Skip to content

TASK-7549 - Include new annotation data: ACMG and variant context #728

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 14 commits into
base: release-6.x.x
Choose a base branch
from
+204 −46
Open

TASK-7549 - Include new annotation data: ACMG and variant context #728

Show file tree
Hide file tree
Changes from 13 commits
Commits
Show all changes
14 commits
Select commit Hold shift + click to select a range
f7ecf88
lib: add ACMG annotation, #TASK-7626, #TASK-7549
jtarraga Apr 24, 2025
809ba1f
lib: include genomic sequence context for INDELs, #TASK-7627, #TASK-7549
jtarraga Apr 25, 2025
d0c8e80
lib: fix checkstyle, #TASK-7549
jtarraga May 29, 2025
c9bf7f4
Merge branch 'release-6.x.x' into TASK-7549
ifiancu Jun 26, 2025
0e7adfd
Merge branch 'release-6.x.x' into TASK-7549
juanfeSanahuja Jun 27, 2025
ad2788c
Added org param in docker build #TASK-7549
juanfeSanahuja Jun 27, 2025
7bb887d
Merge branch 'release-6.x.x' into TASK-7549
juanfeSanahuja Jun 27, 2025
ee9470b
pom: upgrade biodata and java-commons-lib versions, #TASK-7549
jtarraga Jul 11, 2025
8876b74
Merge branch 'release-6.x.x' into TASK-7549
jtarraga Jul 11, 2025
1931420
Merge branch 'TASK-7549' of https://github.com/opencb/cellbase into T…
jtarraga Jul 11, 2025
1777480
lib: fix the position 'end' for the genomic sequence context, #TASK-7…
jtarraga Sep 10, 2025
fa77559
Merge branch 'release-6.x.x' into TASK-7549
jtarraga Sep 10, 2025
cf07116
lib: check genomic context ranges, and minor improvements, #TASK-7627…
jtarraga Sep 10, 2025
19c5f33
lib: add the include value 'genomicContext', #TASK-7627, #TASK-7549
jtarraga Sep 11, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
112 changes: 82 additions & 30 deletions ...src/main/java/org/opencb/cellbase/lib/variant/annotation/VariantAnnotationCalculator.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,13 +18,15 @@

import org.apache.commons.collections4.CollectionUtils;
import org.apache.commons.lang3.StringUtils;
import org.opencb.biodata.models.clinical.ClinicalAcmg;
import org.opencb.biodata.models.clinical.interpretation.VariantClassification;
import org.opencb.biodata.models.core.*;
import org.opencb.biodata.models.pharma.PharmaChemical;
import org.opencb.biodata.models.variant.Variant;
import org.opencb.biodata.models.variant.VariantBuilder;
import org.opencb.biodata.models.variant.annotation.ConsequenceTypeMappings;
import org.opencb.biodata.models.variant.avro.GeneCancerAssociation;
import org.opencb.biodata.models.variant.avro.*;
import org.opencb.biodata.models.variant.avro.GeneCancerAssociation;
import org.opencb.biodata.tools.variant.VariantNormalizer;
import org.opencb.biodata.tools.variant.exceptions.VariantNormalizerException;
import org.opencb.cellbase.core.ParamConstants;
Expand All @@ -39,6 +41,7 @@
import org.opencb.cellbase.lib.EtlCommons;
import org.opencb.cellbase.lib.managers.*;
import org.opencb.cellbase.lib.variant.VariantAnnotationUtils;
import org.opencb.cellbase.lib.variant.annotation.futures.FutureGenomicSequenceContextAnnotator;
import org.opencb.cellbase.lib.variant.annotation.futures.FuturePharmacogenomicsAnnotator;
import org.opencb.cellbase.lib.variant.annotation.futures.FutureSnpAnnotator;
import org.opencb.cellbase.lib.variant.annotation.futures.FutureSpliceScoreAnnotator;
Expand Down Expand Up @@ -68,6 +71,29 @@ public class VariantAnnotationCalculator {

private static final String EMPTY_STRING = "";
private static final String ALTERNATE = "1";

