Generative AI-Driven Molecular Design: Combining Predictive Models and Reinforcement Learning for Tailored Molecule Generation

Abstract

Molecular design is a critical aspect of various scientific and industrial fields, where the properties of molecules hold significant importance. In this study, a three-fold methodology design is presented that leverages the power of generative artificial intelligence (AI), predictive modeling, and reinforcement learning to create tailored molecules with desired properties. This model synergistically combines deep learning techniques with Self-Referencing Embedded Strings (SELFIES) molecular representation to build a generative model which generates valid molecules and a graphical neural network model that accurately forecasts molecular properties. The Variational Autoencoder (VAE) coupled with reinforcement learning, helps refine molecule generation based on targeted attributes. Data from an experimental study involving surfactants was used to test the framework. Saliency maps for the generated surfactants were produced to identify the features explaining the property values. The results showed that the proposed framework can effectively produce valid molecules within the set property threshold value. This approach not only streamlines molecular design for surfactant systems but also augurs transformative advancements across different scientific and industrial landscapes.