Building a unified statistical computing environment at scale

Novartis ran over 1,000 statistical programmers and data scientists across hundreds of active clinical studies on fragmented legacy software platforms and needed to streamline operations while meeting regulatory requirements. It launched project QUANTA to consolidate its global statistical computing environment onto a single cloud-hosted Domino platform, building four custom extensions with partner KSM Technology Partners: an RA Creator (provisioning), a Task Manager (simplified git workflows), a Batch Runner (pipeline coordination), and a Publisher (exporting deliverables with regulatory metadata). Speakers Priya Subramaniam (Novartis) and Mike Harnish (KSM) described a multi-year transition where mapping '25 years of legacy data early' let compliance be built into the platform architecture itself. This page presents talking points/takeaways from a recorded presentation rather than a quantified case-study outcome.

Domino Data Lab is an enterprise MLOps platform built for regulated industries — the sanctioned sandbox where biopharma teams run reproducible experiments under GxP/21 CFR Part 11 guardrails.

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.