Examples with ReadCountCollection org.broadinstitute.hellbender.tools.exome.ReadCountCollection used on opensource projects

Example 56 with ReadCountCollection

use of org.broadinstitute.hellbender.tools.exome.ReadCountCollection in project gatk by broadinstitute.

the class HDF5PCACoveragePoNCreationUtilsUnitTest method readCountOnlyWithDiverseShapeData.

@DataProvider(name = "readCountOnlyWithDiverseShapeData")
public Object[][] readCountOnlyWithDiverseShapeData() {
    final List<Object[]> result = new ArrayList<>(4);
    final Random rdn = new Random(31);
    final int[] columnCounts = new int[] { 10, 100, 100, 200 };
    final int[] targetCounts = new int[] { 100, 100, 200, 200 };
    for (int k = 0; k < columnCounts.length; k++) {
        final List<String> columnNames = IntStream.range(0, columnCounts[k]).mapToObj(i -> "sample_" + (i + 1)).collect(Collectors.toList());
        final List<Target> targets = IntStream.range(0, targetCounts[k]).mapToObj(i -> new Target("target_" + (i + 1))).collect(Collectors.toList());
        final double[][] counts = new double[targetCounts[k]][columnCounts[k]];
        for (int i = 0; i < counts.length; i++) {
            for (int j = 0; j < counts[0].length; j++) {
                counts[i][j] = rdn.nextDouble();
            }
        }
        final ReadCountCollection readCounts = new ReadCountCollection(targets, columnNames, new Array2DRowRealMatrix(counts, false));
        result.add(new Object[] { readCounts });
    }
    return result.toArray(new Object[result.size()][]);
}

Example 57 with ReadCountCollection

use of org.broadinstitute.hellbender.tools.exome.ReadCountCollection in project gatk by broadinstitute.

the class PCATangentNormalizationUtilsUnitTest method normalizeReadCountByTargetFactorsData.

@DataProvider(name = "normalizeReadCountByTargetFactorsData")
public Object[][] normalizeReadCountByTargetFactorsData() {
    final List<Object[]> result = new ArrayList<>(1);
    @SuppressWarnings("serial") final List<Target> targets = new ArrayList<Target>() {

        {
            add(new Target("A"));
            add(new Target("B"));
            add(new Target("C"));
        }
    };
    @SuppressWarnings("serial") final List<String> columnNames = new ArrayList<String>() {

        {
            add("1");
            add("2");
            add("3");
        }
    };
    result.add(new Object[] { new ReadCountCollection(targets, columnNames, new Array2DRowRealMatrix(new double[][] { new double[] { 1.1, 2.2, 3.3 }, new double[] { 0.1, 0.2, 0.3 }, new double[] { 11.1, 22.2, 33.3 } }, false)), new double[] { 100.0, 200.0, 300.0 } });
    return result.toArray(new Object[1][]);
}

Example 58 with ReadCountCollection

use of org.broadinstitute.hellbender.tools.exome.ReadCountCollection in project gatk by broadinstitute.

the class PCATangentNormalizationUtils method tangentNormalize.

/**
     *  Do the full tangent normalization process given a {@link PCACoveragePoN} and a proportional-coverage profile.
     *
     *  This includes:
     *   <ul><li>normalization by target factors (optional)</li>
     *   <li>projection of the normalized coverage profile into the hyperplane from the PoN</li>
     *   </ul>
     *
     * @param pon -- never {@code null}
     * @param profile -- never {@code null}.  Must contain data for at least one sample.
     * @param ctx spark context.  Use {@code null} if no context is available
     * @param doFactorNormalization if true, perform factor normalization (set to false for normalizing normals in a PoN that have already been factor normalized)
     * @return never {@code null}
     */
static PCATangentNormalizationResult tangentNormalize(final PCACoveragePoN pon, final ReadCountCollection profile, final boolean doFactorNormalization, final JavaSparkContext ctx) {
    Utils.nonNull(pon, "PoN cannot be null.");
    Utils.nonNull(profile, "Proportional coverages cannot be null.");
    ParamUtils.isPositive(profile.columnNames().size(), "Column names cannot be an empty list.");
    //normals stored in a PoN may already be factor normalized
    final ReadCountCollection factorNormalizedCoverage = doFactorNormalization ? mapTargetsToPoNAndFactorNormalize(profile, pon) : profile;
    return tangentNormalize(factorNormalizedCoverage, pon.getPanelTargetNames(), pon.getReducedPanelCounts(), pon.getReducedPanelPInverseCounts(), ctx);
}

