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

Example 1 with SexGenotypeData

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

the class CoverageModelEMWorkspace method getCopyRatioSegmentsSpark.

/**
     * Fetch copy ratio segments from compute blocks (Spark implementation)
     *
     * @return a list of {@link CopyRatioHMMResults}
     */
private List<List<HiddenStateSegmentRecord<STATE, Target>>> getCopyRatioSegmentsSpark() {
    /* local final member variables for lambda capture */
    final List<Target> processedTargetList = new ArrayList<>();
    processedTargetList.addAll(this.processedTargetList);
    final List<SexGenotypeData> processedSampleSexGenotypeData = new ArrayList<>();
    processedSampleSexGenotypeData.addAll(this.processedSampleSexGenotypeData);
    final List<String> processedSampleNameList = new ArrayList<>();
    processedSampleNameList.addAll(this.processedSampleNameList);
    final INDArray sampleReadDepths = Transforms.exp(sampleMeanLogReadDepths, true);
    final CopyRatioExpectationsCalculator<CoverageModelCopyRatioEmissionData, STATE> copyRatioExpectationsCalculator = this.copyRatioExpectationsCalculator;
    final BiFunction<SexGenotypeData, Target, STATE> referenceStateFactory = this.referenceStateFactory;
    return fetchCopyRatioEmissionDataSpark().mapPartitionsToPair(it -> {
        final List<Tuple2<Integer, CopyRatioHMMResults<CoverageModelCopyRatioEmissionData, STATE>>> newPartitionData = new ArrayList<>();
        while (it.hasNext()) {
            final Tuple2<Integer, List<CoverageModelCopyRatioEmissionData>> prevDatum = it.next();
            final int sampleIndex = prevDatum._1;
            final CopyRatioCallingMetadata copyRatioCallingMetadata = CopyRatioCallingMetadata.builder().sampleName(processedSampleNameList.get(sampleIndex)).sampleSexGenotypeData(processedSampleSexGenotypeData.get(sampleIndex)).sampleCoverageDepth(sampleReadDepths.getDouble(sampleIndex)).emissionCalculationStrategy(EmissionCalculationStrategy.HYBRID_POISSON_GAUSSIAN).build();
            newPartitionData.add(new Tuple2<>(sampleIndex, copyRatioExpectationsCalculator.getCopyRatioHMMResults(copyRatioCallingMetadata, processedTargetList, prevDatum._2)));
        }
        return newPartitionData.iterator();
    }, true).mapPartitionsToPair(it -> {
        final List<Tuple2<Integer, List<HiddenStateSegmentRecord<STATE, Target>>>> newPartitionData = new ArrayList<>();
        while (it.hasNext()) {
            final Tuple2<Integer, CopyRatioHMMResults<CoverageModelCopyRatioEmissionData, STATE>> prevDatum = it.next();
            final int sampleIndex = prevDatum._1;
            final CopyRatioHMMResults<CoverageModelCopyRatioEmissionData, STATE> result = prevDatum._2;
            final HMMSegmentProcessor<CoverageModelCopyRatioEmissionData, STATE, Target> processor = new HMMSegmentProcessor<>(Collections.singletonList(result.getMetaData().getSampleName()), Collections.singletonList(result.getMetaData().getSampleSexGenotypeData()), referenceStateFactory, Collections.singletonList(new HashedListTargetCollection<>(processedTargetList)), Collections.singletonList(result.getForwardBackwardResult()), Collections.singletonList(result.getViterbiResult()));
            newPartitionData.add(new Tuple2<>(sampleIndex, processor.getSegmentsAsList()));
        }
        return newPartitionData.iterator();
    }).collect().stream().sorted(Comparator.comparingInt(t -> t._1)).map(t -> t._2).collect(Collectors.toList());
}

Example 2 with SexGenotypeData

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

the class CoverageModelEMWorkspace method updateCopyRatioPosteriorExpectationsSpark.

