use of de.bioforscher.jstructure.model.structure.aminoacid.AminoAcid in project jstructure by JonStargaryen.
the class ProteinParserTest method shouldHandleProteinWithOligopeptide.
@Test
public void shouldHandleProteinWithOligopeptide() {
Protein protein = ProteinParser.source("1lyb").parse();
// contains peptide-like groups - ought to be an AminoAcid
AminoAcid statine = (AminoAcid) protein.select().groupName("STA").asGroup();
Assert.assertTrue(statine.getPolymerType() == GroupPrototype.PolymerType.PEPTIDE_LIKE);
Assert.assertTrue(statine.isAminoAcid());
Assert.assertFalse(statine.isLigand());
Assert.assertTrue(protein.aminoAcids().collect(Collectors.toList()).contains(statine));
}
use of de.bioforscher.jstructure.model.structure.aminoacid.AminoAcid in project jstructure by JonStargaryen.
the class A06_WriteStructuralInformationByResidueCsv method handleLine.
private static Optional<String> handleLine(String line) {
try {
System.out.println(line);
String[] split = line.split(";");
String entryId = split[0];
String pdbId = split[1];
List<Integer> experimentIds = Pattern.compile(",").splitAsStream(split[2].replaceAll("\\[", "").replaceAll("]", "")).map(Integer::valueOf).collect(Collectors.toList());
// boolean sane = split[6].equalsIgnoreCase("true");
Structure structure = StructureParser.fromPdbId(pdbId).parse();
Chain chain = structure.chains().findFirst().get();
Path start2foldXml = Start2FoldConstants.XML_DIRECTORY.resolve(entryId + ".xml");
Start2FoldXmlParser.parseStability(chain, start2foldXml);
Start2FoldXmlParser.parseSpecificExperiment(chain, start2foldXml, experimentIds);
try {
EvolutionaryCouplingParser.parseHotSpotFile(chain, Start2FoldConstants.COUPLING_DIRECTORY.resolve(entryId.toUpperCase() + "_hs.html"));
} catch (Exception e) {
}
boolean ecAnnotation = chain.aminoAcids().anyMatch(residue -> residue.getFeature(HotSpotScoring.class).getEcCount() > 0);
List<AminoAcid> topScoringResidues;
if (ecAnnotation) {
double fraction = 0.4;
int residuesToSelect = (int) (fraction * chain.aminoAcids().count());
topScoringResidues = chain.aminoAcids().sorted(Comparator.comparingDouble((AminoAcid aminoAcid) -> aminoAcid.getFeature(HotSpotScoring.class).getCumStrength()).reversed()).limit(residuesToSelect).collect(Collectors.toList());
} else {
topScoringResidues = new ArrayList<>();
}
EQuantParser.parseEQuantFile(chain, Start2FoldConstants.EQUANT_DIRECTORY.resolve(entryId.toLowerCase() + ".equant-small.txt"));
List<AminoAcid> earlyFoldingResidues = chain.aminoAcids().filter(aminoAcid -> aminoAcid.getFeature(Start2FoldResidueAnnotation.class).isEarly()).collect(Collectors.toList());
List<AminoAcid> strongResidues = chain.aminoAcids().filter(aminoAcid -> aminoAcid.getFeature(Start2FoldResidueAnnotation.class).isStrong()).collect(Collectors.toList());
List<Integer> functionalResidueNumbers = Start2FoldConstants.extractFunctionalResidueNumbers(split);
List<AminoAcid> functionalResidues = new ArrayList<>();
// do nothing if no annotation of functional residues exists
if (!functionalResidueNumbers.isEmpty()) {
FunctionalResidueParser.parse(chain, functionalResidueNumbers);
chain.aminoAcids().filter(aminoAcid -> aminoAcid.getFeature(FunctionalResidueAnnotation.class).isFunctional()).forEach(functionalResidues::add);
}
List<AminoAcid> aminoAcids = chain.aminoAcids().collect(Collectors.toList());
List<ContactStructuralInformation> contactStructuralInformation = StructuralInformationParserService.getInstance().parseContactStructuralInformation(Start2FoldConstants.DATA_DIRECTORY.resolve("si").resolve("raw").resolve(entryId.toUpperCase() + ".out"), chain, earlyFoldingResidues);
List<ResidueStructuralInformation> residueStructuralInformation = StructuralInformationParserService.getInstance().composeResidueStructuralInformation(aminoAcids, earlyFoldingResidues, contactStructuralInformation);
ResidueGraph conventionalProteinGraph = ResidueGraph.createResidueGraph(chain, ContactDefinitionFactory.createAlphaCarbonContactDefinition(8.0));
List<AminoAcid> residuesInEarlyFoldingSecondaryStructureElements = chain.aminoAcids().filter(aminoAcid -> !aminoAcid.getFeature(GenericSecondaryStructure.class).getSecondaryStructure().isCoilType()).filter(aminoAcid -> {
