Graph-Theoretical Approach for Predicting Physicochemical Properties of Stiff-Person Syndrome Drugs.

This work applies quantitative structure-property relationship analysis to examine molecular characteristics linked to stiffness person syndrome (SPS), a rare neurological condition marked by persistent muscle rigidity and spasmodic episodes. Topological indices such as Zagreb indices and their modification are employed to examine their correlations with key physicochemical properties. Linear, quadratic, exponential growth, and power curve fitting models are applied to identify the best correlations, focusing on the maximum F-statistic and the coefficient of determination R2. Furthermore, heatmap-based correlation analysis is performed to visually quantify the strength and direction of correlations between the calculated topological indices and selected physicochemical parameters. In addition to classical regression techniques, gradient boosting, a powerful ensemble machine learning method, is utilized to enhance predictive accuracy and evaluate the contribution of each descriptor toward property estimation. Additionally, M-polynomials are calculated, and their corresponding graphs are plotted to assess the structural features of potential therapeutic agents. The findings offer significant insights into the role of graph-theoretical methods in drug discovery, advancing the computational design of targeted treatments for SPS.