Molecular fingerprint-based machine learning assisted QSAR model development for prediction of ionic liquid properties

Abstract

Abstract Ionic liquids (ILs) have many applications in, for example, organic synthesis, batteries and drug delivery. In this study, molecular fingerprint (MF) was used to represent ionic liquids (ILs) and was combined with machine learning (ML) to develop quantitative structure-activity relationship (QSAR) models for predicting the refractive index and viscosity of ILs. To demonstrate the effectiveness of this approach, four datasets with different sizes containing different numbers of ILs refractive indexes and viscosity, which were previously used to develop QSAR models by molecular descriptor (MD)-based method and group contribution method (GCM), were employed to develop QSAR models by MF-ML method. The results showed that the models developed by MF-ML showed comparative predictive performance with the MD-based method and GCM for these four datasets, but MF-ML can more quickly obtain the representations of IL within milliseconds. Moreover, the MF-ML models were interpreted by the recently developed shapely additive explanation (SHAP) method. The results showed that the models made the predictions based on the reasonable understanding of how different features affect the related properties of IL, thus building the trustworthiness of MF-ML models. This study offered a new approach with theoretical support to rapidly developing trustful QSAR models to predict the properties of ILs.