/**
     * The Spark implementation of the E-step update of copy ratio posteriors
     *
     * @return a {@link SubroutineSignal} containing the update size
     */
@EvaluatesRDD
@UpdatesRDD
@CachesRDD
private SubroutineSignal updateCopyRatioPosteriorExpectationsSpark(final double admixingRatio) {
    /* local final member variables for lambda capture */
    final List<LinearlySpacedIndexBlock> targetBlocks = new ArrayList<>();
    targetBlocks.addAll(this.targetBlocks);
    final List<Target> targetList = new ArrayList<>();
    targetList.addAll(processedTargetList);
    final List<String> sampleNameList = new ArrayList<>();
    sampleNameList.addAll(processedSampleNameList);
    final List<SexGenotypeData> sampleSexGenotypeData = new ArrayList<>();
    sampleSexGenotypeData.addAll(processedSampleSexGenotypeData);
    final int numTargetBlocks = targetBlocks.size();
    final CopyRatioExpectationsCalculator<CoverageModelCopyRatioEmissionData, STATE> calculator = this.copyRatioExpectationsCalculator;
    final INDArray sampleReadDepths = Transforms.exp(sampleMeanLogReadDepths, true);
    /* make an RDD of copy ratio posterior expectations */
    final JavaPairRDD<Integer, CopyRatioExpectations> copyRatioPosteriorExpectationsPairRDD = /* fetch copy ratio emission data from workers */
    fetchCopyRatioEmissionDataSpark().mapPartitionsToPair(it -> {
        final List<Tuple2<Integer, CopyRatioExpectations>> newPartitionData = new ArrayList<>();
        while (it.hasNext()) {
            final Tuple2<Integer, List<CoverageModelCopyRatioEmissionData>> prevDatum = it.next();
            final int si = prevDatum._1;
            final CopyRatioCallingMetadata copyRatioCallingMetadata = CopyRatioCallingMetadata.builder().sampleName(sampleNameList.get(si)).sampleSexGenotypeData(sampleSexGenotypeData.get(si)).sampleCoverageDepth(sampleReadDepths.getDouble(si)).emissionCalculationStrategy(EmissionCalculationStrategy.HYBRID_POISSON_GAUSSIAN).build();
            newPartitionData.add(new Tuple2<>(prevDatum._1, calculator.getCopyRatioPosteriorExpectations(copyRatioCallingMetadata, targetList, prevDatum._2)));
        }
        return newPartitionData.iterator();
    }, true);
    /* we need to do two things to copyRatioPosteriorExpectationsPairRDD; so we cache it */
    /* step 1. update log chain posterior expectation on the driver node */
    final double[] newSampleLogChainPosteriors = copyRatioPosteriorExpectationsPairRDD.mapValues(CopyRatioExpectations::getLogChainPosteriorProbability).collect().stream().sorted(Comparator.comparingInt(t -> t._1)).mapToDouble(t -> t._2).toArray();
    sampleLogChainPosteriors.assign(Nd4j.create(newSampleLogChainPosteriors, new int[] { numSamples, 1 }));
    /* step 2. repartition in target space */
    final JavaPairRDD<LinearlySpacedIndexBlock, ImmutablePair<INDArray, INDArray>> blockifiedCopyRatioPosteriorResultsPairRDD = copyRatioPosteriorExpectationsPairRDD.flatMapToPair(dat -> targetBlocks.stream().map(tb -> new Tuple2<>(tb, new Tuple2<>(dat._1, ImmutablePair.of(dat._2.getLogCopyRatioMeans(tb), dat._2.getLogCopyRatioVariances(tb))))).iterator()).combineByKey(/* recipe to create an singleton list */
    Collections::singletonList, /* recipe to add an element to the list */
    (list, element) -> Stream.concat(list.stream(), Stream.of(element)).collect(Collectors.toList()), /* recipe to concatenate two lists */
    (list1, list2) -> Stream.concat(list1.stream(), list2.stream()).collect(Collectors.toList()), /* repartition with respect to target space blocks */
    new HashPartitioner(numTargetBlocks)).mapValues(list -> list.stream().sorted(Comparator.comparingInt(t -> t._1)).map(p -> p._2).map(t -> ImmutablePair.of(Nd4j.create(t.left), Nd4j.create(t.right))).collect(Collectors.toList())).mapValues(CoverageModelEMWorkspace::stackCopyRatioPosteriorDataForAllSamples);
    /* we do not need copy ratio expectations anymore */
    copyRatioPosteriorExpectationsPairRDD.unpersist();
    /* step 3. merge with computeRDD and update */
    computeRDD = computeRDD.join(blockifiedCopyRatioPosteriorResultsPairRDD).mapValues(t -> t._1.cloneWithUpdatedCopyRatioPosteriors(t._2.left, t._2.right, admixingRatio));
    cacheWorkers("after E-step for copy ratio update");
    /* collect subroutine signals */
    final List<SubroutineSignal> sigs = mapWorkersAndCollect(CoverageModelEMComputeBlock::getLatestMStepSignal);
    final double errorNormInfinity = Collections.max(sigs.stream().map(sig -> sig.<Double>get(StandardSubroutineSignals.RESIDUAL_ERROR_NORM)).collect(Collectors.toList()));
    return SubroutineSignal.builder().put(StandardSubroutineSignals.RESIDUAL_ERROR_NORM, errorNormInfinity).build();
}

