ENPICOMAn honest conversation about what it takes to make ML work in biotherapeutics
Hear from experts at Sanofi, Eli Lilly, Amgen, AbbVie, and Genmab as they share real-world lessons from adopting AI/ML in biologics discovery and engineering.
From bridging lab and data science workflows to dealing with scattered data and real-world model limitations, the panel offers a candid look at what works, what doesn’t, and why. Gain a grounded perspective on the everyday decisions behind successful ML implementation, with practical insights on preparing data, aligning teams, and deploying models where they matter most: in scientists’ hands.
Discussion points:
- Why structured, high-throughput data and robust pipelines matter at least as much as the ML models themselves
- What it takes to move from scattered analyses to automated, end-to-end workflows that support ML adoption
- Why AI initiatives stall, and what it takes to operationalize ML models and shift team culture
- Overcoming AI adoption blockers, including siloed teams, missing expertise, and infrastructure limitationsHow to ensure lab scientists can actually use ML model outputs in their day-to-day work
Panelists & moderator:
Roberto Spreafico, PhD
Vice President, Head, Discovery Data Science, Genmab
Melody Shahsavarian, PhD
Director, Data Strategy & Digital Transformation, Biotherapeutics Discovery Research, Eli Lilly & Company
Daniel Yoo
Scientific Associate Director, Large Molecule Discovery, Amgen
Michail Vlysidis, PhD
Principal Engineer, AbbVie
Abhinav Gupta, PhD
Principal Machine Learning Scientist, AI Innovation, Large Molecule Research, Sanofi
Nicola Bonzanni, PhD
Founder and CEO, ENPICOM
