DISQOVER Knowledge Feeds

DISQOVER Knowledge Feeds, by ONTOFORCE, are modular, domain-specific collections of publicly available life sciences data that are curated, harmonized, ontology-mapped, and delivered directly into your DISQOVER Foundation. Designed for life sciences and pharmaceutical organizations, they eliminate the time-consuming burden of sourcing, cleaning, and normalizing public datasets, allowing research and data teams to focus on discovery and analysis rather than data preparation.

Each Knowledge Feed is refreshed monthly by ONTOFORCE's expert data team and linked across domains within the DISQOVER Foundation. This creates a single, connected knowledge graph that integrates seamlessly with an organization's own internal data, enabling reliable cross-domain queries and insights without additional integration effort.

Available Knowledge Feeds

• Life Sciences Foundation — Included in Foundation; covers Clinical Study, Disease, Drug, Gene, Gene-Disease-Target Association, Ontology, and Target entities from 30+ data sources, totalling 3.7 billion triples.
• Clinical Development — Covers Adverse Event, Arm, Clinical Protocol, Mechanism of Action, Outcome, Site, Sponsor, Study Population, and Withdrawal from 20+ data sources, totalling 2.7 billion triples.
• Biomedical Research — Covers Anatomy, Biomarker, Cell Line, Chemical, GWAS Result, GWAS Study, Isomer, Mechanism of Action, Ontology, Pathway, Patent, Patent Family, Person, PheWAS Result, Reaction, and Variant from 30+ data sources, totalling 18.2 billion triples.
• Protein Functions & Interactions — Covers Anatomy, Analytical Antibody, Enzyme, Isoform, Organism, Protein, Protein Complex, Protein Domain, Protein Interactions, Protein-Variant-Association, and Variant from 20+ data sources, totalling 7.7 billion triples.
• Scientific Literature & Publications — Covers Journal, Ontology, Person, and Publication from 5+ data sources, totalling 22.2 billion triples.
• Safety & Regulatory — Covers Adverse Event, Drug Treatment, Drug-Drug Interaction, IDMP-Property, IDMP-Referential, IDMP-Substance, Location, Medical Device, Medicinal Package, Medicinal Product, Organization, Pharmacokinetics, Toxicity, and Vendor from 10+ data sources, totalling 36.5 billion triples.
• Gene Function & Conservation — Covers Gene, Organism, Ortholog, Transcript, and Variant from 10+ data sources, totalling 1.4 billion triples.

Key Capabilities and Benefits

• Ready from day one — Trusted, harmonized data is delivered directly into your Foundation so analysis can begin immediately, with no weeks spent on sourcing or cleaning.
• Shared ontologies — All entities are mapped to shared ontologies, enabling reliable and consistent queries across domains and sources.
• Always current — Monthly refreshes keep the knowledge graph aligned with the latest publicly available scientific data, eliminating stale data from manual refresh cycles.
• Full provenance — Every data point is traceable to its original source, providing the confidence needed to act on insights.
• One connected graph — Public and internal data are linked within a single knowledge graph, ready for cross-domain discovery without siloed structures.
• 80+ trusted sources — All feeds are mapped to shared ontologies, linked across entities, and enriched with full provenance to create a single connected source of truth.

Licensed Data Integration

• In addition to curated public datasets, DISQOVER can ingest and harmonize licensed data from providers such as Clarivate (Cortellis), BioRelate, and Citeline into the same knowledge graph.
• Licensed content is fully linked, ontology-mapped, and searchable alongside all other data, unlocking richer cross-domain insights without requiring additional integration effort.

DISQOVER Knowledge Feeds are built on ONTOFORCE's knowledge graph technology and are designed to integrate with the broader DISQOVER platform, supporting life sciences and pharmaceutical companies with connected data management and visualization across research, clinical development, safety, regulatory, and beyond.