QSPR modeling of polychlorinated biphenyls using degree-based molecular descriptors: a comparative study with linear, polynomial, and ridge regression

Key Points

• The analysis reveals that regression models can effectively predict the properties of polychlorinated biphenyls, enhancing chemical understanding.
• Through this approach, different regression techniques, including linear and ridge regression, provide insights into molecular descriptor relationships.
• Employing degree-based molecular descriptors, this study models polychlorinated biphenyls' characteristics effectively.
• The findings suggest that method choice impacts predictive accuracy, highlighting the need for careful model selection.