摘要：Non-ionic deep eutectic solvents(DESs)are non-ionic designer solvents with various applications in catalysis,extraction,carbon capture,and ***,discovering new DES candidates is challenging due to a lack of efficient tools that accurately predict DES *** search for DES relies heavily on intuition or trial-and-error processes,leading to low success rates or missed *** 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 *** first analyze the HB properties of 38 known DES and 111 known non-DES systems using their molecular dynamics(MD)simulation *** analysis reveals that DES systems have two unique features compared to non-DES systems:The DESs have①more imbalance between the numbers of the two intra-component HBs and②more and stronger inter-component *** on these results,we develop 30 ML models using ten algorithms and three types of HB-based *** model performance is first benchmarked using the average and minimal receiver operating characteristic(ROC)-area under the curve(AUC)*** also analyze the importance of individual features in the models,and the results are consistent with the simulation-based statistical ***,we validate the models using the experimental data of 34 *** extra trees forest model outperforms the other models in the validation,with an ROC-AUC of *** work illustrates the importance of HBs in DES formation and shows the potential of ML in discovering new DESs.