private void buildProfiles() {
log.info("Filling repository with profiles");
List<String> referenceProfile;
List<String> referenceGeneNames;
Set<GctReplicate> gctReplicatePairs = repositoryService.getGctReplicatesCombinations();
int dummyClusteringOrder = gctReplicatePairs.size();
for (GctReplicate gctReplicate : gctReplicatePairs) {
GctFile gctFile = gctReplicate.getGctFile();
ReplicateAnnotation replicateAnnotation = gctReplicate.getReplicateAnnotation();
List<PeakArea> peakAreas =
peakAreaRepository.findByGctFileAndReplicateAnnotation(gctFile, replicateAnnotation);
AssayType assayType = gctFile.getAssayType();
referenceProfile = getReferenceProfile(assayType);
referenceGeneNames = getReferenceGeneNames(assayType);
Double[] profileVector = new Double[referenceProfile.size()];
boolean[] imputeVector = new boolean[referenceProfile.size()];
for (PeakArea peakArea : peakAreas) {
int index = referenceProfile.indexOf(peakArea.getPeptideAnnotation().getPeptideId());
profileVector[index] = peakArea.getValue();
}
UtilsStatistics.imputeProfileVector(profileVector, imputeVector);
Profile profile =
new Profile(
replicateAnnotation,
gctFile,
ArrayUtils.toPrimitive(profileVector),
imputeVector,
referenceProfile,
referenceGeneNames,
dummyClusteringOrder--);
profileRepository.save(profile);
}
}
private void computeCorrelations() {
log.info("Filling repository with most correlated profiles");
List<String> referenceProfile;
for (AssayType assayType : AssayType.values()) {
referenceProfile = getReferenceProfile(assayType);
List<Profile> profiles = profileRepository.findByAssayType(assayType);
String[] profileNames = new String[profiles.size()];
double[][] distanceMatrix = new double[profiles.size()][profiles.size()];
int i = 0;
for (Profile profileA : profiles) {
profileNames[i] = profileA.getId().toString();
Double maxPearson = Double.MIN_VALUE;
Profile maxProfile = profileA;
int j = 0;
for (Profile profileB : profiles) {
if (profileA.equals(profileB)) {
distanceMatrix[i][j] = 0;
j++;
continue;
}
double[] vectorA = profileA.getVector();
double[] vectorB = profileB.getVector();
PearsonsCorrelation pearson = new PearsonsCorrelation();
Double pearsonCorrelation = pearson.correlation(vectorA, vectorB);
if (pearsonCorrelation >= maxPearson) {
maxPearson = pearsonCorrelation;
maxProfile = profileB;
}
double[] profileAasDouble = UtilsTransform.intArrayToDouble(profileA.getColors());
double[] profileBasDouble = UtilsTransform.intArrayToDouble(profileB.getColors());
Double pearsonOfColors = pearson.correlation(profileAasDouble, profileBasDouble);
distanceMatrix[i][j] = pearsonOfColors;
j++;
}
profileA.setCorrelatedVector(maxProfile.getListWrapper());
SortedSet<StringDouble> positivePeptides =
UtilsStatistics.influentialPeptides(
profileA.getVector(), maxProfile.getVector(), referenceProfile, true);
profileA.setPositivePeptides(UtilsTransform.SortedSetToHTML(positivePeptides, false));
DecimalFormat df = new DecimalFormat("0.0000");
String peptideCorrelation = " <br/><br/><b style=\"color: #23527c;\">%s</b>";
profileA.setPositiveCorrelation(
maxProfile.toString() + String.format(peptideCorrelation, df.format(maxPearson)));
profileRepository.save(profileA);
i++;
}
}
}