Modern semiempirical electronic structure methods have considerable promise in drug discovery as universal “force fields” that can reliably model biological and drug-like molecules, including alternative tautomers and protonation states. Herein, we compare the performance of several neglect of diatomic differential overlap-based semiempirical (MNDO/d, AM1, PM6, PM6-D3H4X, PM7, and ODM2), density-functional tight-binding based (DFTB3, DFTB/ChIMES, GFN1-xTB, and GFN2-xTB) models with pure machine learning potentials (ANI-1x and ANI-2x) and hybrid quantum mechanical/machine learning potentials (AIQM1 and QDπ) for a wide range of data computed at a consistent ωB97X/6-31G* level of theory (as in the ANI-1x database). This data includes conformational energies, intermolecular interactions, tautomers, and protonation states. Additional comparisons are made to a set of natural and synthetic nucleic acids from the artificially expanded genetic information system that has important implications for the design of new biotechnology and therapeutics. Finally, we examine the acid/base chemistry relevant for RNA cleavage reactions catalyzed by small nucleolytic ribozymes, DNAzymes, and ribonucleases. Overall, the hybrid quantum mechanical/machine learning potentials appear to be the most robust for these datasets, and the recently developed QDπ model performs exceptionally well, having especially high accuracy for tautomers and protonation states relevant to drug discovery.
Skip Nav Destination
Article navigation
28 March 2023
Research Article|
March 22 2023
Modern semiempirical electronic structure methods and machine learning potentials for drug discovery: Conformers, tautomers, and protonation states
Special Collection:
Modern Semiempirical Electronic Structure Methods
Jinzhe Zeng (曾晋哲)
;
Jinzhe Zeng (曾晋哲)
(Data curation, Software, Visualization, Writing – original draft, Writing – review & editing)
Laboratory for Biomolecular Simulation Research, Institute for Quantitative Biomedicine and Department of Chemistry and Chemical Biology, Rutgers University
, Piscataway, New Jersey 08854, USA
Search for other works by this author on:
Yujun Tao (陶玉君)
;
Yujun Tao (陶玉君)
(Data curation, Visualization, Writing – review & editing)
Laboratory for Biomolecular Simulation Research, Institute for Quantitative Biomedicine and Department of Chemistry and Chemical Biology, Rutgers University
, Piscataway, New Jersey 08854, USA
Search for other works by this author on:
Timothy J. Giese
;
Timothy J. Giese
(Writing – review & editing)
Laboratory for Biomolecular Simulation Research, Institute for Quantitative Biomedicine and Department of Chemistry and Chemical Biology, Rutgers University
, Piscataway, New Jersey 08854, USA
Search for other works by this author on:
Darrin M. York
Darrin M. York
a)
(Formal analysis, Funding acquisition, Project administration, Resources, Supervision, Writing – original draft, Writing – review & editing)
Laboratory for Biomolecular Simulation Research, Institute for Quantitative Biomedicine and Department of Chemistry and Chemical Biology, Rutgers University
, Piscataway, New Jersey 08854, USA
a)Author to whom correspondence should be addressed: Darrin.York@rutgers.edu
Search for other works by this author on:
a)Author to whom correspondence should be addressed: Darrin.York@rutgers.edu
Note: This paper is part of the JCP Special Topic on Modern Semiempirical Electronic Structure Methods.
J. Chem. Phys. 158, 124110 (2023)
Article history
Received:
December 19 2022
Accepted:
March 03 2023
Citation
Jinzhe Zeng, Yujun Tao, Timothy J. Giese, Darrin M. York; Modern semiempirical electronic structure methods and machine learning potentials for drug discovery: Conformers, tautomers, and protonation states. J. Chem. Phys. 28 March 2023; 158 (12): 124110. https://doi.org/10.1063/5.0139281
Download citation file:
Sign in
Don't already have an account? Register
Sign In
You could not be signed in. Please check your credentials and make sure you have an active account and try again.
Sign in via your Institution
Sign in via your InstitutionPay-Per-View Access
$40.00
Citing articles via
Related Content
Benchmark of general-purpose machine learning-based quantum mechanical method AIQM1 on reaction barrier heights
J. Chem. Phys. (February 2023)
Tetrazole acetic acid: Tautomers, conformers, and isomerization
J. Chem. Phys. (February 2014)
Photoelectron spectroscopy of adiabatically bound valence anions of rare tautomers of the nucleic acid bases
J. Chem. Phys. (November 2007)
Strong electron correlations in cobalt valence tautomers
J. Chem. Phys. (March 2002)
Label-free GR5 DNAzyme-based colorimetric sensing for lead ions (Pb2+) detection
AIP Conference Proceedings (May 2023)