GenericSecondaryStructure.SecondaryStructureElement surroundingSecondaryStructureElement = aminoAcid.getFeature(GenericSecondaryStructure.class).getSurroundingSecondaryStructureElement(aminoAcid);
List<AminoAcid> surroundingAminoAcids = chain.getAminoAcids().subList(surroundingSecondaryStructureElement.getStart(), surroundingSecondaryStructureElement.getEnd() + 1);
return surroundingAminoAcids.stream().anyMatch(earlyFoldingResidues::contains);
}).collect(Collectors.toList());
System.out.println("efr: " + (earlyFoldingResidues.size() > 0) + " strong: " + (strongResidues.size() > 0) + " functional: " + (functionalResidues.size() > 0));
return Optional.of(chain.aminoAcids().filter(AminoAcid::isStandardAminoAcid).map(aminoAcid -> {
GenericSecondaryStructure sse = aminoAcid.getFeature(GenericSecondaryStructure.class);
HotSpotScoring hotSpotScoring = aminoAcid.getFeature(HotSpotScoring.class);
PLIPInteractionContainer plipInteractionContainer = aminoAcid.getFeature(PLIPInteractionContainer.class);
PLIPInteractionContainer nonLocalPlipInteractionContainer = new PLIPInteractionContainer(null, plipInteractionContainer.getInteractions().stream().filter(inter -> Math.abs(inter.getPartner1().getResidueIndex() - inter.getPartner2().getResidueIndex()) > 5).collect(Collectors.toList()));
PLIPInteractionContainer localPlipInteractionContainer = new PLIPInteractionContainer(null, plipInteractionContainer.getInteractions().stream().filter(inter -> !nonLocalPlipInteractionContainer.getInteractions().contains(inter)).collect(Collectors.toList()));
String equantScore = "NA";
try {
equantScore = StandardFormat.format(aminoAcid.getFeature(EQuantScore.class).getEvaluation());
} catch (ComputationException e) {
logger.warn("missing equant scoring for {}", aminoAcid);
}
String functionalAnnotation = "NA";
if (functionalResidues.size() > 0) {
functionalAnnotation = functionalResidues.contains(aminoAcid) ? "functional" : "non-functional";
}
ResidueTopologicPropertiesContainer residueTopologicPropertiesContainer = aminoAcid.getFeature(ResidueTopologicPropertiesContainer.class);
double terminusDistance = aminoAcids.indexOf(aminoAcid);
terminusDistance = Math.min(terminusDistance, aminoAcids.size() - terminusDistance);
terminusDistance /= (double) aminoAcids.size();
ResidueStructuralInformation residueStructuralInformationEntry = residueStructuralInformation.get(aminoAcid.getAminoAcidIndex());
GenericSecondaryStructure.SecondaryStructureElement surroundingSecondaryStructureElement = sse.getSurroundingSecondaryStructureElement(aminoAcid);
int sseSize = surroundingSecondaryStructureElement.getSize();
if (sse.getSecondaryStructure().isCoilType()) {
sseSize = 0;
}
int sseTerminusDistance = surroundingSecondaryStructureElement.getTerminusDistance();
if (sse.getSecondaryStructure().isCoilType()) {
sseTerminusDistance = -1;
}
return pdbId + "," + "A" + "," + aminoAcid.getResidueIdentifier() + "," + aminoAcid.getOneLetterCode() + "," + sse.getSecondaryStructure().getReducedRepresentation() + "," + sse.getSecondaryStructure().getOneLetterRepresentation() + "," + (sse.getSecondaryStructure().isHelixType() ? "true" : "false") + "," + (sse.getSecondaryStructure().isStrandType() ? "true" : "false") + "," + (sse.getSecondaryStructure().isCoilType() ? "true" : "false") + "," + sseSize + "," + sseTerminusDistance + "," + (aminoAcid.getFeature(AccessibleSurfaceArea.class).isExposed() ? "exposed" : "buried") + "," + StandardFormat.format(aminoAcid.getFeature(GeometricProperties.class).getDistanceToCentroid()) + "," + StandardFormat.format(terminusDistance) + "," + plipInteractionContainer.getHydrogenBonds().size() + "," + plipInteractionContainer.getHydrophobicInteractions().size() + "," + plipInteractionContainer.getBackboneInteractions().size() + "," + plipInteractionContainer.getInteractions().size() + "," + localPlipInteractionContainer.getHydrogenBonds().size() + "," + localPlipInteractionContainer.getHydrophobicInteractions().size() + "," + localPlipInteractionContainer.getBackboneInteractions().size() + "," + localPlipInteractionContainer.getInteractions().size() + "," + nonLocalPlipInteractionContainer.getHydrogenBonds().size() + "," + nonLocalPlipInteractionContainer.getHydrophobicInteractions().size() + "," + nonLocalPlipInteractionContainer.getBackboneInteractions().size() + "," + nonLocalPlipInteractionContainer.getInteractions().size() + "," + StandardFormat.format(aminoAcid.getFeature(EnergyProfile.class).getSolvationEnergy()) + "," + StandardFormat.format(aminoAcid.getFeature(EgorAgreement.class).getEgorPrediction()) + "," + equantScore + "," + StandardFormat.format(aminoAcid.getFeature(AccessibleSurfaceArea.class).getRelativeAccessibleSurfaceArea()) + "," + StandardFormat.format(aminoAcid.getFeature(LoopFraction.class).getLoopFraction()) + "," + hotSpotScoring.getEcCount() + "," + StandardFormat.format(hotSpotScoring.getCumStrength()) + "," + StandardFormat.format(hotSpotScoring.getEcStrength()) + "," + hotSpotScoring.getConservation() + "," + topScoringResidues.contains(aminoAcid) + "," + StandardFormat.format(residueTopologicPropertiesContainer.getFullPlip().getBetweenness()) + "," + StandardFormat.format(residueTopologicPropertiesContainer.getFullPlip().getCloseness()) + "," + StandardFormat.format(residueTopologicPropertiesContainer.getFullPlip().getClusteringCoefficient()) + "," + StandardFormat.format(residueTopologicPropertiesContainer.getHydrogenPlip().getBetweenness()) + "," + StandardFormat.format(residueTopologicPropertiesContainer.getHydrogenPlip().getCloseness()) + "," + StandardFormat.format(residueTopologicPropertiesContainer.getHydrogenPlip().getClusteringCoefficient()) + "," + StandardFormat.format(residueTopologicPropertiesContainer.getHydrophobicPlip().getBetweenness()) + "," + StandardFormat.format(residueTopologicPropertiesContainer.getHydrophobicPlip().getCloseness()) + "," + StandardFormat.format(residueTopologicPropertiesContainer.getHydrophobicPlip().getClusteringCoefficient()) + "," + conventionalProteinGraph.getContactsOf(aminoAcid).size() + "," + conventionalProteinGraph.getLocalContactsOf(aminoAcid).size() + "," + conventionalProteinGraph.getNonLocalContactsOf(aminoAcid).size() + "," + StandardFormat.format(residueTopologicPropertiesContainer.getConventional().getBetweenness()) + "," + StandardFormat.format(residueTopologicPropertiesContainer.getConventional().getCloseness()) + "," + StandardFormat.format(residueTopologicPropertiesContainer.getConventional().getClusteringCoefficient()) + "," + StandardFormat.format(residueTopologicPropertiesContainer.getFullPlip().getDistinctNeighborhoodCount()) + "," + StandardFormat.format(residueTopologicPropertiesContainer.getConventional().getDistinctNeighborhoodCount()) + "," + StandardFormat.format(residueStructuralInformationEntry.getAverageRmsdIncrease()) + "," + StandardFormat.format(residueStructuralInformationEntry.getAverageTmScoreIncrease()) + "," + StandardFormat.format(residueStructuralInformationEntry.getAverageQIncrease()) + "," + StandardFormat.format(residueStructuralInformationEntry.getMaximumRmsdIncrease()) + "," + StandardFormat.format(residueStructuralInformationEntry.getMaximumTmScoreIncrease()) + "," + StandardFormat.format(residueStructuralInformationEntry.getMaximumQIncrease()) + "," + StandardFormat.format(residueStructuralInformationEntry.getAverageRmsdIncreaseZScore()) + "," + StandardFormat.format(residueStructuralInformationEntry.getFractionOfTopScoringContacts()) + "," + (earlyFoldingResidues.contains(aminoAcid) ? "early" : "late") + "," + (residuesInEarlyFoldingSecondaryStructureElements.contains(aminoAcid) ? "true" : "false") + "," + functionalAnnotation + "," + (strongResidues.contains(aminoAcid) ? "strong" : "weak") + "," + (earlyFoldingResidues.size() > 0) + "," + (strongResidues.size() > 0) + "," + (functionalResidues.size() > 0) + "," + ecAnnotation;
}).collect(Collectors.joining(System.lineSeparator())));
} catch (Exception e) {
logger.info("calculation failed for {}\nby: {}", line, e.getMessage());
return Optional.empty();
}
}
use of de.bioforscher.jstructure.model.structure.aminoacid.AminoAcid in project jstructure by JonStargaryen.
