Examples with ExperimentalFactor ubic.gemma.model.expression.experiment.ExperimentalFactor used on opensource projects

Example 36 with ExperimentalFactor

use of ubic.gemma.model.expression.experiment.ExperimentalFactor in project Gemma by PavlidisLab.

the class SVDServiceHelperImpl method getImportantFactors.

@Override
public Set<ExperimentalFactor> getImportantFactors(ExpressionExperiment ee, Collection<ExperimentalFactor> experimentalFactors, Double importanceThreshold) {
    Set<ExperimentalFactor> importantFactors = new HashSet<>();
    if (experimentalFactors.isEmpty()) {
        return importantFactors;
    }
    Map<Long, ExperimentalFactor> factors = EntityUtils.getIdMap(experimentalFactors);
    SVDValueObject svdFactorAnalysis = this.svdFactorAnalysis(ee);
    if (svdFactorAnalysis == null) {
        return importantFactors;
    }
    Map<Integer, Map<Long, Double>> factorPVals = svdFactorAnalysis.getFactorPvals();
    for (Integer cmp : factorPVals.keySet()) {
        Map<Long, Double> factorPv = factorPVals.get(cmp);
        for (Long efId : factorPv.keySet()) {
            Double pvalue = factorPv.get(efId);
            ExperimentalFactor ef = factors.get(efId);
            if (pvalue < importanceThreshold) {
                assert factors.containsKey(efId);
                SVDServiceHelperImpl.log.info(ef + " retained at p=" + String.format("%.2g", pvalue) + " for PC" + cmp);
                importantFactors.add(ef);
            } else {
                SVDServiceHelperImpl.log.info(ef + " not retained at p=" + String.format("%.2g", pvalue) + " for PC" + cmp);
            }
        }
    }
    return importantFactors;
}

Example 37 with ExperimentalFactor

use of ubic.gemma.model.expression.experiment.ExperimentalFactor in project Gemma by PavlidisLab.

the class SVDServiceHelperImpl method svdFactorAnalysis.

@Override
public SVDValueObject svdFactorAnalysis(PrincipalComponentAnalysis pca) {
    BioAssayDimension bad = pca.getBioAssayDimension();
    List<BioAssay> bioAssays = bad.getBioAssays();
    SVDValueObject svo;
    try {
        svo = new SVDValueObject(pca);
    } catch (Exception e) {
        SVDServiceHelperImpl.log.error(e.getLocalizedMessage());
        return null;
    }
    Map<Long, Date> bioMaterialDates = new HashMap<>();
    Map<ExperimentalFactor, Map<Long, Double>> bioMaterialFactorMap = new HashMap<>();
    this.prepareForFactorComparisons(svo, bioAssays, bioMaterialDates, bioMaterialFactorMap);
    if (bioMaterialDates.isEmpty() && bioMaterialFactorMap.isEmpty()) {
        SVDServiceHelperImpl.log.warn("No factor or date information to compare to the eigenGenes");
        return svo;
    }
    Long[] svdBioMaterials = svo.getBioMaterialIds();
    svo.getDateCorrelations().clear();
    svo.getFactorCorrelations().clear();
    svo.getDates().clear();
    svo.getFactors().clear();
    for (int componentNumber = 0; componentNumber < Math.min(svo.getvMatrix().columns(), SVDServiceHelperImpl.MAX_EIGEN_GENES_TO_TEST); componentNumber++) {
        this.analyzeComponent(svo, componentNumber, svo.getvMatrix(), bioMaterialDates, bioMaterialFactorMap, svdBioMaterials);
    }
    return svo;
}

Example 38 with ExperimentalFactor

use of ubic.gemma.model.expression.experiment.ExperimentalFactor in project Gemma by PavlidisLab.

the class SVDServiceHelperImpl method populateBMFMap.

public static void populateBMFMap(Map<ExperimentalFactor, Map<Long, Double>> bioMaterialFactorMap, BioMaterial bm) {
    for (FactorValue fv : bm.getFactorValues()) {
        ExperimentalFactor experimentalFactor = fv.getExperimentalFactor();
        if (!bioMaterialFactorMap.containsKey(experimentalFactor)) {
            bioMaterialFactorMap.put(experimentalFactor, new HashMap<Long, Double>());
        }
        double valueToStore;
        if (fv.getMeasurement() != null) {
            try {
                valueToStore = Double.parseDouble(fv.getMeasurement().getValue());
            } catch (NumberFormatException e) {
                SVDServiceHelperImpl.log.warn("Measurement wasn't a number for " + fv);
                valueToStore = Double.NaN;
            }
        } else {
            /*
                 * This is a hack. We're storing the ID but as a double.
                 */
            valueToStore = fv.getId().doubleValue();
        }
        bioMaterialFactorMap.get(experimentalFactor).put(bm.getId(), valueToStore);
    }
}

Example 39 with ExperimentalFactor

use of ubic.gemma.model.expression.experiment.ExperimentalFactor in project Gemma by PavlidisLab.

the class BatchConfound method getBioMaterialFactorMap.

private static Map<ExperimentalFactor, Map<Long, Double>> getBioMaterialFactorMap(ExpressionExperiment ee) {
    Map<ExperimentalFactor, Map<Long, Double>> bioMaterialFactorMap = new HashMap<>();
    for (BioAssay bioAssay : ee.getBioAssays()) {
        BioMaterial bm = bioAssay.getSampleUsed();
        SVDServiceHelperImpl.populateBMFMap(bioMaterialFactorMap, bm);
    }
    return bioMaterialFactorMap;
}

