Pharmacolibrary: Interoperable executable models for PK, PD and PGx derived from published evidence
In the authors' words
Published pharmacological knowledge is distributed across heterogeneous scientific literature, databases, and computational models, making systematic reuse, comparison, and reproducibility difficult. We present Pharmacolibrary v26.11, a source-traceable resource that connects pharmacokinetic (PK), pharmacodynamic (PD), and pharmacogenomic (PGx) knowledge with executable models, simulations, and interactive visualizations. A multi-agent workflow combines LLM-assisted literature retrieval and extraction with deterministic validation, ontology mapping, provenance tracking, automated model generation, and rule-based review. The system transforms published evidence and extracted parameters into executable models across Modelica, FMI, SBML, MATLAB, and CellML and provides browser-based simulations for research and education. Preliminary evaluation indicates that decomposing literature extraction into multiple stages improves parameter recovery compared with single-pass extraction and that locally deployed open-weight models can provide performance that is at least comparable with frontier commercial LLMs. Pharmacolibrary provides a foundation for scalable, auditable curation of pharmacological knowledge and for connecting published evidence to reusable computational models across research, simulation, and education.
Appeared: Wednesday, November 18. bioRxiv. Preprint, not yet peer-reviewed.