English

Data-Driven Parametrization of Molecular Mechanics Force Fields for Expansive Chemical Space Coverage

Machine Learning 2024-10-10 v2 Chemical Physics

Abstract

A force field is a critical component in molecular dynamics simulations for computational drug discovery. It must achieve high accuracy within the constraints of molecular mechanics' (MM) limited functional forms, which offers high computational efficiency. With the rapid expansion of synthetically accessible chemical space, traditional look-up table approaches face significant challenges. In this study, we address this issue using a modern data-driven approach, developing ByteFF, an Amber-compatible force field for drug-like molecules. To create ByteFF, we generated an expansive and highly diverse molecular dataset at the B3LYP-D3(BJ)/DZVP level of theory. This dataset includes 2.4 million optimized molecular fragment geometries with analytical Hessian matrices, along with 3.2 million torsion profiles. We then trained an edge-augmented, symmetry-preserving molecular graph neural network (GNN) on this dataset, employing a carefully optimized training strategy. Our model predicts all bonded and non-bonded MM force field parameters for drug-like molecules simultaneously across a broad chemical space. ByteFF demonstrates state-of-the-art performance on various benchmark datasets, excelling in predicting relaxed geometries, torsional energy profiles, and conformational energies and forces. Its exceptional accuracy and expansive chemical space coverage make ByteFF a valuable tool for multiple stages of computational drug discovery.

Keywords

Cite

@article{arxiv.2408.12817,
  title  = {Data-Driven Parametrization of Molecular Mechanics Force Fields for Expansive Chemical Space Coverage},
  author = {Tianze Zheng and Ailun Wang and Xu Han and Yu Xia and Xingyuan Xu and Jiawei Zhan and Yu Liu and Yang Chen and Zhi Wang and Xiaojie Wu and Sheng Gong and Wen Yan},
  journal= {arXiv preprint arXiv:2408.12817},
  year   = {2024}
}

Comments

ByteFF, a machine learning parametrized MMFF. Code available at https://github.com/bytedance/byteff

R2 v1 2026-06-28T18:21:38.821Z