AI/ML

Knowledge Graphs and Scientific Discovery: Connecting the Dots in Research

How semantic knowledge graphs enable breakthrough discoveries by revealing hidden connections across millions of research papers.

Ankita Choudhary

December 12, 2025

18 min read

The Information Overload Problem

Scientific literature is growing exponentially. PubMed alone adds over 1 million new articles annually, and researchers estimate that the total body of scientific knowledge doubles every 9 years. No human can keep pace.

This creates a paradox: we have more knowledge than ever, but it's increasingly difficult to find relevant information and make connections across disciplines.

Annual publication volume has outrun human reading capacity

What is a Knowledge Graph?

A knowledge graph represents information as a network of entities (nodes) and relationships (edges). Unlike traditional databases, knowledge graphs capture semantic meaning and enable complex queries across interconnected data.

A fragment of the BRCA1 knowledge graph

BioAgents Knowledge Extraction Pipeline

Our BioAgents system transforms unstructured research papers into structured knowledge graphs through a multi-stage pipeline:

The four-stage BioAgents extraction pipeline

Ontology Integration

BioAgents maps extracted entities to established biomedical ontologies:

Ontology	Coverage	Entities
Gene Ontology (GO)	Biological processes, molecular functions	45,000+
Human Phenotype Ontology (HPO)	Clinical phenotypes	16,000+
ChEBI	Chemical entities	170,000+
Disease Ontology (DO)	Human diseases	12,000+
Protein Ontology (PRO)	Protein forms	40,000+

Example: Entity Linking

typescript

// Raw text extraction
const rawEntity = "BRCA1 gene";

// Entity linking result
const linkedEntity = {
  text: "BRCA1 gene",
  type: "Gene",
  ontologyMappings: [
    { ontology: "HGNC", id: "HGNC:1100", label: "BRCA1" },
    { ontology: "NCBI Gene", id: "672", label: "BRCA1" },
    { ontology: "UniProt", id: "P38398", label: "BRCA1_HUMAN" }
  ],
  confidence: 0.98
};

SPARQL Queries for Discovery

Knowledge graphs enable powerful semantic queries that would be impossible with traditional search:

Query 1: Find Drug Repurposing Candidates

sparql

PREFIX bio: <http://bio-ontology.org/>
PREFIX drug: <http://drugbank.org/>

SELECT ?drug ?originalIndication ?newTarget ?disease
WHERE {
  ?drug a drug:Drug ;
        drug:indication ?originalIndication ;
        drug:target ?target .
  
  ?target bio:associatedWith ?pathway .
  ?pathway bio:involvedIn ?disease .
  
  FILTER NOT EXISTS {
    ?drug drug:indication ?disease
  }
  
  FILTER (?disease != ?originalIndication)
}
ORDER BY DESC(?confidence)
LIMIT 100

Query 2: Discover Hidden Gene-Disease Connections

sparql

PREFIX bio: <http://bio-ontology.org/>

SELECT ?gene ?disease (COUNT(?pathway) as ?sharedPathways)
WHERE {
  ?gene bio:participatesIn ?pathway .
  ?pathway bio:associatedWith ?disease .
  
  FILTER NOT EXISTS {
    ?gene bio:directlyAssociatedWith ?disease
  }
}
GROUP BY ?gene ?disease
HAVING (COUNT(?pathway) >= 3)
ORDER BY DESC(?sharedPathways)

Real-World Discovery: A Case Study

In 2024, researchers using knowledge graph analysis discovered a previously unknown connection between a rare metabolic disorder and a common cardiovascular drug:

A connection hidden across three domains for twenty years

Integration with DIDs

Every knowledge graph node in Bio-DID-Seq is linked to its source via DIDs, creating a verifiable provenance chain:

json

{
  "@context": "https://schema.org",
  "@type": "BiomedicalEntity",
  "@id": "did:bio:entity:brca1-protein",
  "name": "BRCA1 Protein",
  "derivedFrom": [
    {
      "@type": "ScholarlyArticle",
      "identifier": "did:bio:paper:10.1038/nature12912",
      "extractionConfidence": 0.95,
      "extractionDate": "2025-01-15"
    }
  ],
  "relationships": [
    {
      "type": "interacts_with",
      "target": "did:bio:entity:rad51-protein",
      "evidence": "did:bio:paper:10.1016/j.cell.2020.01.001",
      "confidence": 0.92
    }
  ]
}

The Future: Hypothesis Generation

The next frontier is using knowledge graphs not just for discovery, but for generating testable hypotheses:

typescript

// AI-powered hypothesis generation
const hypotheses = await client.graph.generateHypotheses({
  seedEntity: 'did:bio:entity:alzheimers-disease',
  maxHops: 3,
  minConfidence: 0.7,
  noveltyThreshold: 0.8
});

// Returns ranked hypotheses with supporting evidence
hypotheses.forEach(h => {
  console.log(`Hypothesis: ${h.statement}`);
  console.log(`Confidence: ${h.confidence}`);
  console.log(`Supporting papers: ${h.evidence.length}`);
  console.log(`Novelty score: ${h.novelty}`);
});

Conclusion

Knowledge graphs are transforming scientific discovery from a needle-in-a-haystack problem to a connected exploration. By representing research as interconnected entities and relationships, we can:

Discover hidden connections across disciplines
Identify drug repurposing opportunities
Generate testable hypotheses automatically
Accelerate the pace of scientific progress

The combination of knowledge graphs with decentralized identifiers ensures that every discovery is traceable, verifiable, and reproducible.

---

Further reading: Gene Ontology, BioBERT, SPARQL Query Language

Ready to Get Started?

Explore our documentation to learn how to integrate Ekayana into your research workflow.

Read Documentation More Articles