Example 40 with ExperimentalFactor

use of ubic.gemma.model.expression.experiment.ExperimentalFactor in project Gemma by PavlidisLab.

the class BatchConfound method factorBatchConfoundTest.

private static Collection<BatchConfoundValueObject> factorBatchConfoundTest(ExpressionExperiment ee, Map<ExperimentalFactor, Map<Long, Double>> bioMaterialFactorMap) throws IllegalArgumentException {
    Map<Long, Long> batchMembership = new HashMap<>();
    ExperimentalFactor batchFactor = null;
    Map<Long, Integer> batchIndexes = new HashMap<>();
    for (ExperimentalFactor ef : bioMaterialFactorMap.keySet()) {
        if (ExperimentalDesignUtils.isBatch(ef)) {
            batchFactor = ef;
            Map<Long, Double> bmToFv = bioMaterialFactorMap.get(batchFactor);
            if (bmToFv == null) {
                log.warn("No biomaterial --> factor value map for batch factor: " + batchFactor);
                continue;
            }
            int index = 0;
            for (FactorValue fv : batchFactor.getFactorValues()) {
                batchIndexes.put(fv.getId(), index++);
            }
            for (Long bmId : bmToFv.keySet()) {
                batchMembership.put(bmId, bmToFv.get(bmId).longValue());
            }
            break;
        }
    }
    Set<BatchConfoundValueObject> result = new HashSet<>();
    if (batchFactor == null) {
        return result;
    }
    for (ExperimentalFactor ef : bioMaterialFactorMap.keySet()) {
        if (ef.equals(batchFactor))
            continue;
        Map<Long, Double> bmToFv = bioMaterialFactorMap.get(ef);
        int numBioMaterials = bmToFv.keySet().size();
        assert numBioMaterials > 0 : "No biomaterials for " + ef;
        double p = Double.NaN;
        double chiSquare;
        int df;
        int numBatches = batchFactor.getFactorValues().size();
        if (ExperimentalDesignUtils.isContinuous(ef)) {
            DoubleArrayList factorValues = new DoubleArrayList(numBioMaterials);
            factorValues.setSize(numBioMaterials);
            IntArrayList batches = new IntArrayList(numBioMaterials);
            batches.setSize(numBioMaterials);
            int j = 0;
            for (Long bmId : bmToFv.keySet()) {
                assert factorValues.size() > 0 : "Biomaterial to factorValue is empty for " + ef;
                factorValues.set(j, bmToFv.get(bmId));
                long batch = batchMembership.get(bmId);
                batches.set(j, batchIndexes.get(batch));
                j++;
            }
            p = KruskalWallis.test(factorValues, batches);
            df = KruskalWallis.dof(factorValues, batches);
            chiSquare = KruskalWallis.kwStatistic(factorValues, batches);
            log.debug("KWallis\t" + ee.getId() + "\t" + ee.getShortName() + "\t" + ef.getId() + "\t" + ef.getName() + "\t" + String.format("%.2f", chiSquare) + "\t" + df + "\t" + String.format("%.2g", p) + "\t" + numBatches);
        } else {
            Map<Long, Integer> factorValueIndexes = new HashMap<>();
            int index = 0;
            for (FactorValue fv : ef.getFactorValues()) {
                factorValueIndexes.put(fv.getId(), index++);
            }
            Map<Long, Long> factorValueMembership = new HashMap<>();
            for (Long bmId : bmToFv.keySet()) {
                factorValueMembership.put(bmId, bmToFv.get(bmId).longValue());
            }
            long[][] counts = new long[numBatches][ef.getFactorValues().size()];
            for (int i = 0; i < batchIndexes.size(); i++) {
                for (int j = 0; j < factorValueIndexes.size(); j++) {
                    counts[i][j] = 0;
                }
            }
            for (Long bm : bmToFv.keySet()) {
                long fv = factorValueMembership.get(bm);
                Long batch = batchMembership.get(bm);
                if (batch == null) {
                    log.warn("No batch membership for : " + bm);
                    continue;
                }
                int batchIndex = batchIndexes.get(batch);
                int factorIndex = factorValueIndexes.get(fv);
                counts[batchIndex][factorIndex]++;
            }
            ChiSquareTest cst = new ChiSquareTest();
            try {
                chiSquare = cst.chiSquare(counts);
            } catch (IllegalArgumentException e) {
                log.warn("IllegalArgumentException exception computing ChiSq for : " + ef + "; Error was: " + e.getMessage());
                chiSquare = Double.NaN;
            }
            df = (counts.length - 1) * (counts[0].length - 1);
            ChiSquaredDistribution distribution = new ChiSquaredDistribution(df);
            if (!Double.isNaN(chiSquare)) {
                p = 1.0 - distribution.cumulativeProbability(chiSquare);
            }
            log.debug("ChiSq\t" + ee.getId() + "\t" + ee.getShortName() + "\t" + ef.getId() + "\t" + ef.getName() + "\t" + String.format("%.2f", chiSquare) + "\t" + df + "\t" + String.format("%.2g", p) + "\t" + numBatches);
        }
        BatchConfoundValueObject summary = new BatchConfoundValueObject(ee, ef, chiSquare, df, p, numBatches);
        result.add(summary);
    }
    return result;
}