Justin S SmithPostdoctoral Research Associate T-1/CNLS Computational Chemistry Office: TA-3, Bldg 1690, Room 117 Mail Stop: N/A Phone: (505) 665-5693 Fax: N/A just@lanl.gov home page Research highlight
Available on GitHub
I am on the development team of the ANI-1, ANI-1x, and ANI-1ccx general purpose neural network-based molecular potentials for organic molecules. I also assisted in research focused on the prediction of other QM properties such as atomic charges and molecular dipoles. I was also involved in the developement of the HIP-NN and AIMNet neural network-based models for molecular property prediction.
Continuing efforts:
- Recapturing long-range physics for general purpose ML potentials.
- Improved active learning through better data selection methods.
- Active learning for large scale materials simulation.
- Application and validation of ANI and HIP-NN ML-based potentials.
| | Educational Background/Employment:- Ph.D. (2018) Chemistry, University of Florida
- B.S. (2013) Mathematics, University of Montevallo
Research Interests: Selected Recent Publications: Google Scholar profile available here.
- Smith, J. S., Isayev, O., Roitberg, A. E. ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost, Chemical Science 8, 3192-3203 (2017).
- Smith, J. S., Isayev, O., Roitberg, A. E. ANI-1: A data set of 20M off-equilibrium DFT calculations for organic molecules, Scientific Data 4, 170193 (2017).
- Lubbers N., Smith, J. S., Barros, K. Hierarchical modeling of molecular energies using a deep neural network, The Journal of Chemical Physics 148, 241715 (2018).
- Smith, J. S., Nebgen B., Lubbers N., Isayev O., Roitberg, A. E. Less is more: sampling chemical space with active learning, The Journal of Chemical Physics 148, 241733 (2018).
- Nebgen B., Lubbers N., Smith, J. S., et al. Transferable dynamic molecular charge assignment using deep neural networks, Journal of Chemical Theory and Computation 14, 4687-4698 (2018).
- Sifain, A. E., Lubbers N., Nebgen B., Smith, J. S., et al. Discovering a transferable charge assignment model using machine learning, The Journal of Physical Chemistry Letters9, 4495-4501 (2018).
- Smith, J. S., Roitberg, A. E., Isayev, O. Transforming Computational Drug Discovery with Machine Learning and AI, ACS Medicinal Chemistry Letters 9,1065-1069 (2018).
|