use of org.broadinstitute.hdf5.HDF5File in project gatk-protected by broadinstitute.
the class HDF5PCACoveragePoNUnitTest method testTargetFactorsReading.
@Test(dependsOnMethods = "testTargetNameReading")
public void testTargetFactorsReading() throws IOException {
final HDF5File reader = new HDF5File(TEST_PON);
final PCACoveragePoN pon = new HDF5PCACoveragePoN(reader);
final List<String> targets = pon.getTargetNames();
final double[] factors = pon.getTargetFactors();
Assert.assertEquals(factors.length, targets.size());
final List<Double> expected = readDoubleLines(TEST_PON_TARGET_FACTORS);
Assert.assertNotNull(factors);
Assert.assertEquals(factors.length, expected.size());
for (int i = 0; i < expected.size(); i++) {
Assert.assertEquals(factors[i], expected.get(i), Math.abs(expected.get(i)) * 0.0001);
}
reader.close();
}
use of org.broadinstitute.hdf5.HDF5File in project gatk-protected by broadinstitute.
the class HDF5PCACoveragePoNUnitTest method testLogNormalizedMatrixReading.
@Test(dependsOnMethods = { "testTargetNameReading", "testLogNormalizedSampleNameReading" })
public void testLogNormalizedMatrixReading() throws IOException {
final HDF5File reader = new HDF5File(TEST_PON);
final PCACoveragePoN pon = new HDF5PCACoveragePoN(reader);
final List<String> targets = pon.getTargetNames();
final List<String> samples = pon.getPanelSampleNames();
final RealMatrix actual = pon.getLogNormalizedCounts();
Assert.assertNotNull(actual);
Assert.assertEquals(actual.getRowDimension(), targets.size());
Assert.assertEquals(actual.getColumnDimension(), samples.size());
final RealMatrix expected = readDoubleMatrix(TEST_PON_LOG_NORMALS);
MathObjectAsserts.assertRealMatrixEquals(actual, expected);
}
use of org.broadinstitute.hdf5.HDF5File in project gatk by broadinstitute.
the class NormalizeSomaticReadCountsIntegrationTest method assertBetaHatsRobustToOutliers.
/**
* Asserts that the calculation of beta hats is not significantly affected by zero-coverage outlier counts
* We perform this check by randomly setting some coverages to zero in copy ratio space (-infinity in log space).
* betaHats imputes 0 in log space (1 in copy ratio space) whenever coverage is below a certain low threshold
* and should thus be robust to this type of noise.
*/
private void assertBetaHatsRobustToOutliers(final ReadCountCollection preTangentNormalized, final File ponFile) {
try (final HDF5File ponReader = new HDF5File(ponFile)) {
final PCACoveragePoN pon = new HDF5PCACoveragePoN(ponReader);
final List<String> ponTargets = pon.getPanelTargetNames();
final RealMatrix input = reorderTargetsToPoNOrder(preTangentNormalized, ponTargets);
// randomly set some entries to zero in copy-ratio space (-infinity in log space)
final Random random = new Random(13);
final double noiseProportion = 0.01;
final RealMatrix noisyInput = input.copy();
noisyInput.walkInOptimizedOrder(new DefaultRealMatrixChangingVisitor() {
@Override
public double visit(final int row, final int column, final double value) {
return random.nextDouble() < noiseProportion ? Double.NEGATIVE_INFINITY : value;
}
});
final RealMatrix betaHats = PCATangentNormalizationUtils.calculateBetaHats(pon.getReducedPanelPInverseCounts(), input, PCATangentNormalizationUtils.EPSILON);
final RealMatrix noisyBetaHats = PCATangentNormalizationUtils.calculateBetaHats(pon.getReducedPanelPInverseCounts(), noisyInput, PCATangentNormalizationUtils.EPSILON);
final RealMatrix difference = betaHats.subtract(noisyBetaHats);
difference.walkInOptimizedOrder(new DefaultRealMatrixPreservingVisitor() {
@Override
public void visit(final int row, int column, double value) {
Assert.assertEquals(value, 0, 0.01);
}
});
}
}
use of org.broadinstitute.hdf5.HDF5File in project gatk by broadinstitute.
the class CreatePanelOfNormalsIntegrationTest method assertRamPoNDuplicate.
private void assertRamPoNDuplicate(final File outputFile) {
try (final HDF5File hdf5FilePoN = new HDF5File(outputFile)) {
final HDF5PCACoveragePoN filePoN = new HDF5PCACoveragePoN(hdf5FilePoN);
assertRamPoNDuplicate(filePoN);
}
}
use of org.broadinstitute.hdf5.HDF5File in project gatk by broadinstitute.
the class NormalizeSomaticReadCountsIntegrationTest method assertTangentNormalized.
private void assertTangentNormalized(final ReadCountCollection actualReadCounts, final ReadCountCollection preTangentNormalized, final RealMatrix betaHats, final File ponFile) {
try (final HDF5File ponReader = new HDF5File(ponFile)) {
final PCACoveragePoN pon = new HDF5PCACoveragePoN(ponReader);
final RealMatrix inCounts = reorderTargetsToPoNOrder(preTangentNormalized, pon.getPanelTargetNames());
final RealMatrix actual = reorderTargetsToPoNOrder(actualReadCounts, pon.getPanelTargetNames());
final RealMatrix ponMat = pon.getReducedPanelCounts();
final RealMatrix projection = ponMat.multiply(betaHats);
final RealMatrix expected = inCounts.subtract(projection);
Assert.assertEquals(actual.getRowDimension(), expected.getRowDimension());
Assert.assertEquals(actual.getColumnDimension(), expected.getColumnDimension());
for (int i = 0; i < actual.getRowDimension(); i++) {
Assert.assertEquals(actual.getRow(i), expected.getRow(i));
}
}
}
Aggregations