Example 59 with ReadCountCollection

use of org.broadinstitute.hellbender.tools.exome.ReadCountCollection in project gatk by broadinstitute.

the class CopyRatioModellerUnitTest method testRunMCMCOnCopyRatioSegmentedGenome.

/**
     * Tests Bayesian inference of the copy-ratio model via MCMC.
     * <p>
     *     Recovery of input values for the variance and outlier-probability global parameters is checked.
     *     In particular, the true input value of the variance must fall within
     *     {@link CopyRatioModellerUnitTest#MULTIPLES_OF_SD_THRESHOLD}
     *     standard deviations of the posterior mean and the standard deviation of the posterior must agree
     *     with the analytic value to within a relative error of
     *     {@link CopyRatioModellerUnitTest#RELATIVE_ERROR_THRESHOLD} for 250 samples
     *     (after 250 burn-in samples have been discarded).  Similar criteria are applied
     *     to the recovery of the true input value for the outlier probability.
     * </p>
     * <p>
     *     Furthermore, the number of truth values for the segment-level means falling outside confidence intervals of
     *     1-sigma, 2-sigma, and 3-sigma given by the posteriors in each segment should be roughly consistent with
     *     a normal distribution (i.e., ~32, ~5, and ~0, respectively; we allow for errors of
     *     {@link CopyRatioModellerUnitTest#DELTA_NUMBER_OF_MEANS_ALLOWED_OUTSIDE_1_SIGMA},
     *     {@link CopyRatioModellerUnitTest#DELTA_NUMBER_OF_MEANS_ALLOWED_OUTSIDE_2_SIGMA}, and
     *     {@link CopyRatioModellerUnitTest#DELTA_NUMBER_OF_MEANS_ALLOWED_OUTSIDE_3_SIGMA}, respectively).
     *     The mean of the standard deviations of the posteriors for the segment-level means should also be
     *     recovered to within a relative error of {@link CopyRatioModellerUnitTest#RELATIVE_ERROR_THRESHOLD}.
     * </p>
     * <p>
     *     Finally, the recovered values for the latent outlier-indicator parameters should agree with those used to
     *     generate the data.  For each indicator, the recovered value (i.e., outlier or non-outlier) is taken to be
     *     that given by the majority of posterior samples.  We require that at least
     *     {@link CopyRatioModellerUnitTest#FRACTION_OF_OUTLIER_INDICATORS_CORRECT_THRESHOLD}
     *     of the 10000 indicators are recovered correctly.
     * </p>
     * <p>
     *     With these specifications, this unit test is not overly brittle (i.e., it should pass for a large majority
     *     of randomly generated data sets), but it is still brittle enough to check for correctness of the sampling
     *     (for example, specifying a sufficiently incorrect likelihood will cause the test to fail).
     * </p>
     */
@Test
public void testRunMCMCOnCopyRatioSegmentedGenome() throws IOException {
    final JavaSparkContext ctx = SparkContextFactory.getTestSparkContext();
    LoggingUtils.setLoggingLevel(Log.LogLevel.INFO);
    //load data (coverages and number of targets in each segment)
    final ReadCountCollection coverage = ReadCountCollectionUtils.parse(COVERAGES_FILE);
    //Genome with no SNPs
    final Genome genome = new Genome(coverage, Collections.emptyList());
    final SegmentedGenome segmentedGenome = new SegmentedGenome(SEGMENT_FILE, genome);
    //run MCMC
    final CopyRatioModeller modeller = new CopyRatioModeller(segmentedGenome);
    modeller.fitMCMC(NUM_SAMPLES, NUM_BURN_IN);
    //check statistics of global-parameter posterior samples (i.e., posterior mode and standard deviation)
    final Map<CopyRatioParameter, PosteriorSummary> globalParameterPosteriorSummaries = modeller.getGlobalParameterPosteriorSummaries(CREDIBLE_INTERVAL_ALPHA, ctx);
    final PosteriorSummary variancePosteriorSummary = globalParameterPosteriorSummaries.get(CopyRatioParameter.VARIANCE);
    final double variancePosteriorCenter = variancePosteriorSummary.getCenter();
    final double variancePosteriorStandardDeviation = (variancePosteriorSummary.getUpper() - variancePosteriorSummary.getLower()) / 2;
    Assert.assertEquals(Math.abs(variancePosteriorCenter - VARIANCE_TRUTH), 0., MULTIPLES_OF_SD_THRESHOLD * VARIANCE_POSTERIOR_STANDARD_DEVIATION_TRUTH);
    Assert.assertEquals(relativeError(variancePosteriorStandardDeviation, VARIANCE_POSTERIOR_STANDARD_DEVIATION_TRUTH), 0., RELATIVE_ERROR_THRESHOLD);
