Merck Life Science: Ensuring scientists get the products they need with powerful ML models

Merck Life Science's previous third-party data tool offered only descriptive insights (page views, sales) with a 2-day ERP-to-platform lag, and couldn't support predictive forecasting, anomaly detection or recommendations across its complex, globalized product catalog. It rebuilt its data stack on Google Cloud using BigQuery, Vertex AI, Looker, the Cloud Natural Language API and GKE. Similar-product-grid traffic rose 400% and Looker ecommerce dashboard traffic grew 650% over two years, with data latency cut from two days to near real-time and new releases shipping every other week; Head of Data Science Gail Buffington said the team needed to go "much deeper, to be able to build algorithms and models to drive predictions, forecasting, anomaly analysis, and recommendations in real time."

Google supplies AI to pharma through several distinct lines — Gemini/Vertex AI as an enterprise platform, and AlphaFold-based drug design licensed commercially through Isomorphic Labs.

This sits in the Build stage of the AI use-case lifecycle: Named examples from the foundation-model labs and platforms pharma teams use to actually construct, train and generate the model or application.