Non-ionic deep eutectic solvents (DESs) are non-ionic designer solvents with various applications in catalysis, extraction, carbon capture, and pharmaceuticals. However, discovering new DES candidates is challenging due to a lack of efficient tools that accurately predict DES formation. The search for DES relies heavily on intuition or trial-and-error processes, leading to low success rates or missed opportunities. Recognizing that hydrogen bonds (HBs) play a central role in DES formation, we aim to identify HB features that distinguish DES from non-DES systems and use them to develop machine learning (ML) models to discover new DES systems. We first analyze the HB properties of 38 known DES and 111 known non-DES systems using their molecular dynamics (MD) simulation trajectories. The analysis reveals that DES systems have two unique features compared to non-DES systems: The DESs have ① more imbalance between the numbers of the two intra-component HBs and ② more and stronger inter-component HBs. Based on these results, we develop 30 ML models using ten algorithms and three types of HB-based descriptors. The model performance is first benchmarked using the average and minimal receiver operating characteristic (ROC)-area under the curve (AUC) values. We also analyze the importance of individual features in the models, and the results are consistent with the simulation-based statistical analysis. Finally, we validate the models using the experimental data of 34 systems. The extra trees forest model outperforms the other models in the validation, with an ROC-AUC of 0.88. Our work illustrates the importance of HBs in DES formation and shows the potential of ML in discovering new DESs.

中文翻译：

---

基于未发现的氢键模式的深度共晶溶剂的机器学习辅助设计


非离子低共熔溶剂 (DES) 是非离子设计溶剂，在催化、萃取、碳捕获和制药领域具有多种应用。然而，由于缺乏准确预测 DES 形成的有效工具，发现新的 DES 候选者具有挑战性。 DES 的搜索在很大程度上依赖于直觉或试错过程，导致成功率低或错失机会。认识到氢键 (HB) 在 DES 形成中发挥核心作用，我们的目标是识别区分 DES 与非 DES 系统的 HB 特征，并使用它们开发机器学习 (ML) 模型以发现新的 DES 系统。我们首先使用分子动力学 (MD) 模拟轨迹分析 38 个已知 DES 和 111 个已知非 DES 系统的 HB 特性。分析表明，与非 DES 系统相比，DES 系统有两个独特的特征：DES 的①两个组件内 HB 的数量之间更加不平衡；②更多且更强的组件间 HB。基于这些结果，我们使用十种算法和三种基于 HB 的描述符开发了 30 个 ML 模型。首先使用平均和最小接收者操作特征 (ROC) 曲线下面积 (AUC) 值对模型性能进行基准测试。我们还分析了模型中各个特征的重要性，结果与基于模拟的统计分析一致。最后，我们使用 34 个系统的实验数据验证了模型。额外树木森林模型在验证中优于其他模型，ROC-AUC 为 0.88。我们的工作说明了 HB 在 DES 形成中的重要性，并展示了机器学习在发现新 DES 方面的潜力。