// Include values
public static final String EXPRESSION_INCLUDE = "expression";
public static final String GENE_DISEASE_INCLUDE = "geneDisease";
public static final String DRUG_INTERACTION_INCLUDE = "drugInteraction";
public static final String GENE_CONSTRAINTS_INCLUDE = "geneConstraints";
public static final String MIRNA_TARGETS_INCLUDE = "mirnaTargets";
public static final String CANCER_GENE_ASSOCIATION_INCLUDE = "cancerGeneAssociation";
public static final String CANCER_HOTSPOTS_INCLUDE = "cancerHotspots";
public static final String VARIATION_INCLUDE = "variation";
public static final String POPULATION_FREQUENCIES_INCLUDE = "populationFrequencies";
public static final String XREFS_INCLUDE = "xrefs";
public static final String CONSERVATION_INCLUDE = "conservation";
public static final String FUNCTIONAL_SCORE_INCLUDE = "functionalScore";
@Deprecated
public static final String CLINICAL_INCLUDE = "clinical";
public static final String TRAIT_ASSOCIATION_INCLUDE = "traitAssociation";
public static final String REPEATS_INCLUDE = "repeats";
public static final String CYTOBAND_INCLUDE = "cytoband";
public static final String CONSEQUENCE_TYPE_INCLUDE = "consequenceType";
public static final String PHARMACOGENOMICS_INCLUDE = "pharmacogenomics";
public static final String HGVS_INCLUDE = "hgvs";

private GenomeManager genomeManager;
private GeneManager geneManager;
private RegulatoryManager regulationManager;
Expand Down Expand Up @@ -270,7 +296,7 @@ private List<Gene> setGeneAnnotation(List<Gene> geneList, Variant variant)
VariantAnnotation variantAnnotation = variant.getAnnotation();

// TODO Remove expression data since is deprecated
if (annotatorSet.contains("expression")) {
if (annotatorSet.contains(EXPRESSION_INCLUDE)) {
variantAnnotation.setGeneExpression(new ArrayList<>());
for (Gene gene : geneList) {
// refseq genes don't have annotation (yet)
Expand All @@ -280,7 +306,7 @@ private List<Gene> setGeneAnnotation(List<Gene> geneList, Variant variant)
}
}

if (annotatorSet.contains("geneDisease")) {
if (annotatorSet.contains(GENE_DISEASE_INCLUDE)) {
variantAnnotation.setGeneTraitAssociation(new ArrayList<>());
Set<String> visited = new HashSet<>();
for (Gene gene : geneList) {
Expand All @@ -294,7 +320,7 @@ private List<Gene> setGeneAnnotation(List<Gene> geneList, Variant variant)
}
}

if (annotatorSet.contains("drugInteraction")) {
if (annotatorSet.contains(DRUG_INTERACTION_INCLUDE)) {
variantAnnotation.setGeneDrugInteraction(new ArrayList<>());
for (Gene gene : geneList) {
if (gene.getAnnotation() != null && gene.getAnnotation().getDrugs() != null) {
Expand All @@ -303,7 +329,7 @@ private List<Gene> setGeneAnnotation(List<Gene> geneList, Variant variant)
}
}

if (annotatorSet.contains("geneConstraints")) {
if (annotatorSet.contains(GENE_CONSTRAINTS_INCLUDE)) {
variantAnnotation.setGeneConstraints(new ArrayList<>());
for (Gene gene : geneList) {
if (gene.getAnnotation() != null && gene.getAnnotation().getConstraints() != null) {
Expand All @@ -312,7 +338,7 @@ private List<Gene> setGeneAnnotation(List<Gene> geneList, Variant variant)
}
}

if (annotatorSet.contains("mirnaTargets")) {
if (annotatorSet.contains(MIRNA_TARGETS_INCLUDE)) {
variantAnnotation.setGeneMirnaTargets(new ArrayList<>());
for (Gene gene : geneList) {
if (gene.getMirna() != null && gene.getMirna().getMatures() != null) {
Expand All @@ -321,7 +347,7 @@ private List<Gene> setGeneAnnotation(List<Gene> geneList, Variant variant)
}
}

if (annotatorSet.contains("cancerGeneAssociation")) {
if (annotatorSet.contains(CANCER_GENE_ASSOCIATION_INCLUDE)) {
variantAnnotation.setGeneCancerAssociations(new ArrayList<>());
Set<String> visited = new HashSet<>();
for (Gene gene : geneList) {
Expand Down Expand Up @@ -374,7 +400,7 @@ private List<Gene> setGeneAnnotation(List<Gene> geneList, Variant variant)
}
}

if (annotatorSet.contains("cancerHotspots")) {
if (annotatorSet.contains(CANCER_HOTSPOTS_INCLUDE)) {
variantAnnotation.setCancerHotspots(new ArrayList<>());
Set<String> visited = new HashSet<>();
for (Gene gene : geneList) {
Expand Down Expand Up @@ -460,7 +486,7 @@ private List<VariantAnnotation> runAnnotationProcess(List<Variant> normalizedVar
Future<List<CellBaseDataResult<Variant>>> variationFuture = null;
List<Gene> batchGeneList = getBatchGeneList(normalizedVariantList);

