QSPR-based calculation model for stability constants of new metal-thiosemicarbazone complexes with hybrid techniques

Abstract

In the present study, we calculated the logb₁₂ stability constant of twenty new ML₂ complexes between thiosemicarbazone and metal ions based on the modelling techniques of the quantitative structure and property relationship (QSPR). The QSPR models were developed by combining the genetic algorithm (GA) with multivariate linear regression techniques (QSPR_GA-MLR), support vector regression (QSPR_GA-SVR), and artificial neural network (QSPR_GA-ANN). The descriptive parameters were calculated from semi-empirical quantum computation with the new versions PM7 and PM7/sparkle. The resulting QSPR_GA-MLR models had three variables, and the QSPR_GA-SVR and QSPR_GA-ANN models were developed from the variables of the QSPR_GA-MLR model. The results show that the best QSPR_GA-SVR model had the following optimal parameters: C = 10.0; g = 0.333; e = 0.10 with 51 support vectors, and a QSPR_GA-ANN model with the network architecture I(3)-HL(10)-O(1) was successfully developed. Furthermore, the quality of QSPR models conformed to statistical values ​​according to OECD principles and Tropsha’s criteria.