Example 3 with SexGenotypeData

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

the class CoverageModelEMWorkspace method getViterbiAsNDArray.

/**
     * Fetches the Viterbi copy ratio (or copy number) states as a target-sample matrix
     *
     * @return an {@link INDArray}
     */
protected INDArray getViterbiAsNDArray(final List<List<HiddenStateSegmentRecord<STATE, Target>>> segments) {
    final INDArray res = Nd4j.create(numSamples, numTargets);
    final TargetCollection<Target> targetCollection = new HashedListTargetCollection<>(processedTargetList);
    for (int si = 0; si < numSamples; si++) {
        final SexGenotypeData sampleSexGenotype = processedSampleSexGenotypeData.get(si);
        /* start with all ref */
        final double[] calls = IntStream.range(0, numTargets).mapToDouble(ti -> referenceStateFactory.apply(sampleSexGenotype, processedTargetList.get(ti)).getScalar()).toArray();
        /* go through segments and mutate ref calls as necessary */
        segments.get(si).forEach(seg -> {
            final IndexRange range = targetCollection.indexRange(seg.getSegment());
            final double copyRatio = seg.getSegment().getCall().getScalar();
            for (int ti = range.from; ti < range.to; ti++) {
                calls[ti] = copyRatio;
            }
        });
        res.get(NDArrayIndex.point(si), NDArrayIndex.all()).assign(Nd4j.create(calls, new int[] { 1, numTargets }));
    }
    return res.transpose();
}

Example 4 with SexGenotypeData

use of org.broadinstitute.hellbender.tools.exome.sexgenotyper.SexGenotypeData in project gatk-protected by broadinstitute.

the class CoverageModelEMWorkspace method updateCopyRatioPosteriorExpectationsSpark.

