DISGENET: Accelerating Data-Driven Discovery in Disease Genomics and Therapeutic Development

Abstract Precision medicine and therapeutic development rely on a comprehensive understanding of genotype–phenotype relationships, yet this information remains fragmented across diverse sources. DISGENET, established over 15 years ago, addresses this challenge by systematically integrating gene–disease, variant–disease, and disease–disease associations from authoritative databases and the literature. This major upgrade expands coverage with chemical and pharmacological annotations and integrates biobank and clinical data. An advanced natural language processing (NLP) pipeline captures emerging evidence with full provenance and contextual details, key to streamlining data-driven insights. DISGENET supports diverse users through multiple tools, including an intuitive web interface, a REST API, an R package, a Cytoscape app, and an AI assistant for natural language queries. Quarterly updates ensure data currency, while a sustainable freemium model provides free academic access and supports ongoing development. DISGENET aims to accelerate data-driven discoveries and advance precision medicine and drug development. The platform is accessible at https://www.disgenet.com. Highlights DISGENET accelerates precision medicine via comprehensive genotype–phenotype data Access to gene, variant, disease, and drug data in a single platform Up-to-date evidence with provenance and full context Suite of tools to serve diverse research and clinical communities Sustainable freemium model ensures ongoing platform innovation. Competing Interest Statement The authors have declared no competing interest.