Melting Temperature Estimation of Imidazole Ionic Liquids with Clustering Methods

Abstract

Ionic liquids (ILs) are ionic compounds with low melting points that can be designed to be used in an extensive set of commercial and industrial applications. However, the design of ILs is limited by the quantity and quality of the available data in the literature; therefore, the estimation of physicochemical properties of ILs by computational methods is a promising way of solving this problem, since it provides approximations of the real values, resulting in savings in both time and money. We studied two data sets of 281 and 134 liquids based on the molecule imidazole that were analyzed with QSPR techniques. This paper presents a software architecture that uses clustering techniques to improve the robustness of estimation models of the melting point of ILs. These results indicate an error of 6.25% in the previously unmodeled data set and an error of 4.43% in the second data set. We have an improvement with the second data set of 1.81% over the last results previously found.

A review on machine learning algorithms for the ionic liquid chemical space

“…al. 90 (2019) noticed that the published works until then on ML for IL property prediction were not signicantly more accurate than classic QSPR methods and hypothesized that this was due to the struggle to deal with many different types of IL families at once. Therefore, they decided to work solely on imidazolium ILs.…”

Ionic Liquids Toxicity—Benefits and Threats

“…The examinations of activities and properties of ILs are cost and time-consuming, that is why some studies have been performed by the theoretical calculations based on quantitative structure-property/structure/activity relationships (QSPR/QSAR). The QSPR model has been proposed for the evaluation of the melting temperature of the imidazolium ILs [ 229 ]. The quantitative structural-activity relationship studies (QSAR) have been used for predicting the toxicity against human HeLa and MCF-7 cancer cell lines [ 230 ], the leukemia rat cell line (IPC-81) [ 231 , 232 ].…”

Ionic Liquid Melting Points: Structure–Property Analysis and New Hybrid Group Contribution Model

“…Many such descriptors are calculated using computationally intensive statistical modeling and quantum chemical methods. Some of the most known examples of these models are COSMO-RS and CODESSA. − More recently, machine learning approaches have been combined with the QSPR approach with improvements achieved in terms of predictive capability. − However, the high computational cost of QSPR methods utilizing quantum-based descriptors, combined with the “black box” nature of machine learning algorithms, still presents a barrier to the scalability of such models for computer-aided molecular design (CAMD) to very large search spaces. An alternative approach is the group contribution method (GCM), which is based on the assumption that the structural functional groups that make up the chemical species make defined contributions toward the overall properties. , As these functional groups can also be descriptors in a QSPR model, GCMs can be considered to be a special case of a QSPR model .…”