the class A01_CreatePyMolRenderJobsForEarlyFoldingResidues method composePyMolCommand.
private static String composePyMolCommand(String line) {
String[] split = line.split(";");
String entryId = split[0];
String pdbId = split[1];
List<Integer> experimentIds = Pattern.compile(",").splitAsStream(split[2].replaceAll("\\[", "").replaceAll("]", "")).map(Integer::valueOf).collect(Collectors.toList());
Structure structure = StructureParser.fromPdbId(pdbId).parse();
Chain chain = structure.chains().findFirst().get();
Start2FoldXmlParser.parseSpecificExperiment(chain, Start2FoldConstants.XML_DIRECTORY.resolve(entryId + ".xml"), experimentIds);
List<Integer> earlyFoldingResidues = chain.aminoAcids().filter(aminoAcid -> aminoAcid.getFeature(Start2FoldResidueAnnotation.class).isEarly()).map(AminoAcid::getResidueIdentifier).map(ResidueIdentifier::getResidueNumber).collect(Collectors.toList());
return "delete all" + System.lineSeparator() + "fetch " + pdbId + ", async=0" + System.lineSeparator() + // hide non-relevant stuff
"hide everything" + System.lineSeparator() + "show cartoon, chain A" + System.lineSeparator() + // decolor everything
"color grey80" + System.lineSeparator() + "zoom (chain A)" + System.lineSeparator() + earlyFoldingResidues.stream().map(res -> "color efr, resi " + res).collect(Collectors.joining(System.lineSeparator())) + System.lineSeparator() + "ray" + System.lineSeparator() + "png " + Start2FoldConstants.PYMOL_DIRECTORY.resolve(entryId + "-efr.png") + System.lineSeparator();
}
use of de.bioforscher.jstructure.model.structure.aminoacid.AminoAcid in project jstructure by JonStargaryen.
the class StructuralInformationService method process.
public void process(Chain referenceChain, String jobName, Path confoldPath, Path tmalignPath, Path outputDirectory, int numberOfThreads, double baselineFrequency) {
try {
ExecutorService executorService = Executors.newFixedThreadPool(numberOfThreads);
List<AminoAcid> aminoAcids = referenceChain.aminoAcids().collect(Collectors.toList());
int numberOfAminoAcids = aminoAcids.size();
ReconstructionContactMap fullMap = ReconstructionContactMap.createReconstructionContactMap(referenceChain, ContactDefinitionFactory.createAlphaCarbonContactDefinition(8.0));
List<Pair<AminoAcid, AminoAcid>> contacts = fullMap.getLongRangeContacts();
int numberOfLongRangeContacts = contacts.size();
String sequence = fullMap.getSequence();
String secondaryStructure = fullMap.getSecondaryStructureElements();
// report general statistics
logger.info("evaluating structural information of chain with {} residues and {} long-range contacts", numberOfAminoAcids, numberOfLongRangeContacts);
logger.info("present long-range contacts:{}{}", System.lineSeparator(), composeConsoleOutput(fullMap.getLongRangeContacts()));
logger.info("coverage per position:{}{}", System.lineSeparator(), aminoAcids.stream().map(fullMap::getNonLocalContactsOf).mapToInt(List::size).mapToObj(size -> {
if (size < 10) {
return String.valueOf(size);
} else {
return "*";
}
}).collect(Collectors.joining()));
// write reference structure
Path referenceChainStructurePath = Files.createTempFile("confoldservice-ref", ".pdb");
Files.write(referenceChainStructurePath, referenceChain.getPdbRepresentation().getBytes());
// create outputDirectory
Path reconstructionDirectory = outputDirectory.resolve(jobName);
if (!Files.exists(reconstructionDirectory)) {
Files.createDirectory(reconstructionDirectory);
}
// create sampling containers
List<Future<BaselineReconstruction>> baselineFutures = new ArrayList<>();
for (int iteration = 0; iteration < COVERAGE; iteration++) {
baselineFutures.add(executorService.submit(new BaselineReconstruction(iteration, referenceChainStructurePath, referenceChain, fullMap, sequence, secondaryStructure, baselineFrequency, confoldPath.toFile().getAbsolutePath(), tmalignPath.toFile().getAbsolutePath(), outputDirectory, jobName)));
}
