Examples with CvTerm org.nextprot.api.core.domain.CvTerm used on opensource projects

Example 26 with CvTerm

use of org.nextprot.api.core.domain.CvTerm in project nextprot-api by calipho-sib.

the class StatementAnnotationBuilder method buildAnnotationList.

public List<T> buildAnnotationList(String isoformName, List<Statement> flatStatements) {
    List<T> annotations = new ArrayList<>();
    Map<String, List<Statement>> flatStatementsByAnnotationHash = flatStatements.stream().collect(Collectors.groupingBy(rs -> rs.getValue(StatementField.ANNOTATION_ID)));
    flatStatementsByAnnotationHash.forEach((key, statements) -> {
        T annotation = get();
        Statement firstStatement = statements.get(0);
        annotation.setAnnotationHash(firstStatement.getValue(StatementField.ANNOTATION_ID));
        // annotation.setAnnotationName(firstStatement.getValue(StatementField.ANNOTATION_NAME));
        AnnotationCategory category = AnnotationCategory.getDecamelizedAnnotationTypeName(StringUtils.camelToKebabCase(firstStatement.getValue(StatementField.ANNOTATION_CATEGORY)));
        annotation.setAnnotationCategory(category);
        if (category.equals(AnnotationCategory.VARIANT) || category.equals(AnnotationCategory.MUTAGENESIS)) {
            setVariantAttributes(annotation, firstStatement);
        }
        setIsoformTargeting(annotation, firstStatement);
        setIsoformName(annotation, isoformName);
        annotation.setDescription(firstStatement.getValue(StatementField.ANNOT_DESCRIPTION));
        String cvTermAccession = firstStatement.getValue(StatementField.ANNOT_CV_TERM_ACCESSION);
        // Set the evidences if not Mammalian phenotype or Protein Property https://issues.isb-sib.ch/browse/BIOEDITOR-466
        if (!ANNOT_CATEGORIES_WITHOUT_EVIDENCES.contains(category)) {
            annotation.setEvidences(buildAnnotationEvidences(statements));
            // TODO Remove this when you are able to do XREFs
            if (((annotation.getEvidences() == null) || ((annotation.getEvidences().isEmpty()))) && (category.equals(AnnotationCategory.VARIANT) || category.equals(AnnotationCategory.MUTAGENESIS))) {
                // All variants from BED are GOLD, and this is a special case when we don't have evidences for VDs.
                annotation.setQualityQualifier("GOLD");
            } else {
                annotation.setQualityQualifier(AnnotationUtils.computeAnnotationQualityBasedOnEvidences(annotation.getEvidences()).name());
            }
        } else {
            // Case of Protein propert and mammalian phenotypes
            annotation.setEvidences(new ArrayList<AnnotationEvidence>());
            boolean foundGold = statements.stream().anyMatch(s -> s.getValue(StatementField.EVIDENCE_QUALITY).equalsIgnoreCase("GOLD"));
            if (foundGold) {
                annotation.setQualityQualifier("GOLD");
            } else {
                annotation.setQualityQualifier("SILVER");
            }
        }
        if (cvTermAccession != null && !cvTermAccession.isEmpty()) {
            annotation.setCvTermAccessionCode(cvTermAccession);
            CvTerm cvTerm = terminologyService.findCvTermByAccession(cvTermAccession);
            if (cvTerm != null) {
                annotation.setCvTermName(cvTerm.getName());
                annotation.setCvApiName(cvTerm.getOntology());
                annotation.setCvTermDescription(cvTerm.getDescription());
                if (category.equals(AnnotationCategory.PROTEIN_PROPERTY)) {
                    // according to https://issues.isb-sib.ch/browse/BIOEDITOR-466
                    annotation.setDescription(cvTerm.getDescription());
                } else if (category.equals(AnnotationCategory.MAMMALIAN_PHENOTYPE)) {
                    annotation.setDescription("Relative to modification-effect annotations");
                }
            } else {
                LOGGER.error("cv term was expected to be found " + cvTermAccession);
                annotation.setCvTermName(firstStatement.getValue(StatementField.ANNOT_CV_TERM_NAME));
