Purdue University Graduate School
Browse

File(s) under embargo

Reason: The dissertation contains articles which are under preparation for the purpose of publication.

1

year(s)

9

month(s)

14

day(s)

until file(s) become available

MACHINE LEARNING FACILITATED QUANTUM MECHANIC/MOLECULAR MECHANIC FREE ENERGY SIMULATIONS

thesis
posted on 2023-08-30, 20:19 authored by Ryan Michael SnyderRyan Michael Snyder

Bridging the accuracy of ab initio (AI) QM/MM with the efficiency of semi-empirical
(SE) QM/MM methods has long been a goal in computational chemistry. This dissertation
presents four ∆-Machine learning schemes aimed at achieving this objective. Firstly, the in-
corporation of negative force observations into the Gaussian process regression (GPR) model,
resulting in GPR with derivative observations, demonstrates the remarkable capability to
attain high-quality potential energy surfaces, accurate Cartesian force descriptions, and reli-
able free energy profiles using a training set of just 80 points. Secondly, the adaptation of the
sparse streaming GPR algorithm showcases the potential of memory retention from previous
phasespace, enabling energy-only models to converge using simple descriptors while faith-
fully reproducing high-quality potential energy surfaces and accurate free energy profiles.
Thirdly, the utilization of GPR with atomic environmental vectors as input features proves
effective in enhancing both potential energy surface and free energy description. Further-
more, incorporating derivative information on solute atoms further improves the accuracy
of force predictions on molecular mechanical (MM) atoms, addressing discrepancies arising
from QM/MM interaction energies between the target and base levels of theory. Finally, a
comprehensive comparison of three distinct GPR schemes, namely GAP, GPR with an aver-
age kernel, and GPR with a system-specific sum kernel, is conducted to evaluate the impact
of permutational invariance and atomistic learning on the model’s quality. Additionally, this
dissertation introduces the adaptation of the GAP method to be compatible with the sparse
variational Gaussian processes scheme and the streaming sparse GPR scheme, enhancing
their efficiency and applicability. Through these four ∆-Machine learning schemes, this dis-
sertation makes significant contributions to the field of computational chemistry, advancing
the quest for accurate potential energy surfaces, reliable force descriptions, and informative
free energy profiles in QM/MM simulations.

History

Degree Type

  • Doctor of Philosophy

Department

  • Chemistry

Campus location

  • Indianapolis

Advisor/Supervisor/Committee Chair

Jingzhi Pu

Additional Committee Member 2

Christoph Naumann

Additional Committee Member 3

Ian Webb

Additional Committee Member 4

Yongming Deng