How AI is changing drug discovery

AstraZeneca notes drug discovery normally takes 10-15 years and costs over $5 billion, with under 5% of drugs reaching market, and that infrastructure complexity, disjointed data across hundreds of sources, and difficulty scaling data science slowed the search for new targets. Using the Databricks Data + AI Platform, AstraZeneca built a knowledge graph of biological insights and a recommendation engine that lets scientists generate novel drug-target hypotheses for any disease, using NLP-processed scientific literature and ML-based ranking. The system processes millions of data points from thousands of sources. The page describes improved data science productivity and 'faster time-to-insight' but does not give a specific quantified outcome metric for the knowledge graph itself.

Databricks is a unified data-and-AI lakehouse platform, used across pharma R&D for everything from early prototyping to production model governance via Unity Catalog.

This sits in the Design & Stress-Test stage of the AI use-case lifecycle: Named examples from the tools pharma teams use to scope, prototype and benchmark an AI use case before committing to build it — data-catalog, sandbox and evaluation platforms.