Artificial intelligence (AI) techniques for scientific discovery have gained increasing interest across machine learning (ML), physics, chemistry, material, and biology communities. A central challenge in AI-driven scientific discovery is effective molecular search and design, as molecules form the fundamental building blocks of chemical compounds and biological systems. These molecules can be naturally represented through various modalities, including chemical formulas, molecular graphs, geometric conformations, knowledge graphs, and textual literature.

Shengchao’s research focuses on leveraging multimodal information to develop a physics-inspired foundation model. To assess its effectiveness, he outlines and applies two key paradigms. The first involves employing physics-inspired AI (PhysAI) models to accelerate established scientific discovery processes, such as molecular dynamics simulations and molecule crystallization. The second paradigm integrates the reasoning and planning capabilities of generative AI (GenAI) models to explore novel approaches, including text-guided lead optimization, protein engineering, and material design. By bridging AI and physics in chemistry, biology, and materials science, Shengchao’s work provides a transformative vision for AI-driven scientific discovery, paving the way for groundbreaking innovations that empower scientists and accelerate progress across disciplines.