/**
     * The Spark implementation of the E-step update of copy ratio posteriors
     *
     * @return a {@link SubroutineSignal} containing the update size
     */
@EvaluatesRDD
@UpdatesRDD
@CachesRDD
private SubroutineSignal updateCopyRatioPosteriorExpectationsSpark(final double admixingRatio) {
    /* local final member variables for lambda capture */
    final List<LinearlySpacedIndexBlock> targetBlocks = new ArrayList<>();
    targetBlocks.addAll(this.targetBlocks);
    final List<Target> targetList = new ArrayList<>();
    targetList.addAll(processedTargetList);
    final List<String> sampleNameList = new ArrayList<>();
    sampleNameList.addAll(processedSampleNameList);
    final List<SexGenotypeData> sampleSexGenotypeData = new ArrayList<>();
    sampleSexGenotypeData.addAll(processedSampleSexGenotypeData);
    final int numTargetBlocks = targetBlocks.size();
    final CopyRatioExpectationsCalculator<CoverageModelCopyRatioEmissionData, STATE> calculator = this.copyRatioExpectationsCalculator;
    final INDArray sampleReadDepths = Transforms.exp(sampleMeanLogReadDepths, true);
    /* make an RDD of copy ratio posterior expectations */
    final JavaPairRDD<Integer, CopyRatioExpectations> copyRatioPosteriorExpectationsPairRDD = /* fetch copy ratio emission data from workers */
    fetchCopyRatioEmissionDataSpark().mapPartitionsToPair(it -> {
        final List<Tuple2<Integer, CopyRatioExpectations>> newPartitionData = new ArrayList<>();
        while (it.hasNext()) {
            final Tuple2<Integer, List<CoverageModelCopyRatioEmissionData>> prevDatum = it.next();
            final int si = prevDatum._1;
            final CopyRatioCallingMetadata copyRatioCallingMetadata = CopyRatioCallingMetadata.builder().sampleName(sampleNameList.get(si)).sampleSexGenotypeData(sampleSexGenotypeData.get(si)).sampleCoverageDepth(sampleReadDepths.getDouble(si)).emissionCalculationStrategy(EmissionCalculationStrategy.HYBRID_POISSON_GAUSSIAN).build();
            newPartitionData.add(new Tuple2<>(prevDatum._1, calculator.getCopyRatioPosteriorExpectations(copyRatioCallingMetadata, targetList, prevDatum._2)));
        }
        return newPartitionData.iterator();
    }, true);
    /* we need to do two things to copyRatioPosteriorExpectationsPairRDD; so we cache it */
    /* step 1. update log chain posterior expectation on the driver node */
    final double[] newSampleLogChainPosteriors = copyRatioPosteriorExpectationsPairRDD.mapValues(CopyRatioExpectations::getLogChainPosteriorProbability).collect().stream().sorted(Comparator.comparingInt(t -> t._1)).mapToDouble(t -> t._2).toArray();
    sampleLogChainPosteriors.assign(Nd4j.create(newSampleLogChainPosteriors, new int[] { numSamples, 1 }));
    /* step 2. repartition in target space */
    final JavaPairRDD<LinearlySpacedIndexBlock, ImmutablePair<INDArray, INDArray>> blockifiedCopyRatioPosteriorResultsPairRDD = copyRatioPosteriorExpectationsPairRDD.flatMapToPair(dat -> targetBlocks.stream().map(tb -> new Tuple2<>(tb, new Tuple2<>(dat._1, ImmutablePair.of(dat._2.getLogCopyRatioMeans(tb), dat._2.getLogCopyRatioVariances(tb))))).iterator()).combineByKey(/* recipe to create an singleton list */
    Collections::singletonList, /* recipe to add an element to the list */
    (list, element) -> Stream.concat(list.stream(), Stream.of(element)).collect(Collectors.toList()), /* recipe to concatenate two lists */
    (list1, list2) -> Stream.concat(list1.stream(), list2.stream()).collect(Collectors.toList()), /* repartition with respect to target space blocks */
    new HashPartitioner(numTargetBlocks)).mapValues(list -> list.stream().sorted(Comparator.comparingInt(t -> t._1)).map(p -> p._2).map(t -> ImmutablePair.of(Nd4j.create(t.left), Nd4j.create(t.right))).collect(Collectors.toList())).mapValues(CoverageModelEMWorkspace::stackCopyRatioPosteriorDataForAllSamples);
    /* we do not need copy ratio expectations anymore */
    copyRatioPosteriorExpectationsPairRDD.unpersist();
    /* step 3. merge with computeRDD and update */
    computeRDD = computeRDD.join(blockifiedCopyRatioPosteriorResultsPairRDD).mapValues(t -> t._1.cloneWithUpdatedCopyRatioPosteriors(t._2.left, t._2.right, admixingRatio));
    cacheWorkers("after E-step for copy ratio update");
    /* collect subroutine signals */
    final List<SubroutineSignal> sigs = mapWorkersAndCollect(CoverageModelEMComputeBlock::getLatestMStepSignal);
    final double errorNormInfinity = Collections.max(sigs.stream().map(sig -> sig.<Double>get(StandardSubroutineSignals.RESIDUAL_ERROR_NORM)).collect(Collectors.toList()));
    return SubroutineSignal.builder().put(StandardSubroutineSignals.RESIDUAL_ERROR_NORM, errorNormInfinity).build();
}

Example 5 with SexGenotypeData

use of org.broadinstitute.hellbender.tools.exome.sexgenotyper.SexGenotypeData in project gatk-protected by broadinstitute.

the class CoverageModelEMWorkspace method getCopyRatioSegmentsSpark.

