Testing Thousands of Hypotheses with an FDA-Qualified Research Platform

An unnamed global biopharmaceutical company needed to modernize its statistical computing environment and standardize systems across 500+ data scientists, researchers, and biostatisticians working in silos, while ensuring FDA-compliant reproducibility and productionizing models faster for 400+ internal/external consumers. It deployed an FDA-qualified research system on Domino's Enterprise MLOps platform (supporting SAS, R, Python, PyTorch, MATLAB), automatically tracking code, data, tools and packages, rolled out in phases across 15 teams. The company tested 10,000+ hypotheses with full reproducibility, grew to 2,000+ total Domino users, eliminated the need for a separate FDA submission team, and says the platform enabled cancer-research breakthroughs including identifying new drug classes and chromosomes affecting cancer immunity.

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.