From Molecular Dynamics to Bayesian Optimization: Matteo Aldeghi on Cutting-Edge Molecular Design

In this episode, we’re joined by Matteo Aldegni, Director of Machine Learning Research at Bayer, where he leads a team specializing in Machine Learning applications for chemistry and drug discovery. With a rich background spanning Google Research, Massachusetts Institute of Technology, and the Max Planck Institute for Biophysical Chemistry/University of Gottingen, Matteo brings extensive expertise in Machine Learning, drug discovery, and molecular design. His academic journey includes a PhD in computational biochemistry from the University of Oxford, where he explored topics from drug design to Molecular Dynamics.

Matteo delves into the intricacies of Molecular Dynamics, the cornerstone of computer-aided molecular design, shedding light on how it paved the way for modern Machine Learning techniques. From the innovative sampling methods inspired by Molecular Dynamics to the transformative potential of Bayesian optimization, Matteo provides insights into the cutting-edge advancements driving molecular design. Join us as we explore the intersection of first-principles molecular models and Machine Learning, as well as Matteo’s vision for the future of molecular design, including the concept of self-driving laboratories and Machine Learning force fields.