A Computational Approach to Predictive Modeling Using Connection-Based Topological Descriptors: Applications in...

Cheminformatics bridges chemistry, computer science, and information technology to predict chemical behaviors using quantitative structure-property relationships (QSPRs). This study advances QSPR modeling by introducing novel connection-based graphical invariants, specifically designed to enhance the predictive accuracy for physicochemical properties (PCPs) of benzenoid hydrocarbons (BHs). Employing cutting-edge computational methods, we evaluate these invariants against established descriptors in modeling the normal boiling point and standard heat of formation. The findings reveal superior predictive performance by newly proposed invariants, such as the sum-connectivity connection index, outperforming traditional indices like the Zagreb connection indices. Furthermore, we extend these methods to model the physicochemical properties of coumarin-related anti-cancer drugs, demonstrating their potential in drug development. The statistical analysis suggests that the most appropriate structure-property models are nonlinear. This work not only proposes robust tools for PCP estimation but also advocates for rigorous testing of descriptors to ensure relevance in cheminformatics.