                annotation.setCvApiName(firstStatement.getValue(StatementField.ANNOT_CV_TERM_TERMINOLOGY));
            }
        }
        annotation.setAnnotationHash(firstStatement.getValue(StatementField.ANNOTATION_ID));
        annotation.setAnnotationName(firstStatement.getValue(StatementField.ANNOTATION_NAME));
        // Check this with PAM (does it need to be a human readable stuff)
        // Does it need a name?
        annotation.setUniqueName(firstStatement.getValue(StatementField.ANNOTATION_ID));
        String bioObjectAnnotationHash = firstStatement.getValue(StatementField.OBJECT_ANNOTATION_IDS);
        String bioObjectAccession = firstStatement.getValue(StatementField.BIOLOGICAL_OBJECT_ACCESSION);
        String bot = firstStatement.getValue(StatementField.BIOLOGICAL_OBJECT_TYPE);
        if ((bioObjectAnnotationHash != null) && (bioObjectAnnotationHash.length() > 0) || (bioObjectAccession != null && (bioObjectAccession.length() > 0))) {
            BioObject bioObject;
            if (AnnotationCategory.BINARY_INTERACTION.equals(annotation.getAPICategory())) {
                if (bioObjectAccession.startsWith("NX_") && BioType.PROTEIN.name().equalsIgnoreCase(bot)) {
                    // note that if we handle BioType.PROTEIN_ISOFORM in the future, we should
                    // add the property isoformName as well, see how it's done in BinaryInteraction2Annotation.newBioObject()
                    bioObject = BioObject.internal(BioType.PROTEIN);
                    // // TODO: REMOVE THIS HACK WHEN ISSUE https://issues.isb-sib.ch/browse/NEXTPROT-1513 will be fixed
                    // // NX_P62158 was split in 3 accessions: NX_P0DP23/CALM1, NX_P0DP24/CALM2 and NX_P0DP25/CALM3
                    // // BEGIN DIRTY HACK
                    /*
                        if (bioObjectAccession.equals("NX_P62158")) {
                            switch (isoformName) {
                                case "NX_P35499":
                                    bioObjectAccession = "NX_P0DP23";
                                    break;
                                case "NX_Q99250":
                                    bioObjectAccession = "NX_P0DP23";
                                    break;
                                case "NX_Q9UQD0":
                                    bioObjectAccession = "NX_P0DP23";
                                    break;
                                case "NX_Q9Y5Y9":
                                    bioObjectAccession = "NX_P0DP23";
                                    break;
                            }
                        }
                        */
                    // /// END OF HACK
                    bioObject.setAccession(bioObjectAccession);
                    bioObject.putPropertyNameValue("geneName", firstStatement.getValue(StatementField.BIOLOGICAL_OBJECT_NAME));
                    String proteinName = mainNamesService.findIsoformOrEntryMainName(bioObjectAccession).orElseThrow(() -> new NextProtException("Cannot create a binary interaction with " + isoformName + ": unknown protein accession " + bioObject.getAccession())).getName();
                    bioObject.putPropertyNameValue("proteinName", proteinName);
                    bioObject.putPropertyNameValue("url", "https://www.nextprot.org/entry/" + bioObjectAccession + "/interactions");
                } else {
                    throw new NextProtException("Binary Interaction only expects to be a nextprot entry NX_ and found " + bioObjectAccession + " with type " + bot);
                }
            } else if (AnnotationCategory.PHENOTYPIC_VARIATION.equals(annotation.getAPICategory())) {
                bioObject = BioObject.internal(BioType.ENTRY_ANNOTATION);
                bioObject.setAnnotationHash(bioObjectAnnotationHash);
            } else {
                throw new NextProtException("Category not expected for bioobject " + annotation.getAPICategory());
            }
            annotation.setBioObject(bioObject);
        }
        annotations.add(annotation);
    });
    return annotations;
}

