Here, we investigate the performance of “Accurate NeurAl networK engINe for Molecular Energies” (ANI), trained on small organic compounds, on bulk systems including non-covalent interactions and applicability to estimate solvation (hydration) free energies using the interaction between the ligand and explicit solvent (water) from single-step MD simulations. The method is adopted from ANI using the Atomic Simulation Environment (ASE) and predicts the non-covalent interaction energies at the accuracy of wb97x/6-31G(d) level by a simple linear scaling for the conformations sampled by molecular dynamics (MD) simulations of ligand-n(H₂O) systems. For the first time, we test ANI potentials' abilities to reproduce solvation free energies using linear interaction energy (LIE) formulism by modifying the original LIE equation. Our results on ~250 different complexes show that the method can be accurate and have a correlation of R² = 0.88–0.89 (MAE <1.0 kcal/mol) to the experimental solvation free energies, outperforming current end-state methods. Moreover, it is competitive to other conventional free energy methods such as FEP and BAR with 15-20 × fold reduced computational cost.

中文翻译：

---

配体-n(H2O) 相互作用能的 ANI-ML 势的性能和端点 MD 模拟中水合自由能的估计

在这里，我们研究了“精确的分子能量神经网络引擎”(ANI) 的性能，该引擎在小型有机化合物、本体系统（包括非共价相互作用）和使用配体之间的相互作用来估计溶剂化（水合）自由能的适用性上进行了训练和来自单步 MD 模拟的显式溶剂（水）。该方法采用原子模拟环境 (ASE) 的 ANI，通过对分子动力学 (MD) 采样的构象进行简单的线性缩放，以 wb97x/6-31G(d) 水平的精度预测非共价相互作用能配体-n(H ₂O）系统。我们首次通过修改原始 LIE 方程，使用线性相互作用能 (LIE) 公式测试 ANI 势再现溶剂化自由能的能力。 我们对约 250 种不同复合物的结果表明，该方法可以是准确的，并且与实验溶剂化自由能的相关性为R ^{2 = 0.88–0.89（MAE <1.0 kcal/mol），优于当前的最终状态方法。}此外，它与 FEP 和 BAR 等其他传统自由能方法相比具有竞争力，计算成本降低了 15-20 倍。