Intermolecular Non-Bonded Interactions from Machine Learning Datasets

• Published in: Molecules (Basel, Switzerland) Vol. 28; no. 23; p. 7900
• Main Authors: Chen, Jia-An, Chao, Sheng D
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 01.12.2023
• Subjects: Accuracy; Algorithms; Analysis; Artificial intelligence; Chemistry; Datasets; Energy; Machine learning; machine learning potentials; Methods; Molecular dynamics; non-bonded interactions; quantum chemistry datasets; Regression analysis; Simulation; symmetry adapted perturbation theory; Iran; machine learning potentials; non-bonded interactions; symmetry adapted perturbation theory; quantum chemistry datasets; artificial intelligence
• ISSN: 1420-3049; 1420-3049
• DOI: 10.3390/molecules28237900

Accurate determination of intermolecular non-covalent-bonded or non-bonded interactions is the key to potentially useful molecular dynamics simulations of polymer systems. However, it is challenging to balance both the accuracy and computational cost in force field modelling. One of the main difficulties is properly representing the calculated energy data as a continuous force function. In this paper, we employ well-developed machine learning techniques to construct a general purpose intermolecular non-bonded interaction force field for organic polymers. The original ab initio dataset SOFG-31 was calculated by us and has been well documented, and here we use it as our training set. The CLIFF kernel type machine learning scheme is used for predicting the interaction energies of heterodimers selected from the SOFG-31 dataset. Our test results show that the overall errors are well below the chemical accuracy of about 1 kcal/mol, thus demonstrating the promising feasibility of machine learning techniques in force field modelling.