Efficient and Precise Force Field Optimization for Biomolecules Using DPA-2

TL;DR

This paper presents a novel method that leverages a fine-tuned DPA-2 model combined with a node-embedding similarity metric to optimize force fields for biomolecules efficiently, reducing computational costs and improving accuracy.

Contribution

It introduces a new approach for on-the-fly force field optimization using a pre-trained DPA-2 model and a similarity metric, enabling seamless adaptation to new chemical species.

Findings

Improved free energy perturbation calculation accuracy.

Reduced computational costs in force field optimization.

Effective application to TYK2 inhibitor and PTP1B systems.

Abstract

Molecular simulations are essential tools in computational chemistry, enabling the prediction and understanding of molecular interactions and thermodynamic properties of biomolecules. However, traditional force fields face significant challenges in accurately representing novel molecules and complex chemical environments due to the labor-intensive process of manually setting optimization parameters and the high computational cost of quantum mechanical calculations. To overcome these difficulties, we fine-tuned a high-accuracy DPA-2 pre-trained model and applied it to optimize force field parameters on-the-fly, significantly reducing computational costs. Our method combines this fine-tuned DPA-2 model with a node-embedding-based similarity metric, allowing seamless augmentation to new chemical species without manual intervention. We applied this process to the TYK2 inhibitor and PTP1B systems and demonstrated its effectiveness through the improvement of free energy perturbation calculation results. This advancement contributes valuable insights and tools for the computational chemistry community.