    final PosteriorSummary outlierProbabilityPosteriorSummary = globalParameterPosteriorSummaries.get(CopyRatioParameter.OUTLIER_PROBABILITY);
    final double outlierProbabilityPosteriorCenter = outlierProbabilityPosteriorSummary.getCenter();
    final double outlierProbabilityPosteriorStandardDeviation = (outlierProbabilityPosteriorSummary.getUpper() - outlierProbabilityPosteriorSummary.getLower()) / 2;
    Assert.assertEquals(Math.abs(outlierProbabilityPosteriorCenter - OUTLIER_PROBABILITY_TRUTH), 0., MULTIPLES_OF_SD_THRESHOLD * OUTLIER_PROBABILITY_POSTERIOR_STANDARD_DEVIATION_TRUTH);
    Assert.assertEquals(relativeError(outlierProbabilityPosteriorStandardDeviation, OUTLIER_PROBABILITY_POSTERIOR_STANDARD_DEVIATION_TRUTH), 0., RELATIVE_ERROR_THRESHOLD);
    //check statistics of segment-mean posterior samples (i.e., posterior means and standard deviations)
    final List<Double> meansTruth = loadList(MEANS_TRUTH_FILE, Double::parseDouble);
    int numMeansOutsideOneSigma = 0;
    int numMeansOutsideTwoSigma = 0;
    int numMeansOutsideThreeSigma = 0;
    final int numSegments = meansTruth.size();
    //segment-mean posteriors are expected to be Gaussian, so PosteriorSummary for
    // {@link CopyRatioModellerUnitTest#CREDIBLE_INTERVAL_ALPHA}=0.32 is
    //(posterior mean, posterior mean - posterior standard devation, posterior mean + posterior standard deviation)
    final List<PosteriorSummary> meanPosteriorSummaries = modeller.getSegmentMeansPosteriorSummaries(CREDIBLE_INTERVAL_ALPHA, ctx);
    final double[] meanPosteriorStandardDeviations = new double[numSegments];
    for (int segment = 0; segment < numSegments; segment++) {
        final double meanPosteriorCenter = meanPosteriorSummaries.get(segment).getCenter();
        final double meanPosteriorStandardDeviation = (meanPosteriorSummaries.get(segment).getUpper() - meanPosteriorSummaries.get(segment).getLower()) / 2.;
        meanPosteriorStandardDeviations[segment] = meanPosteriorStandardDeviation;
        final double absoluteDifferenceFromTruth = Math.abs(meanPosteriorCenter - meansTruth.get(segment));
        if (absoluteDifferenceFromTruth > meanPosteriorStandardDeviation) {
            numMeansOutsideOneSigma++;
        }
        if (absoluteDifferenceFromTruth > 2 * meanPosteriorStandardDeviation) {
            numMeansOutsideTwoSigma++;
        }
        if (absoluteDifferenceFromTruth > 3 * meanPosteriorStandardDeviation) {
            numMeansOutsideThreeSigma++;
        }
    }
    final double meanPosteriorStandardDeviationsMean = new Mean().evaluate(meanPosteriorStandardDeviations);
    Assert.assertEquals(numMeansOutsideOneSigma, 100 - 68, DELTA_NUMBER_OF_MEANS_ALLOWED_OUTSIDE_1_SIGMA);
    Assert.assertEquals(numMeansOutsideTwoSigma, 100 - 95, DELTA_NUMBER_OF_MEANS_ALLOWED_OUTSIDE_2_SIGMA);
    Assert.assertTrue(numMeansOutsideThreeSigma <= DELTA_NUMBER_OF_MEANS_ALLOWED_OUTSIDE_3_SIGMA);
    Assert.assertEquals(relativeError(meanPosteriorStandardDeviationsMean, MEAN_POSTERIOR_STANDARD_DEVIATION_MEAN_TRUTH), 0., RELATIVE_ERROR_THRESHOLD);
    //check accuracy of latent outlier-indicator posterior samples
    final List<CopyRatioState.OutlierIndicators> outlierIndicatorSamples = modeller.getOutlierIndicatorsSamples();
    int numIndicatorsCorrect = 0;
    final int numIndicatorSamples = outlierIndicatorSamples.size();
    final List<Integer> outlierIndicatorsTruthAsInt = loadList(OUTLIER_INDICATORS_TRUTH_FILE, Integer::parseInt);
    final List<Boolean> outlierIndicatorsTruth = outlierIndicatorsTruthAsInt.stream().map(i -> i == 1).collect(Collectors.toList());
    for (int target = 0; target < coverage.targets().size(); target++) {
        int numSamplesOutliers = 0;
        for (final CopyRatioState.OutlierIndicators sample : outlierIndicatorSamples) {
            if (sample.get(target)) {
                numSamplesOutliers++;
            }
        }
        //take predicted state of indicator to be given by the majority of samples
        if ((numSamplesOutliers >= numIndicatorSamples / 2.) == outlierIndicatorsTruth.get(target)) {
            numIndicatorsCorrect++;
        }
    }
    final double fractionOfOutlierIndicatorsCorrect = (double) numIndicatorsCorrect / coverage.targets().size();
    Assert.assertTrue(fractionOfOutlierIndicatorsCorrect >= FRACTION_OF_OUTLIER_INDICATORS_CORRECT_THRESHOLD);
}

