSequence.getSequenceAsString().substring(0, 10));
GenbankProxySequenceReader<NucleotideCompound> genbankDNAReader =
new GenbankProxySequenceReader<NucleotideCompound>(
System.getProperty("java.io.tmpdir"), "NM_001126", DNACompoundSet.getDNACompoundSet());
DNASequence dnaSequence = new DNASequence(genbankDNAReader);
genbankDNAReader.getHeaderParser().parseHeader(genbankDNAReader.getHeader(), dnaSequence);
logger.info(
"Sequence({},{}) = {}...",
dnaSequence.getAccession(),
dnaSequence.getLength(),
dnaSequence.getSequenceAsString().substring(0, 10));
/*
* Method 2: With the GenbankReaderHelper
*/
// Try with the GenbankReaderHelper
ClasspathResource dnaResource = new ClasspathResource("NM_000266.gb", true);
// File dnaFile = new File("src/test/resources/NM_000266.gb");
// File protFile = new File("src/test/resources/BondFeature.gb");
ClasspathResource protResource = new ClasspathResource("BondFeature.gb");
LinkedHashMap<String, DNASequence> dnaSequences =
GenbankReaderHelper.readGenbankDNASequence(dnaResource.getInputStream());
for (DNASequence sequence : dnaSequences.values()) {
logger.info("DNA Sequence: {}", sequence.getSequenceAsString());
}
LinkedHashMap<String, ProteinSequence> protSequences =
GenbankReaderHelper.readGenbankProteinSequence(protResource.getInputStream());
for (ProteinSequence sequence : protSequences.values()) {
logger.info("Protein Sequence: {}", sequence.getSequenceAsString());
}
/*
* Method 3: With the GenbankReader Object
*/
// Try reading with the GanbankReader
GenbankReader<DNASequence, NucleotideCompound> dnaReader =
new GenbankReader<DNASequence, NucleotideCompound>(
dnaResource.getInputStream(),
new GenericGenbankHeaderParser<DNASequence, NucleotideCompound>(),
new DNASequenceCreator(DNACompoundSet.getDNACompoundSet()));
dnaSequences = dnaReader.process();
logger.info("DNA Sequence: {}", dnaSequences);
GenbankReader<ProteinSequence, AminoAcidCompound> protReader =
new GenbankReader<ProteinSequence, AminoAcidCompound>(
protResource.getInputStream(),
new GenericGenbankHeaderParser<ProteinSequence, AminoAcidCompound>(),
new ProteinSequenceCreator(AminoAcidCompoundSet.getAminoAcidCompoundSet()));
protSequences = protReader.process();
logger.info("Protein Sequence: {}", protSequences);
}
