Building Open, Accelerated Foundations for Molecular Science
Speaker: Kyle Tretina, PhD
Affiliation: NVidia
Date: December 2025
Watch the recording on YouTube
Abstract
The life sciences are entering a new computational era. With data spanning millions of proteins, cells, and reactions, progress now depends on how effectively AI systems integrate across these diverse representations. This talk explores how open, GPU-accelerated models and libraries are driving discovery from molecular targets to synthesis. We’ll highlight emerging directions in multimodal modeling, physics-informed generative AI, and accelerated simulation, showing how open research in sequence modeling, structure prediction, and molecular generation is unifying the field. Together, these efforts are establishing digital biology as an open, computational science—where AI and physics jointly advance our ability to model and design life.
Speaker bio
Kyle Tretina is a leading researcher and product marketing leader at NVIDIA, focused on advancing AI for digital biology and drug discovery. He drives the strategy and storytelling behind BioNeMo and our work with BioPharma, shaping how next-generation foundation models and GPU-accelerated microservices transform molecular and protein design. With a PhD in molecular microbiology and immunology, Kyle bridges science and strategy, translating breakthroughs in AI, chemistry, and biology into platforms that accelerate discovery for researchers, startups, and pharmaceutical companies worldwide.
Rights and attribution
This recording and accompanying text are presented for educational access with attribution to the speaker. Speaker views are their own. No open license is implied unless explicitly stated.