List<BaselineReconstruction> baselineReconstructions = baselineFutures.stream().map(this::getBaselineFuture).collect(Collectors.toList());
// create toggling reconstructions
int numberOfCombinations = baselineReconstructions.size() * contacts.size();
logger.info("reconstructing individual maps by contact toggling - evaluating {} combinations", numberOfCombinations);
int counter = 1;
List<Future<ContactTogglingReconstruction>> contactToggleFutures = new ArrayList<>();
for (Pair<AminoAcid, AminoAcid> contact : contacts) {
for (BaselineReconstruction baselineReconstruction : baselineReconstructions) {
contactToggleFutures.add(executorService.submit(baselineReconstruction.createContactTogglingReconstruction(contact, counter, numberOfCombinations)));
counter++;
}
}
Path outputPath = outputDirectory.resolve(jobName + ".out");
FileWriter outputWriter = new FileWriter(outputPath.toFile());
contactToggleFutures.stream().map(this::getContactToggleFuture).filter(Optional::isPresent).map(Optional::get).map(contactTogglingReconstruction -> contactTogglingReconstruction.getContactToToggle() + "\t" + contactTogglingReconstruction.isContactWasRemoved() + "\t" + StandardFormat.format(contactTogglingReconstruction.getBaselineReconstruction().getAverageRmsd()) + "\t" + StandardFormat.format(contactTogglingReconstruction.getBaselineReconstruction().getAverageTmScore()) + "\t" + StandardFormat.format(contactTogglingReconstruction.getBaselineReconstruction().getAverageQ()) + "\t" + StandardFormat.format(contactTogglingReconstruction.getAverageRmsd()) + "\t" + StandardFormat.format(contactTogglingReconstruction.getAverageTmScore()) + "\t" + StandardFormat.format(contactTogglingReconstruction.getAverageQ()) + "\t" + StandardFormat.format(contactTogglingReconstruction.getDecreaseRmsd()) + "\t" + StandardFormat.format(contactTogglingReconstruction.getIncreaseTMScore()) + "\t" + StandardFormat.format(contactTogglingReconstruction.getIncreaseQ()) + System.lineSeparator()).forEach(line -> {
try {
outputWriter.write(line);
outputWriter.flush();
} catch (IOException e) {
throw new UncheckedIOException(e);
}
});
// clean up
outputWriter.close();
Files.delete(referenceChainStructurePath);
} catch (IOException e) {
throw new UncheckedIOException(e);
}
}
use of de.bioforscher.jstructure.model.structure.aminoacid.AminoAcid in project jstructure by JonStargaryen.
the class A02_WriteHeatmapFiles method handleChain.
private static void handleChain(ExplorerChain explorerChain) {
try {
String entryId = explorerChain.getStfId();
System.out.println(entryId);
Chain chain = explorerChain.getChain();
List<ContactStructuralInformation> contactStructuralInformation = explorerChain.getContacts();
StringJoiner stringJoiner = new StringJoiner(System.lineSeparator(), "res1,res2,avg" + System.lineSeparator(), "");
List<AminoAcid> aminoAcids = chain.aminoAcids().collect(Collectors.toList());
SetOperations.cartesianProductOf(aminoAcids, aminoAcids).forEach(pair -> {
int residueIdentifier1 = pair.getLeft().getResidueIdentifier().getResidueNumber();
int residueIdentifier2 = pair.getRight().getResidueIdentifier().getResidueNumber();
Optional<ContactStructuralInformation> information = contactStructuralInformation.stream().filter(contact -> (contact.getResidueIdentifier1() == residueIdentifier1 && contact.getResidueIdentifier2() == residueIdentifier2) || (contact.getResidueIdentifier1() == residueIdentifier2 && contact.getResidueIdentifier2() == residueIdentifier1)).findFirst();
if (information.isPresent()) {
stringJoiner.add(residueIdentifier1 + "," + residueIdentifier2 + "," + information.get().getAverageRmsdIncrease());
} else {
stringJoiner.add(residueIdentifier1 + "," + residueIdentifier2 + "," + "0.0");
}
});
Files.write(Start2FoldConstants.DATA_DIRECTORY.resolve("si").resolve("heatmaps").resolve(entryId + ".csv"), stringJoiner.toString().getBytes());
} catch (Exception e) {
e.printStackTrace();
}
}
Aggregations