Predicting acetyl cholinesterase enzyme inhibition potential of ionic liquids using machine learning approaches: An aid to green chemicals designing

The ionic liquids (ILs) constitute a group of novel chemicals that have potential industrial applications. Designing of safer ILs is among the priorities of the chemists and toxicologists today. Computational approaches have been considered appropriate methods for prior safety assessment of the chemicals. The present study is an attempt to investigate the chemical attributes of a wide variety of ILs towards their inhibitory potential of acetyl cholinesterase enzyme (AChE) through the development of predictive qualitative and quantitative structure-activity relationship (SAR) models in light of the OECD principles. Here, machine learning based cascade correlation network (CCN) and support vector machine (SVM) SAR models were established for qualitative and quantitative prediction of the AChE inhibition potential of ILs. Diversity and nonlinearity of the considered dataset were evaluated. The CCN and SVM models were constructed using simple descriptors and validated with external data. Predictive power of these SAR models was established through deriving several stringent parameters recommended for QSAR studies. The developed SAR models exhibited better statistical confidence than those in the previously reported studies. The models identified the structural elements of the ILs responsible for the AChE inhibition, and hence could be useful tools in designing of safer and green ILs.