Biolink Model: a Universal Schema for Knowledge Graphs in Clinical, Biomedica...
summary
An open‑source schema (Biolink Model) standardizes biomedical KGs by reusing ontologies (MONDO), ordering ID prefixes, and supporting class hierarchies plus multiple inheritance; it adds association (statement-level) qualifiers to capture context like tissue and direction, provides LinkML validators and converters (YAML → JSON Schema/SQL), auto-generates docs, and powers a federated Translator ecosystem that maps over 350 data sources, with a Python toolkit for programmatic use.
AI-written summary · about
chapters (17)
- 0:00Biolink Model introduction
- 1:07Inconsistent biomedical data challenges
- 2:11Schema: rigidity vs flexibility
- 4:50Shared model practices
- 5:57Biolink as socio-technical solution
- 7:02Biolink core: nodes and edges
- 8:49Class hierarchies and inheritance
- 9:53Metadata and slot domains/ranges
- 10:35Predicates in knowledge triples
- 11:17Mapping biomedical statements
- 12:23Refining statements with qualifiers
- 13:50Qualifiers and association classes
- 14:54Robust modeling language importance
- 15:57LinkML tools overview
- 16:40Principles for reusable models
- 17:22Biolink in Translator Consortium
- 18:06Q&A: LinkML, KGX, qualifiers
related talks
44mBuilding Knowledge Graphs- 44mBuilding Knowledge Graphs
46mBuilding Knowledge Graphs
26mKnowledge Combined Common Data Model: A Graph-Based Integration of Reactome and OMOP CDM
25mKnowledge graphs for financial institutions
16mMedQGraph: TMKGs for AI-Driven Healthcare Insights
29mBuilding a knowledge graph with the Natural History Museum to work as a taxonomic equivalence engine
28mOntology Creation