Lab Home | Phone | Search
Center for Nonlinear Studies  Center for Nonlinear Studies
 Colloquia Archive 
 Postdoc Seminars Archive 
 Quantum Lunch 
 Quantum Lunch Archive 
 CMS Colloquia 
 Q-Mat Seminars 
 Q-Mat Seminars Archive 
 P/T Colloquia 
 Kac Lectures 
 Kac Fellows 
 Dist. Quant. Lecture 
 Ulam Scholar 
 CNLS Fellowship Application 
 Student Program 
 Past Visitors 
 History of CNLS 
 Maps, Directions 
 CNLS Office 
Justin S Smith

Postdoctoral Research Associate

Computational Chemistry

Justin S Smith

Office: TA-3, Bldg 1690, Room 117
Mail Stop: N/A
Phone: (505) 665-5693
Fax: N/A
home page

Research highlight
    ANI-1 TOC
    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:

    Research interests

Selected Recent Publications:

    Google Scholar profile available here.

  1. 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).
  2. 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).
  3. 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).
  4. 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).
  5. 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).
  6. 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).
  7. 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).
LANL Operated by the Triad National Security, LLC for the National Nuclear Security Administration of the US Department of Energy.
Copyright © 2003 LANS, LLC | Disclaimer/Privacy