Novel QSPR modeling of stability constants of metal-thiosemicarbazone complexes by hybrid multivariate technique: GA-MLR, GA-SVR and GA-ANN

Abstract

The quantitative structural property relationship (QSPR) models of the logβ11 stability constants of M:L complexes of the structurally diverse thiosemicarbazones and several metal ions (M = Ag+, Cd2+, Co2+, Cu2+, Fe3+, Mn2+, Cr3+, La3+, Mg2+, Mo6+, Nd3+, Ni2+, Pb2+, Zn2+, Pr3+, Dy3+, Gd3+, Ho3+, Sm3+, Tb3+, V5+) in aqueous solution have been constructed by combining the genetic algorithm with multivariate linear regression (QSPRGA-MLR), support vector regression (QSPRGA-SVR) and artificial neural network (QSPRGA-ANN). The multi-levels optimization for grid search technique is used to find the best QSPRGA-SVR model with the optimized parameters capacity C = 1.0, Gamma, γ = 1.0 and Epsilon, ε = 0.1. The quality of the QSPR models presented in statistical values as training R2 in range 0.9148–0.9815, validation Q2 in range 0.7168–0.9669 and MSE values in range 0.2742–2.4906. The new two thiosemicarbazone reagents were designed and synthesized based on the lead thiosemicarbazone reagents. The logβ11 values of new complexes Cu2+L, Ni2+L, Cd2+L and Zn2+L derived from the QSPRGA-SVR and QSPRGA-ANN model turn out to be in a good agreement with experimental data.