/**
     * Fetch copy ratio segments from compute blocks (Spark implementation)
     *
     * @return a list of {@link CopyRatioHMMResults}
     */
private List<List<HiddenStateSegmentRecord<STATE, Target>>> getCopyRatioSegmentsSpark() {
    /* local final member variables for lambda capture */
    final List<Target> processedTargetList = new ArrayList<>();
    processedTargetList.addAll(this.processedTargetList);
    final List<SexGenotypeData> processedSampleSexGenotypeData = new ArrayList<>();
    processedSampleSexGenotypeData.addAll(this.processedSampleSexGenotypeData);
    final List<String> processedSampleNameList = new ArrayList<>();
    processedSampleNameList.addAll(this.processedSampleNameList);
    final INDArray sampleReadDepths = Transforms.exp(sampleMeanLogReadDepths, true);
    final CopyRatioExpectationsCalculator<CoverageModelCopyRatioEmissionData, STATE> copyRatioExpectationsCalculator = this.copyRatioExpectationsCalculator;
    final BiFunction<SexGenotypeData, Target, STATE> referenceStateFactory = this.referenceStateFactory;
    return fetchCopyRatioEmissionDataSpark().mapPartitionsToPair(it -> {
        final List<Tuple2<Integer, CopyRatioHMMResults<CoverageModelCopyRatioEmissionData, STATE>>> newPartitionData = new ArrayList<>();
        while (it.hasNext()) {
            final Tuple2<Integer, List<CoverageModelCopyRatioEmissionData>> prevDatum = it.next();
            final int sampleIndex = prevDatum._1;
            final CopyRatioCallingMetadata copyRatioCallingMetadata = CopyRatioCallingMetadata.builder().sampleName(processedSampleNameList.get(sampleIndex)).sampleSexGenotypeData(processedSampleSexGenotypeData.get(sampleIndex)).sampleCoverageDepth(sampleReadDepths.getDouble(sampleIndex)).emissionCalculationStrategy(EmissionCalculationStrategy.HYBRID_POISSON_GAUSSIAN).build();
            newPartitionData.add(new Tuple2<>(sampleIndex, copyRatioExpectationsCalculator.getCopyRatioHMMResults(copyRatioCallingMetadata, processedTargetList, prevDatum._2)));
        }
        return newPartitionData.iterator();
    }, true).mapPartitionsToPair(it -> {
        final List<Tuple2<Integer, List<HiddenStateSegmentRecord<STATE, Target>>>> newPartitionData = new ArrayList<>();
        while (it.hasNext()) {
            final Tuple2<Integer, CopyRatioHMMResults<CoverageModelCopyRatioEmissionData, STATE>> prevDatum = it.next();
            final int sampleIndex = prevDatum._1;
            final CopyRatioHMMResults<CoverageModelCopyRatioEmissionData, STATE> result = prevDatum._2;
            final HMMSegmentProcessor<CoverageModelCopyRatioEmissionData, STATE, Target> processor = new HMMSegmentProcessor<>(Collections.singletonList(result.getMetaData().getSampleName()), Collections.singletonList(result.getMetaData().getSampleSexGenotypeData()), referenceStateFactory, Collections.singletonList(new HashedListTargetCollection<>(processedTargetList)), Collections.singletonList(result.getForwardBackwardResult()), Collections.singletonList(result.getViterbiResult()));
            newPartitionData.add(new Tuple2<>(sampleIndex, processor.getSegmentsAsList()));
        }
        return newPartitionData.iterator();
    }).collect().stream().sorted(Comparator.comparingInt(t -> t._1)).map(t -> t._2).collect(Collectors.toList());
}