Deep Residual Learning for Molecular Force Fields
Preprint
- 22 October 2025
- preprint
- Published by American Chemical Society (ACS) in ChemRxiv
Abstract
Accurate interatomic interaction modeling via force fields is critical for biological studies and drug discovery, but balancing accuracy and generalizability remains challenging. We introduce ResFF (Residual Learning Force Field), a hybrid machine learning force field that employs deep residual learning to integrate physics-based learnable molecular mechanics covalent terms with residual corrections from a lightweight equivariant neural network. Through a three-stage joint optimization, the two components are trained in a complementary manner to achieve optimal performance. Benchmarks show ResFF outperforms classical and neural network force fields in generalization (mean absolute error (MAE): 1.16 kcal/mol on Gen2-Opt, 0.90 kcal/mol on DES370K), torsional profiles (MAE: 0.45/0.48 kcal/mol on TorsionNet-500 and Torison Scan), and intermolecular interactions (MAE: 0.32 kcal/mol on S66×8). It also enables precise energy minima reproduction and stable molecular dynamics of biological systems. ResFF merges physical constraints with neural expressiveness, offering a robust tool for accurate and efficient molecular simulation.Keywords
All Related Versions
This publication has 71 references indexed in Scilit:
- Studying Noncovalent Interactions in Molecular Systems with Machine LearningChemical Reviews, 2025
- The emergence of machine learning force fields in drug designMedicinal Research Reviews, 2024
- LAMMPS - a flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scalesComputer Physics Communications, 2022
- Recent progress in general force fields of small moleculesCurrent Opinion in Structural Biology, 2021
- Machine Learning Force FieldsChemical Reviews, 2021
- The MolSSI QCArchive project: An open‐source platform to compute, organize, and share quantum chemistry dataWIREs Computational Molecular Science, 2020
- The good, the bad and the twisted: a survey of ligand geometry in protein crystal structuresJournal of Computer-Aided Molecular Design, 2012
- CHARMM general force field: A force field for drug‐like molecules compatible with the CHARMM all‐atom additive biological force fieldsJournal of Computational Chemistry, 2009
- Long-timescale molecular dynamics simulations of protein structure and functionCurrent Opinion in Structural Biology, 2009
- Automatic atom type and bond type perception in molecular mechanical calculationsJournal of Molecular Graphics and Modelling, 2006