Olexandr Isayev

Connecting artificial intelligence (AI) with chemical sciences.

 

I am research professor at the UNC School of Pharmacy, the University of North Carolina at Chapel Hill. My current research interests focus on solving fundamental chemical problems with machine learning, molecular modeling, and quantum mechanics.

Featured publications:

AFLOW-ML: A RESTful API for machine-learning predictions of materials propertiesComputational Materials Science, 152, 2018, 134-145.
[DOI: 10.1016/j.commatsci.2018.03.075]

Less is more: Sampling chemical space with active learning.
Journal of Chemical Physics 148, 2018, 241733.
[DOI: 10.1063/1.5023802]

Universal fragment descriptors for predicting properties of inorganic crystals. Nature Communications 8, 2017, Article number: 15679.
[DOI: 10.1038/ncomms15679]

ANI-1: an extensible neural network potential with DFT accuracy at force field computational costChem. Sci., 2017, 8, 3192-3203.
[DOI: 10.1039/C6SC05720A]

Material informatics driven design and experimental validation of lead titanate as an aqueous solar photocathode. Materials Discovery. 20176, 9-16.
[DOI: 10.1016/j.md.2017.04.001]

Deep Reinforcement Learning for De-Novo Drug Design.
Accepted.
Preprint: arXiv:1711.10907
[DOI:  ]