Skip to main content

VWSCC logo Virtual Winter School on Computational Chemistry

CET

Cecam Logo

Biomolecular Simulation in the Age of AI

Friday 29th Jan 2027

EaStCHEM School of Chemistry, University of Edinburgh; OpenBioSim Community Interest Company
Scotland, United Kingdom
15:00 CET

Please log in to be able to watch

Biomolecular Simulation in the Age of AI

J. Michel1,2

EaStCHEM School of Chemistry, University of Edinburgh
OpenBioSim Community Interest Company
Corresponding author:

Abstract:

Biomolecular simulation is an essential computational technology that is now widely adopted in drug discovery programmes. Molecular simulations chart the rugged energy landscapes that describe protein–ligand conformations and reveal opportunities for ligand optimisation through cryptic binding pockets, water-mediated interactions and entropic contributions to binding. Yet the methodologies remain computationally costly, are limited by the assumptions inherent in potential energy functions and, beyond well-trodden use cases, are restricted to expert workflows with implementations scattered across packages.

Drawing on examples from my research group, I will discuss how these challenges can be tackled through the adoption of robust software engineering practices and the deployment of machine learning methods across the complete biomolecular simulation lifecycle. I will conclude by outlining opportunities for AI to empower the field to tackle more challenging problems in the coming years, and by describing how emerging capabilities in quantum computing may complement this picture.

Keywords:

Drug discovery, molecular simulation, free energy calculations, machine learning, quantum computing

Suggested Reading:

Molecular Driving Force of a Small Molecule-Induced Protein Disorder-Order Transition Cesar Mendoza-Martinez, Arun A. Gupta, Salomé Llabrés, Paul N. Barlow, Julien Michel Commun. Chem. 9, 65, 2026

Tan, B.; Ciulli, A.; Michel, J. Quantifying Ternary Complex Stability Through Binding Free Energy Calculations in the Geometric Route., J. Chem. Theory Comput. in press 2026

Scheen, J.; Mackey, M.; Michel, J. Data-Driven Generation of Perturbation Networks for Relative Binding Free Energy Calculations. Digital Discovery, 2022, 1, 870–885.

Morado, J.; Zinovjev, K.; Hedges, L. O.; Cole, D. J.; Michel, J. Enhancing Electrostatic Embedding for ML/MM Free Energy Calculations. J. Chem. Theory Comput., 2025, 21, 11805–11819.

Kolotouros, I.; Sireesh, A.; Ferguson, S.; Thrasher, S.; Wallden, P.; Michel, J. Quantum Elastic Network Models and their Application to Graphene. arXiv, 2026, 2601.05161.

No comments