Premium
Estimation of Ionic Liquids Toxicity against Leukemia Rat Cell Line IPC‐81 based on the Empirical‐like Models using Intuitive and Explainable Fingerprint Descriptors
Author(s) -
Wu Ting,
Li Wanli,
Chen Mengyao,
Zhou Yanmei,
Zhang Qingyou
Publication year - 2020
Publication title -
molecular informatics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.481
H-Index - 68
eISSN - 1868-1751
pISSN - 1868-1743
DOI - 10.1002/minf.202000102
Subject(s) - cheminformatics , ionic liquid , quantitative structure–activity relationship , test set , applicability domain , molecular descriptor , linear regression , computer science , chemistry , measure (data warehouse) , fingerprint (computing) , biological system , data mining , computational chemistry , machine learning , artificial intelligence , organic chemistry , biology , catalysis
Ionic liquids as green solvents have been paid extensive attention in recent years. However, mostly it is cost and time‐consuming to measure their properties. Thus, theorical methods, especially ultrafast chemoinformatics methods were introduced into these studies. Instead of abstract and complex models in some QSPR studies, in this study, the 2D structural features related to the toxicity of ionic liquids were discussed at first, and then the corresponding intuitive and meaningful descriptors were suggested to construct quantitative chemoinformatics models, finally a multiple linear regression (MLR) based on the empirical‐like models were applied to the estimation of toxicities of 304 ionic liquids. For the test sets, the relationship coefficients reached up to R=0.90. An external test set of 11 ionic liquids collected from other literatures was submitted to the achieved MLR equations, and the satisfactory result (R=0.94) was obtained.