TSVP Talk: "AI and Structural Biology: From Protein Structure to Molecular Design" by Alberto Perez

Title: AI and Structural Biology: From Protein Structure to Molecular Design

Speaker: Alberto Perez, University of Florida

Abstract: Proteins are the molecular machines of life. They digest food, transport oxygen, and regulate nearly every biological process. When these systems malfunction, disease emerges. Understanding how proteins work requires knowing not just their structures, but how they move and interact—often in highly dynamic and flexible ways.

Recent advances in artificial intelligence, highlighted by the impact of AlphaFold and recognized by the Nobel Prize in Chemistry, have transformed our ability to predict protein structures with remarkable accuracy. This has fundamentally changed structural biology, opening the door to large-scale modeling and design.

In this talk, I will trace the transition from AI systems that mastered complex games such as Go to those that can predict the structure of proteins. I will highlight how community-wide efforts—through international competitions and shared databases—enabled these breakthroughs. Finally, I will discuss how combining AI with physics-based approaches, such as molecular simulations, is helping us move beyond structure prediction to uncover the principles that govern biological function.

Profile: Alberto Perez is an Associate Professor of Chemistry and Associate Director of the Quantum Theory Project at the University of Florida. His research focuses on developing integrative computational approaches that combine artificial intelligence and molecular simulations to understand and design biomolecular interactions.

He completed his Ph.D. in Barcelona and carried out postdoctoral training at University of California, San Francisco and Stony Brook University with Ken A. Dill. His group develops methods to model flexible systems, including protein–protein and protein–peptide interactions, with applications in peptide-based drug discovery and molecular design.. 

Language: English

Target audience: General audience/everyone at OIST and beyond.
Freely accessible to all OIST members and guests without registration.

This talk will also be broadcast online via Zoom:
Meeting ID: 993 1216 5065
Passcode: 603487

※ Please note that this event may be recorded and the videos uploaded. In addition, photos may be taken during the event. These are intended for publication online (the OIST website, social media, etc.)※