Skip to content

SCRUM-4937: Run all indexers in parallel and fix allele gene species display #1544

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

Merged
oblodgett merged 4 commits into from
Mar 31, 2026
Merged

SCRUM-4937: Run all indexers in parallel and fix allele gene species display #1544

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
01da822
fix: use species abbreviation for allele genes field
oblodgett Mar 30, 2026
4c1a5cf
Update indexer orders
oblodgett Mar 31, 2026
cc1a2d3
Update AlleleSearchResultConverter.java
oblodgett Mar 31, 2026
589ad30
Bump curation version
oblodgett Mar 31, 2026
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
39 changes: 20 additions & 19 deletions agr_indexer/src/main/java/org/alliancegenome/indexer/Main.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,18 +68,7 @@ public static void main(String[] args) {
log.info("Args[" + i + "]: " + args[i]);
}

ExecutorService parallelExecutor = Executors.newFixedThreadPool(10);
ExecutorService sequentialExecutor = Executors.newFixedThreadPool(1);

for (String type : parallelMap.keySet()) {
if (argumentSet.size() == 0 || argumentSet.contains(type)) {
log.info("Running Parallel for: " + type);
parallelExecutor.execute(indexers.get(type));
//indexers.get(type).start();
} else {
log.info("Not Starting: " + type);
}
}

for (String type : sequentialMap.keySet()) {
if (argumentSet.size() == 0 || argumentSet.contains(type)) {
Expand All @@ -90,29 +79,41 @@ public static void main(String[] args) {
log.info("Not Starting: " + type);
}
}

parallelExecutor.shutdown();
while (!parallelExecutor.isTerminated()) {
sequentialExecutor.shutdown();
while (!sequentialExecutor.isTerminated()) {
try {
Thread.sleep(1000);
} catch (InterruptedException e) {
ExceptionCatcher.report(e);
e.printStackTrace();
}
}
log.info("Finished Running Curation Indexers");
sequentialExecutor.shutdown();
while (!sequentialExecutor.isTerminated()) {
log.info("Finished Running Sequential Indexers");


ExecutorService parallelExecutor = Executors.newFixedThreadPool(10);

for (String type : parallelMap.keySet()) {
if (argumentSet.size() == 0 || argumentSet.contains(type)) {
log.info("Running Parallel for: " + type);
parallelExecutor.execute(indexers.get(type));
//indexers.get(type).start();
} else {
log.info("Not Starting: " + type);
}
}
parallelExecutor.shutdown();
while (!parallelExecutor.isTerminated()) {
try {
Thread.sleep(1000);
} catch (InterruptedException e) {
ExceptionCatcher.report(e);
e.printStackTrace();
}
}
log.info("Finished Running Neo4j Indexers");
log.info("Finished Running Parallel Indexers");

log.debug("Waiting for Indexers to finish");
log.debug("Waiting for ALL Indexers to finish");
for (Indexer i : indexers.values()) {
try {
if (i.isAlive()) {
Expand Down
6 changes: 3 additions & 3 deletions agr_indexer/src/main/java/org/alliancegenome/indexer/TestSpeciesOrder.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@ public static void main(String[] args) throws Exception {
String taxonCurie = species.getTaxon() != null ? species.getTaxon().getCurie() : "null";
Integer order = species.getPhylogeneticOrder();
String fullName = species.getFullName();
System.out.println(" " + fullName + " | taxon: " + taxonCurie + " | phylogeneticOrder: " + order);
System.out.println(fullName + " | taxon: " + taxonCurie + " | phylogeneticOrder: " + order);

if (species.getTaxon() != null && order != null) {
String taxonIdPart = taxonCurie.replace("NCBITaxon:", "");
Expand All @@ -41,15 +41,15 @@ public static void main(String[] args) throws Exception {
System.out.println("\n=== Species order lookup map ===");
speciesOrderLookup.entrySet().stream()
.sorted(Map.Entry.comparingByValue())
.forEach(e -> System.out.println(" " + e.getKey() + " -> " + e.getValue()));
.forEach(e -> System.out.println(e.getKey() + " -> " + e.getValue()));

// Test buildSpeciesOrder for a specific taxon (e.g. Xenopus laevis 8355)
String testTaxon = args.length > 0 ? args[0] : "NCBITaxon:8355";
System.out.println("\n=== buildSpeciesOrder for " + testTaxon + " ===");
HashMap<String, Integer> speciesOrder = buildSpeciesOrder(speciesOrderLookup, testTaxon);
speciesOrder.entrySet().stream()
.sorted(Map.Entry.comparingByValue())
.forEach(e -> System.out.println(" " + e.getKey() + " -> " + e.getValue()));
.forEach(e -> System.out.println(e.getKey() + " -> " + e.getValue()));

System.out.println("\nDone.");
}
Expand Down
20 changes: 10 additions & 10 deletions agr_indexer/src/main/java/org/alliancegenome/indexer/config/IndexerConfig.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,9 @@ public enum IndexerConfig {