if (annotatorSet.contains("variation") || annotatorSet.contains("populationFrequencies")) {
if (annotatorSet.contains(VARIATION_INCLUDE) || annotatorSet.contains(POPULATION_FREQUENCIES_INCLUDE)) {
futureVariationAnnotator = new FutureVariationAnnotator(normalizedVariantList, new QueryOptions("include",
"id,annotation.populationFrequencies,annotation.additionalAttributes.dgvSpecificAttributes")
.append("imprecise", imprecise), dataRelease.getRelease());
Expand All @@ -469,22 +495,22 @@ private List<VariantAnnotation> runAnnotationProcess(List<Variant> normalizedVar

FutureSnpAnnotator futureSnpAnnotator = null;
Future<List<CellBaseDataResult<Snp>>> snpFuture = null;
if (annotatorSet.contains("xrefs") && dataRelease.getCollections().containsKey(EtlCommons.SNP_COLLECTION_NAME)) {
if (annotatorSet.contains(XREFS_INCLUDE) && dataRelease.getCollections().containsKey(EtlCommons.SNP_COLLECTION_NAME)) {
futureSnpAnnotator = new FutureSnpAnnotator(normalizedVariantList, dataRelease.getRelease(), variantManager, logger);
snpFuture = CACHED_THREAD_POOL.submit(futureSnpAnnotator);
}

FutureConservationAnnotator futureConservationAnnotator = null;
Future<List<CellBaseDataResult<Score>>> conservationFuture = null;
if (annotatorSet.contains("conservation")) {
if (annotatorSet.contains(CONSERVATION_INCLUDE)) {
futureConservationAnnotator = new FutureConservationAnnotator(normalizedVariantList, QueryOptions.empty(),
dataRelease.getRelease());
conservationFuture = CACHED_THREAD_POOL.submit(futureConservationAnnotator);
}

FutureVariantFunctionalScoreAnnotator futureVariantFunctionalScoreAnnotator = null;
Future<List<CellBaseDataResult<Score>>> variantFunctionalScoreFuture = null;
if (annotatorSet.contains("functionalScore")) {
if (annotatorSet.contains(FUNCTIONAL_SCORE_INCLUDE)) {
futureVariantFunctionalScoreAnnotator = new FutureVariantFunctionalScoreAnnotator(normalizedVariantList, QueryOptions.empty(),
dataRelease.getRelease());
variantFunctionalScoreFuture = CACHED_THREAD_POOL.submit(futureVariantFunctionalScoreAnnotator);
Expand All @@ -493,7 +519,7 @@ private List<VariantAnnotation> runAnnotationProcess(List<Variant> normalizedVar
FutureClinicalAnnotator futureClinicalAnnotator = null;
Future<List<CellBaseDataResult<Variant>>> clinicalFuture = null;
// FIXME "clinical" is deprecated, replaced with traitAssociation
if (annotatorSet.contains("clinical") || annotatorSet.contains("traitAssociation")) {
if (annotatorSet.contains(CLINICAL_INCLUDE) || annotatorSet.contains(TRAIT_ASSOCIATION_INCLUDE)) {
QueryOptions queryOptions = new QueryOptions();
queryOptions.add(ParamConstants.QueryParams.PHASE.key(), phased);
queryOptions.add(ParamConstants.QueryParams.CHECK_AMINO_ACID_CHANGE.key(), checkAminoAcidChange);
Expand All @@ -504,34 +530,38 @@ private List<VariantAnnotation> runAnnotationProcess(List<Variant> normalizedVar

FutureRepeatsAnnotator futureRepeatsAnnotator = null;
Future<List<CellBaseDataResult<Repeat>>> repeatsFuture = null;
if (annotatorSet.contains("repeats")) {
if (annotatorSet.contains(REPEATS_INCLUDE)) {
futureRepeatsAnnotator = new FutureRepeatsAnnotator(normalizedVariantList, dataRelease.getRelease());
repeatsFuture = CACHED_THREAD_POOL.submit(futureRepeatsAnnotator);
}

