Olexandr Isayev

Professor, Chemistry

Bio

Courtesy appointments:

• Associate Editor, Journal of Chemical Information and Modeling, ACS
• Affiliate faculty, CMU-Pitt Computational Biology Ph.D. Program
• Affiliate faculty, CMU-Pitt Molecular Biophysics and Structural Biology Program
• Affiliate faculty, Scott Institute for Energy Innovation

Education

Postdoctoral Fellow, Case Western Reserve University, 2009–2012
Ph.D. in Theoretical Chemistry, Jackson State University, 2008
M.S. in Chemistry, Dnepropetrovsk National University, Ukraine, 2002

Research

Keywords: Theory & Computational; Machine Learning; Experiment Automation; AI

Projects

The Isayev lab works at the interface of theoretical chemistry, pharmaceutical sciences, and computer science. We use molecular simulations and artificial intelligence (AI) to solve difficult chemistry problems. Our research has been groundbreaking in the field of ML and quantum mechanics (QM), paving the way for developing several families of atomistic molecular ML potentials that approximate the solution of the Schrodinger equation. We have developed a single ‘universal’ model, which is highly accurate compared to reference QM calculations at millions of times faster speeds. Focusing on parametrization for molecules in neutral and charged states makes it a valuable model for modeling most non-metallic compounds, including chemical reactions, kinetics, thermochemistry, structural optimization, and MD simulations.

We also develop generative AI (GenAI) methods that solve a so-called inverse design problem. These methods enable the design of molecules with the desired physicochemical, biological, or both properties. We successfully validated this approach by designing small-molecule protein kinase, protease, and GPCR inhibitors. We showed that a trained AI model can mimic expert chemists' skills. This is a prime example of the transfer of decision power from human experts to AI. Using CMU Cloud Lab, we are developing a novel ML-guided molecular discovery platform that combines synergistic innovations in automated experiments and automated machine learning (AutoML) and Reinforcement learning (RL) agents. A software-controlled synthesis platform enables rapid iterative experimental–computational cycles and explores non-intuitive design criteria identified by an agent.

Within the next few years, I would like to push the frontiers of chemistry methods and AI to mimic and supersede expert scientists' chemical intuition and decision-making. The critical need for "Chemical Intelligence" exemplifies the need for advancement beyond the presently available algorithms in two primary ways: (i) elevating ML from generating data models toward generating expert-approved inferences and conclusions; (ii) enabling autonomous reasoning about these outcomes and prior data to generate and execute an actionable research plan.

Publications

The Full List of Publications

Appointments

Years	Position
2024–present	Professor, Carnegie Mellon University
2023–2024	Associate Professor, Carnegie Mellon University
2020–2023	Assistant Professor, Carnegie Mellon University
2017–2019	Research Assistant Professor, UNC Eshelman School of Pharmacy, University of North Carolina at Chapel Hill
2016	Senior Fellow, Institute for Pure & Applied Mathematics, University of California, Los Angeles
2013-2016	Research Scientist, UNC Eshelman School of Pharmacy, University of North Carolina at Chapel Hill
2012-2013	Senior Scientist, US Army Engineering Research and Development Center

Awards and Distinctions

Years	Award
2023	Scialog Fellow
2017, 2014	ACS Emerging Technology Award
2016	Eshelman Institute for Innovation Award
2015	Chemical Structure Association Trust Award
2014	NVIDIA GPU Computing Award
2009	IBM-Löwdin Memorial Fellowship