// Curation Indexers

// Run Sequentially -- typically take a lot of RAM or do consolidation in memory
ReleaseInfoIndexer("release", ReleaseInfoIndexer.class, 1, 1, 1, 1, 1, false),

// Run Parallelly
ParalogyIndexer("paralogy", GeneToGeneParalogyIndexer.class, 4, 5000, 5000, 8, 1, true),
AffectedGenomicModelAnnotationIndexer("agmAnnotation", AGMAnnotationCurationIndexer.class, 4, 1500, 1500, 8, 1, true),
Expand All @@ -44,16 +47,13 @@ public enum IndexerConfig {
DiseaseSummaryIndexer("diseaseSummary", DiseaseSummaryCurationIndexer.class, 4, 1500, 1500, 4, 1, true),
TransgenicAlleleIndexer("transgenicAlleles", TransgenicAlleleCurationIndexer.class, 1, 3000, 1500, 8, 1, true),
GeneExpressionRibbonSummaryIndexer("geneExpressionRibbonSummary", GeneExpressionRibbonSummaryIndexer.class, 1, 1, 1, 1, 1, true),
ReleaseInfoIndexer("release", ReleaseInfoIndexer.class, 1, 1, 1, 1, 1, true),

// Run Sequentially -- typically take a lot of RAM or do consolidation in memory
DiseaseSearchResultIndexer("diseaseSearchResult", DiseaseSearchResultCurationIndexer.class, 8, 50, 50, 4, 1, false),
GOSearchResultCurationIndexer("goSearchResult", GOSearchResultCurationIndexer.class, 4, 1500, 1500, 4, 1, false),
AlleleSummaryIndexer("alleleSummary", AlleleSummaryCurationIndexer.class, 4, 1500, 1500, 4, 1, false),
GeneToGeneOrthologyIndexer("geneToGeneOrthology", GeneToGeneOrthologyIndexer.class, 4, 2500, 2500, 8, 1, false),
GeneMolecularInteractionIndexers("geneMolecularInteraction", GeneMolecularInteractionCurationIndexer.class, 4, 1500, 1500, 2, 1, false),
PhenotypeAnnotationIndexer("phenotypeAnnotation", PhenotypeAnnotationCurationIndexer.class, 4, 1500, 1500, 2, 1, false),
DiseaseAnnotationIndexer("diseaseAnnotation", DiseaseAnnotationCurationIndexer.class, 1, 1500, 1500, 2, 1, false),
DiseaseSearchResultIndexer("diseaseSearchResult", DiseaseSearchResultCurationIndexer.class, 8, 50, 50, 4, 1, true),
GOSearchResultCurationIndexer("goSearchResult", GOSearchResultCurationIndexer.class, 4, 1500, 1500, 4, 1, true),
AlleleSummaryIndexer("alleleSummary", AlleleSummaryCurationIndexer.class, 4, 1500, 1500, 4, 1, true),
GeneToGeneOrthologyIndexer("geneToGeneOrthology", GeneToGeneOrthologyIndexer.class, 4, 2500, 2500, 8, 1, true),
GeneMolecularInteractionIndexers("geneMolecularInteraction", GeneMolecularInteractionCurationIndexer.class, 4, 1500, 1500, 2, 1, true),
PhenotypeAnnotationIndexer("phenotypeAnnotation", PhenotypeAnnotationCurationIndexer.class, 4, 1500, 1500, 2, 1, true),
DiseaseAnnotationIndexer("diseaseAnnotation", DiseaseAnnotationCurationIndexer.class, 1, 1500, 1500, 2, 1, true),
;

private String typeName;
Expand Down
9 changes: 7 additions & 2 deletions ...src/main/java/org/alliancegenome/core/variant/converters/AlleleSearchResultConverter.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,9 +67,14 @@ public List<AlleleSearchResultDocument> convert(List<AlleleSummaryDocument> alle
}

if (doc.getAlleleOfGene() != null && doc.getAlleleOfGene().getGeneSymbol() != null) {
String geneSymbol = doc.getAlleleOfGene().getGeneSymbol().getDisplayText();
String geneSymbol = doc.getAlleleOfGene().getGeneSymbol().getFormatText();
if (taxon != null) {
geneSymbol = geneSymbol + " (" + taxon.getName() + ")";
Species geneSpecies = taxon.getSpecies();
if (geneSpecies != null) {
geneSymbol = geneSymbol + " (" + geneSpecies.getAbbreviation() + ")";
} else {
geneSymbol = geneSymbol + " (" + taxon.getName() + ")";
}
}
searchDoc.setGenes(List.of(geneSymbol));
}
Expand Down
2 changes: 1 addition & 1 deletion pom.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@
<maven-checkstyle-plugin.version>3.3.1</maven-checkstyle-plugin.version>
<checkstyle.version>10.17.0</checkstyle.version>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<curation.version>v0.47.20</curation.version>
<curation.version>v0.47.21</curation.version>
</properties>
<dependencyManagement>
<dependencies>
Expand Down
Loading