FutureCytobandAnnotator futureCytobandAnnotator = null;
Future<List<CellBaseDataResult<Cytoband>>> cytobandFuture = null;
if (annotatorSet.contains("cytoband")) {
if (annotatorSet.contains(CYTOBAND_INCLUDE)) {
futureCytobandAnnotator = new FutureCytobandAnnotator(normalizedVariantList, QueryOptions.empty(), dataRelease.getRelease());
cytobandFuture = CACHED_THREAD_POOL.submit(futureCytobandAnnotator);
}

FutureSpliceScoreAnnotator futureSpliceScoreAnnotator = null;
Future<List<CellBaseDataResult<SpliceScore>>> spliceScoreFuture = null;
if (annotatorSet.contains("consequenceType")) {
if (annotatorSet.contains(CONSEQUENCE_TYPE_INCLUDE)) {
futureSpliceScoreAnnotator = new FutureSpliceScoreAnnotator(normalizedVariantList, dataRelease.getRelease(), apiKey,
variantManager, logger);
spliceScoreFuture = CACHED_THREAD_POOL.submit(futureSpliceScoreAnnotator);
}

FuturePharmacogenomicsAnnotator futurePharmacogenomicsAnnotator = null;
Future<List<CellBaseDataResult<PharmaChemical>>> pharmacogenomicsFuture = null;
if (annotatorSet.contains("pharmacogenomics") && dataRelease.getCollections().containsKey(EtlCommons.PHARMACOGENOMICS_DATA)) {
if (annotatorSet.contains(PHARMACOGENOMICS_INCLUDE) && dataRelease.getCollections().containsKey(EtlCommons.PHARMACOGENOMICS_DATA)) {
futurePharmacogenomicsAnnotator = new FuturePharmacogenomicsAnnotator(normalizedVariantList, QueryOptions.empty(),
dataRelease.getRelease(), pharmacogenomicsManager, logger);
pharmacogenomicsFuture = CACHED_THREAD_POOL.submit(futurePharmacogenomicsAnnotator);
}

FutureGenomicSequenceContextAnnotator contextAnnotator = new FutureGenomicSequenceContextAnnotator(normalizedVariantList,
dataRelease.getRelease(), genomeManager);
Future<List<GenomicSequenceContext>> contextFuture = CACHED_THREAD_POOL.submit(contextAnnotator);

// We iterate over all variants to get the rest of the annotations and to create the VariantAnnotation objects
Queue<Variant> variantBuffer = new LinkedList<>();
long startTime = System.currentTimeMillis();
Expand Down Expand Up @@ -566,7 +596,7 @@ private List<VariantAnnotation> runAnnotationProcess(List<Variant> normalizedVar
// FOR INDELS
// Given that the number of indels is expected to be negligible if compared to the number of SNVs, the
// decision is to run it synchronously
if (annotatorSet.contains("hgvs")) {
if (annotatorSet.contains(HGVS_INCLUDE)) {
try {
// Decided to always set normalize = false for a number of reasons:
// * was raising problems with the normalizer - it could potentially fail in weird multiallelic
Expand All @@ -590,7 +620,7 @@ private List<VariantAnnotation> runAnnotationProcess(List<Variant> normalizedVar
}
}

if (annotatorSet.contains("consequenceType")) {
if (annotatorSet.contains(CONSEQUENCE_TYPE_INCLUDE)) {
try {
List<ConsequenceType> consequenceTypeList = getConsequenceTypeList(variant, affectedGenes, true, QueryOptions.empty(),
dataRelease.getRelease());
Expand Down Expand Up @@ -676,15 +706,35 @@ private List<VariantAnnotation> runAnnotationProcess(List<Variant> normalizedVar
if (futurePharmacogenomicsAnnotator != null) {
futurePharmacogenomicsAnnotator.processResults(pharmacogenomicsFuture, variantAnnotationList);
}
contextAnnotator.processResults(contextFuture, variantAnnotationList);

// Not needed with newCachedThreadPool
// fixedThreadPool.shutdown();

// ACMG, only if consequence type is required
if (annotatorSet.contains(CONSEQUENCE_TYPE_INCLUDE)) {
setAcmdPredictions(variantAnnotationList);
}

logger.debug("Total batch annotation performance is {}ms for {} variants", System.currentTimeMillis()
- globalStartTime, normalizedVariantList.size());
return variantAnnotationList;
}

