Accurate Hydration Free Energy Calculations for Diverse Organic Molecules With a Machine Learning Force Field

Free
energy perturbation (FEP) calculations using classical force
fields remain the dominant approach for large-scale, computational
drug discovery efforts, but the accuracy is fundamentally limited
by simplified forms that cannot quantitatively reproduce ab
initio methods without significant fine-tuning. Machine Learning
force fields (MLFFs) offer a promising avenue to retain quantum mechanical
accuracy with significantly reduced computational cost compared with ab initio molecular dynamics (AIMD) simulations. Thus far,
direct applications of ML force fields to FEP calculations lack systematic
protocols and extensive benchmarking. In this work, we take a step
in this direction by presenting a general and robust workflow for
solvation (hydration) free energy (HFE) calculations which is independent
of the details of the particular MLFF architecture used. Combining
a broadly trained ML force field, Organic_MPNICE, with sufficient
statistical and conformational sampling empowered by the solute-tempering
technique, affords sub-kcal/mol average errors in HFE predictions
relative to experimental estimates. This approach outperforms state-of-the-art
classical force fields and DFT-based implicit solvation models on
a diverse set of 59 organic molecules and provides a route to ab initio-quality HFE predictions, advancing the use of
ML force fields in thermodynamic property prediction.

采用经典力场开展的自由能微扰（Free Energy Perturbation, FEP）计算，仍是大规模计算药物研发工作的主流方法，但其精度本质上受限于简化的形式：若不经过大量微调，无法定量复现从头算方法的计算结果。机器学习力场（Machine Learning Force Fields, MLFFs）提供了极具前景的解决方案：相较于从头算分子动力学（Ab Initio Molecular Dynamics, AIMD）模拟，其可在显著降低计算成本的同时保留量子力学精度。迄今为止，将机器学习力场直接应用于自由能微扰计算仍缺乏系统性的标准化流程与广泛的基准验证。本研究为此迈出了关键一步：提出了一套通用且稳健的溶剂化（水合）自由能（Solvation (Hydration) Free Energy, HFE）计算工作流，该流程与所使用的特定机器学习力场架构细节无关。本工作结合经过充分预训练的机器学习力场Organic_MPNICE，以及依托溶质调温（Solute-tempering）技术实现的充足统计采样与构象采样，使得水合自由能预测结果相较于实验估值的平均误差达到亚千卡每摩尔级别。该方法在涵盖59种有机分子的多样化基准测试集上，性能优于当前最优的经典力场与基于密度泛函理论（Density Functional Theory, DFT）的隐式溶剂化模型，为获得从头算级别的水合自由能预测结果提供了可行路径，进一步推动了机器学习力场在热力学性质预测领域的应用。