Using Machine Learning for Green Substitution of Industrial Chemicals: Integrating Functionality, Hazard, and Life Cycle Impact
Haobo Wang, Jingwen Chen, Wenjia Liu, Dailong Wang, Yuhang Song, Huixiao Hong, T. WANG, Paul T. Anastas, Julie B. Zimmerman
Abstract
Industrial chemicals are characterized by their substantial production volumes, widespread applications, fugitive release into the environment, and the general lack of full awareness regarding their risks, carrying global unintended adverse effects on human and ecological health. In the ongoing pursuit of more sustainable and less hazardous industrial chemicals, a tremendous body of research has been developed. However, reliance on empirical molecular design based solely on human knowledge and expertise may not be adequate for avoiding regrettable substitution. Recent advances in generative machine learning (ML) technologies, and their applications in ML-assisted molecular design, possess immense promise to bring innovative solutions for green substitution of hazardous industrial chemicals. This review outlines the methodologies of ML-assisted molecular design and proposes design strategies for green alternative chemicals that possess both necessary functionalities and low environmental hazards throughout their life cycles. Additionally, case examples are provided to illustrate the methodologies and highlight areas that warrant further research, including the development of AI agents for both chemical risk management and green substitution. Applications of the methodologies can yield a sustainable and responsible way that both promotes the benefits of industrial chemicals and simultaneously minimizes their adverse impacts on humans and the environment.