private static void setAcmdPredictions(List<VariantAnnotation> variantAnnotationList) {
for (VariantAnnotation variantAnnotation : variantAnnotationList) {
if (variantAnnotation != null && CollectionUtils.isNotEmpty(variantAnnotation.getConsequenceTypes())) {
for (ConsequenceType consequenceType : variantAnnotation.getConsequenceTypes()) {
List<ClinicalAcmg> acmgs = VariantClassification.calculateAcmgClassification(consequenceType, variantAnnotation,
null);
if (CollectionUtils.isNotEmpty(acmgs)) {
consequenceType.setAcmg(acmgs.stream().map(ClinicalAcmg::getClassification).collect(Collectors.toList()));
}
}
}
}
}

public List<Gene> getBatchGeneList(List<Variant> variantList)
throws QueryException, IllegalAccessException, CellBaseException {
List<Region> regionList = variantListToRegionList(variantList);
Expand Down Expand Up @@ -1181,9 +1231,11 @@ private Set<String> getAnnotatorSet(QueryOptions queryOptions) {
annotatorSet = new HashSet<>(includeList);
} else {
// 'expression' removed in CB 5.0
annotatorSet = new HashSet<>(Arrays.asList("variation", "traitAssociation", "conservation", "functionalScore",
"consequenceType", "geneDisease", "drugInteraction", "geneConstraints", "mirnaTargets", "pharmacogenomics",
"cancerGeneAssociation", "cancerHotspots", "populationFrequencies", "repeats", "cytoband", "hgvs", "xrefs"));
annotatorSet = new HashSet<>(Arrays.asList(VARIATION_INCLUDE, TRAIT_ASSOCIATION_INCLUDE, CONSERVATION_INCLUDE,
FUNCTIONAL_SCORE_INCLUDE, CONSEQUENCE_TYPE_INCLUDE, GENE_DISEASE_INCLUDE, DRUG_INTERACTION_INCLUDE,
GENE_CONSTRAINTS_INCLUDE, MIRNA_TARGETS_INCLUDE, PHARMACOGENOMICS_INCLUDE, CANCER_GENE_ASSOCIATION_INCLUDE,
CANCER_HOTSPOTS_INCLUDE, POPULATION_FREQUENCIES_INCLUDE, REPEATS_INCLUDE, CYTOBAND_INCLUDE, HGVS_INCLUDE,
XREFS_INCLUDE));
List<String> excludeList = queryOptions.getAsStringList("exclude");
excludeList.forEach(annotatorSet::remove);
}
Expand All @@ -1199,25 +1251,25 @@ private List<String> getIncludedGeneFields(Set<String> annotatorSet) {
"transcripts.exons.cdsEnd", "transcripts.exons.sequence", "transcripts.exons.phase",
"transcripts.exons.exonNumber", "mirna", "transcripts.exons.genomicCodingStart", "transcripts.exons.genomicCodingEnd"));

if (annotatorSet.contains("expression")) {
if (annotatorSet.contains(EXPRESSION_INCLUDE)) {
includeGeneFields.add("annotation.expression");
}
if (annotatorSet.contains("geneDisease")) {
if (annotatorSet.contains(GENE_DISEASE_INCLUDE)) {
includeGeneFields.add("annotation.diseases");
}
if (annotatorSet.contains("drugInteraction")) {
if (annotatorSet.contains(DRUG_INTERACTION_INCLUDE)) {
includeGeneFields.add("annotation.drugs");
}
if (annotatorSet.contains("geneConstraints")) {
if (annotatorSet.contains(GENE_CONSTRAINTS_INCLUDE)) {
includeGeneFields.add("annotation.constraints");
}
if (annotatorSet.contains("mirnaTargets")) {
if (annotatorSet.contains(MIRNA_TARGETS_INCLUDE)) {
includeGeneFields.add("annotation.targets");
}
if (annotatorSet.contains("cancerGeneAssociation")) {
if (annotatorSet.contains(CANCER_GENE_ASSOCIATION_INCLUDE)) {
includeGeneFields.add("annotation.cancerAssociations");
}
if (annotatorSet.contains("cancerHotspots")) {
if (annotatorSet.contains(CANCER_HOTSPOTS_INCLUDE)) {
includeGeneFields.add("annotation.cancerHotspots");
}
return includeGeneFields;
Expand Down Expand Up @@ -1596,7 +1648,7 @@ public void processResults(Future<List<CellBaseDataResult<Variant>>> variationFu
}
}

if (annotatorSet.contains("populationFrequencies") && preferredVariant != null) {
if (annotatorSet.contains(POPULATION_FREQUENCIES_INCLUDE) && preferredVariant != null) {
variantAnnotationList.get(i)
.setPopulationFrequencies(preferredVariant.getAnnotation().getPopulationFrequencies());
}
Expand Down
Loading
Loading