GEMS -- Guided Evolutionary Molecule Design for Sustainable Chemicals

2026-05-15

AI Summary

This work addresses the challenges in designing environmentally benign chemicals, which are hindered by sparse environmental impact data and the inability of conventional machine learning scoring functions to encapsulate expert chemical intuition. To overcome these limitations, the authors propose an interactive visual analytics tool that, for the first time, enables domain experts—without requiring programming or machine learning expertise—to dynamically guide a genetic algorithm for molecular generation through real-time feedback. By deeply integrating expert knowledge into the evolutionary optimization process, the approach transcends the constraints of traditional generative models that rely solely on static numerical scores. The system has been successfully applied to the design of sustainable antioxidant alternatives and has received positive evaluations from domain scientists regarding its practicality and effectiveness.

Abstract

Designing safe and sustainable chemicals is critical to combat chemical pollution in our environment. Machine learning (ML) methods have been developed to aid with de novo molecule design. However, data on the environmental impacts of chemical compounds are sparse, resulting in low-fidelity ML oracles and unreliable candidate proposals. Furthermore, generative ML models rely on numerical scoring functions that cannot fully capture the nuanced chemical intuition of expert scientists required for real-world molecular design. We present GEMS-an interactive visual analytics tool that enables domain experts to directly collaborate with a genetic algorithm for molecule design. Users can integrate their expert knowledge to guide the evolutionary process by modifying the scoring function and molecule population without programming knowledge or ML developer support. A usage scenario demonstrates the system's application in designing sustainable antioxidant alternatives. In an interview session with domain scientists, we collected feedback on the usefulness of GEMS.

Problem

• sustainable chemicals
• molecule design
• machine learning
• chemical pollution
• expert knowledge

Innovation

• interactive visual analytics
• guided evolutionary algorithm
• de novo molecule design
• sustainable chemicals
• expert-in-the-loop