1
|
Houston PL, Qu C, Yu Q, Pandey P, Conte R, Nandi A, Bowman JM. No Headache for PIPs: A PIP Potential for Aspirin Runs Much Faster and with Similar Precision Than Other Machine-Learned Potentials. J Chem Theory Comput 2024; 20:3008-3018. [PMID: 38593438 DOI: 10.1021/acs.jctc.4c00054] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/11/2024]
Abstract
Assessments of machine-learning (ML) potentials are an important aspect of the rapid development of this field. We recently reported an assessment of the linear-regression permutationally invariant polynomial (PIP) method for ethanol, using the widely used (revised) rMD17 data set. We demonstrated that the PIP approach outperformed numerous other methods, e.g., ANI, PhysNet, sGDML, and p-KRR, with respect to precision and notably with respect to speed [Houston et al., J. Chem. Phys. 2022, 156, 044120]. Here, we extend this assessment to the 21-atom aspirin molecule, using the rMD17 data set, with a focus on the speed of evaluation. Both energies and forces are used for training, and the precision of several PIPs is examined for both. Normal mode frequencies, the methyl torsional potential, and 1d vibrational energies for an OH stretch are presented. We show that the PIP approach achieves the level of precision obtained from other ML methods, e.g., atom-centered neural network methods, linear regression ACE, and kernel methods, as reported by Kovács et al. in J. Chem. Theory Comput. 2021, 17, 7696-7711. More significantly, we show that the PIP PESs run much faster than all other ML methods, whose timings were evaluated in that paper. We also show that the PIP PES extrapolates well enough to describe several internal motions of aspirin, including an OH stretch.
Collapse
Affiliation(s)
- Paul L Houston
- Department of Chemistry and Chemical Biology, Cornell University, Ithaca, New York 14853, United States
- Department of Chemistry and Biochemistry, Georgia Institute of Technology, Atlanta, Georgia 30332, United States
| | - Chen Qu
- Independent Researcher, Toronto, Ontario M9B0E3, Canada
| | - Qi Yu
- Department of Chemistry, Fudan University, Shanghai 200438, P. R. China
| | - Priyanka Pandey
- Department of Chemistry, Cherry L. Emerson Center for Scientific Computation, Emory University, Atlanta, Georgia 30322, United States
| | - Riccardo Conte
- Dipartimento di Chimica, Università degli Studi di Milano, via Golgi 19, 20133 Milano, Italy
| | - Apurba Nandi
- Department of Chemistry, Cherry L. Emerson Center for Scientific Computation, Emory University, Atlanta, Georgia 30322, United States
- Department of Physics and Materials Science, University of Luxembourg, Luxembourg City L-1511, Luxembourg
| | - Joel M Bowman
- Department of Chemistry, Cherry L. Emerson Center for Scientific Computation, Emory University, Atlanta, Georgia 30322, United States
| |
Collapse
|
2
|
Käser S, Meuwly M. Numerical Accuracy Matters: Applications of Machine Learned Potential Energy Surfaces. J Phys Chem Lett 2024:3419-3424. [PMID: 38506827 DOI: 10.1021/acs.jpclett.3c03405] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/21/2024]
Abstract
The role of numerical accuracy in training and evaluating neural network-based potential energy surfaces is examined for different experimental observables. For observables that require third- and fourth-order derivatives of the potential energy with respect to Cartesian coordinates single-precision arithmetics as is typically used in ML-based approaches is insufficient and leads to roughness of the underlying PES as is explicitly demonstrated. Increasing the numerical accuracy to double-precision gives a smooth PES with higher-order derivatives that are numerically stable and yield meaningful anharmonic frequencies and tunneling splitting as is demonstrated for H2CO and malonaldehyde. For molecular dynamics simulations, which only require first-order derivatives, single-precision arithmetics appears to be sufficient, though.
Collapse
Affiliation(s)
- Silvan Käser
- Department of Chemistry, University of Basel, Klingelbergstrasse 80, CH-4056 Basel, Switzerland
| | - Markus Meuwly
- Department of Chemistry, University of Basel, Klingelbergstrasse 80, CH-4056 Basel, Switzerland
| |
Collapse
|
3
|
Gao YQ. Preface: paving the road for AI in molecular sciences. Natl Sci Rev 2023; 10:nwae010. [PMID: 38239561 PMCID: PMC10794898 DOI: 10.1093/nsr/nwae010] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/28/2023] [Accepted: 12/28/2023] [Indexed: 01/22/2024] Open
Affiliation(s)
- Yi Qin Gao
- Beijing National Laboratory for Molecular Sciences, College of Chemistry and Molecular Engineering, Peking University, China
| |
Collapse
|