Computer-Aided MOLECULAR Design: Methodology & APPLICATIONS

The demand for newly-designed molecules that enhance existing processes and satisfy more stringent operating requirements in technology has been increasing. However, the design of molecules with desired properties challenges engineers attempting to meet the needs of various industries, including pharmaceuticals, polymers, petrochemicals and construction. The traditional approach of identifying molecules with desired properties involves testing thousands of molecules for their chemical and physical properties, which is an expensive and laborious undertaking. Hence, design techniques, such as computer-aided molecular design (CAMD), have found wide application in recent years.

In this work, an automated CAMD technique that combines genetic algorithms (GAs) as the search tool and three-dimensional non-linear quantitative structure-property relationship (QSPR) models as the prediction platform was developed. Specifically, evolutionary algorithms (EAs) in combination with artificial neural networks (ANNs) were used to select the most significant molecular descriptor inputs to the QSPR models, while identifying simultaneously the optimal model architecture. The developed CAMD methodology was validated using different applications. Herein, we report our findings on the design of novel chemical penetration enhancers (CPEs) for enhancing insulin permeation.