Predicting melting point of ionic liquids using QSPR approach: Literature review and new models

Quantitative structure-property relationships (QSPRs) for predicting melting point temperature (T-m) of ionic liquids (ILs) are reviewed and the new models are proposed by using the experimental data extracted from the literature for 953 salts. The models include both regression of T-m data and classification of the ILs with respect to their state of matter (liquid/solid) at T = 300 K. A variety of machine learning algorithms is applied, including: partial least squares regression, stepwise multiple linear regression, and a number of common classifiers (k-nearest neighbors, naive Bayes, linear discriminant analysis, support vector machines). An effect of the molecular descriptors set as well as the computational level used for the ions' geometry optimization is analyzed and followed in the final model selection protocol, which comprises all the standard steps of good practice of QSRP modeling, e.g. cross-validation, external validation, and the applicability domain analysis. Furthermore, as a key novelty, the robustness of the models is checked for different combining rules, defined as the averaging functions for obtaining the descriptors of ILs from those given for individual ions. The finally selected and recommended models are discussed in detail in terms of various statistics, as well as addressed to other methods reported in the literature. An effect of the chemical family of both cation and anion on the modeling performance is highlighted. Additionally, the predictions of both T-m and state of matter of more than 35, 000 virtual cation-anion combinations are given in order to present the range of potential applications of the new methods in computer-aided molecular design of new ILs displaying demanded phase behavior. (C) 2021 The Authors. Published by Elsevier B.V.

Automated summary

The article reviews quantitative structure-property relationships for predicting melting point temperature of ionic liquids and proposes new models using experimental data for 953 salts. A variety of machine learning algorithms are applied, including regression and classification methods.