Example 27 with CvTerm

use of org.nextprot.api.core.domain.CvTerm in project nextprot-api by calipho-sib.

the class TerminologyServiceImpl method getOnePathToRootTerm.

@Override
public List<CvTerm> getOnePathToRootTerm(String cvTermAccession) {
    List<CvTerm> path = new ArrayList<>();
    String ac = cvTermAccession;
    while (true) {
        CvTerm t = findCvTermByAccession(ac);
        path.add(t);
        List<String> parents = t.getAncestorAccession();
        if (parents == null || parents.size() == 0)
            break;
        ac = parents.get(0);
    }
    return path;
}

Example 28 with CvTerm

use of org.nextprot.api.core.domain.CvTerm in project nextprot-api by calipho-sib.

the class ExperimentalContextDictionaryServiceImpl method updateTerminologies.

private void updateTerminologies(List<ExperimentalContext> ecs) {
    Set<String> terminologyAccessions = new HashSet<String>();
    for (ExperimentalContext ec : ecs) {
        terminologyAccessions.add(ec.getCellLineAC());
        terminologyAccessions.add(ec.getTissueAC());
        terminologyAccessions.add(ec.getOrganelleAC());
        terminologyAccessions.add(ec.getDetectionMethodAC());
        terminologyAccessions.add(ec.getDiseaseAC());
        terminologyAccessions.add(ec.getDevelopmentalStageAC());
    }
    if (terminologyAccessions.size() > 0) {
        List<CvTerm> terms = terminologyService.findCvTermsByAccessions(terminologyAccessions);
        Map<String, CvTerm> map = new HashMap<>();
        for (CvTerm term : terms) {
            map.put(term.getAccession(), term);
        }
        for (ExperimentalContext ec : ecs) {
            updateTerminologies(ec, map);
        }
    }
}

Example 29 with CvTerm

use of org.nextprot.api.core.domain.CvTerm in project nextprot-api by calipho-sib.

the class OntologyDAGAnalyserTask method benchmarkingGetAncestorsMethods.

private List<Long> benchmarkingGetAncestorsMethods(TerminologyCv terminologyCv, TerminologyService terminologyService) {
    List<Long> timings = new ArrayList<>();
    CvTermGraph graph = cvTermGraphService.findCvTermGraph(terminologyCv);
    Map<Long, List<String>> ancestors = new HashMap<>();
    Map<Long, List<String>> ancestorsQuick = new HashMap<>();
    List<CvTerm> cvTerms = terminologyService.findCvTermsByOntology(terminologyCv.name());
    // COMPARE COMPUTATION DURATIONS
    Instant t = Instant.now();
    for (CvTerm cvTerm : cvTerms) {
        ancestors.put(cvTerm.getId(), terminologyService.getAllAncestorsAccession(cvTerm.getAccession()));
    }
    timings.add(ChronoUnit.MILLIS.between(t, Instant.now()));
    t = Instant.now();
    for (CvTerm cvTerm : cvTerms) {
        ancestorsQuick.put(cvTerm.getId(), Arrays.stream(graph.getAncestors(Math.toIntExact(cvTerm.getId()))).boxed().map(graph::getCvTermAccessionById).collect(Collectors.toList()));
    }
    timings.add(ChronoUnit.MILLIS.between(t, Instant.now()));
    // TEST CORRECTNESS
    Set<Long> ids = ancestors.keySet();
    for (long id : ids) {
        Set<String> ancestorsOld = new HashSet<>(ancestors.get(id));
        Set<String> ancestorsNew = new HashSet<>(ancestorsQuick.get(id));
        boolean equals = ancestorsOld.equals(ancestorsNew);
        if (!equals) {
            System.err.println("WARNING: INCONSISTENCY: found different ancestors for cv term " + graph.getCvTermAccessionById((int) id) + "\n\t: old=" + ancestors.get(id) + "\n" + "\t: new=" + ancestorsNew);
        }
    }
    return timings;
}

Example 30 with CvTerm

use of org.nextprot.api.core.domain.CvTerm in project nextprot-api by calipho-sib.

the class TerminologyDaoImpl method findAllTerminology.

@Override
public List<CvTerm> findAllTerminology() {
    SqlParameterSource params = new MapSqlParameterSource();
    List<CvTerm> terms = new NamedParameterJdbcTemplate(dsLocator.getDataSource()).query(sqlDictionary.getSQLQuery("terminology-all"), params, new DbTermRowMapper());
    return terms;
}