Example 60 with ReadCountCollection

use of org.broadinstitute.hellbender.tools.exome.ReadCountCollection in project gatk by broadinstitute.

the class CorrectGCBiasIntegrationTest method testGCCorrection.

// test that results match expected behavior of the backing class
@Test
public void testGCCorrection() throws IOException {
    final List<String> arguments = new ArrayList<>();
    arguments.addAll(Arrays.asList("-" + CorrectGCBias.INPUT_READ_COUNTS_FILE_SHORT_NAME, INPUT_COUNTS_FILE.getAbsolutePath(), "-" + CorrectGCBias.OUTPUT_READ_COUNTS_FILE_SHORT_NAME, OUTPUT_COUNTS_FILE.getAbsolutePath(), "-" + ExomeStandardArgumentDefinitions.TARGET_FILE_SHORT_NAME, TARGETS_FILE.getAbsolutePath()));
    runCommandLine(arguments);
    final ReadCountCollection outputCounts = ReadCountCollectionUtils.parse(OUTPUT_COUNTS_FILE);
    final ReadCountCollection expectedOutputCounts = GCCorrector.correctCoverage(inputCounts, gcContentByTarget);
    Assert.assertEquals(outputCounts.columnNames(), inputCounts.columnNames());
    Assert.assertEquals(outputCounts.counts().subtract(expectedOutputCounts.counts()).getNorm(), 0, 1e-10);
}