Chemometric Versus Random Forest Predictors of Ionic Liquid Toxicity

The objective of this work is comparative analysis of standard chemometric and decision tree(s) models for prediction of biological impact of ionic liquids (ILs) for various combinations of cations and anions. The models are based on molecular descriptors for combinations of the following cations: imidazole, pyridinium, quinolinium, ammonium, phosphonium; and anions: BF4, Cl, PF6, Br, CFNOS, NCN2, C6F18PBF4, Cl, PF6, Br, CFNOS, C6F18P. Derived data matrix is decomposed by singular value decomposition of the cation and anion matrices into corresponding first ten components each accounting for 99,5 % of the corresponding total variances. Biological impact data, i.e. molecular level toxicity, are based on acetylcholinestarase inhibition experimental data provided in MERCK Ionic Liquids Biological Effects Database. Applied are the following models: principal component regression (PCR), partial least squares (PLS), and decision tree(s) model. The model performances are compared by ten fold validation. Obtained are the following Pearson regression coefficients R-2: PCR 0.62, PLS 0.64, and for decision tree forest RFDT 0.992. The decision tree(s) models significantly outperformed chemometric models for numerical predictions of E-50 concentrations and the classification of ILs into four level of toxicities.