Design of CO2-philic molecular units with large language models

Abstract

The integration of large language models (LLMs) into chemical sciences presents a transformative approach for molecular design. In this study, we explore the capabilities of LLMs for generating novel molecular structures with enhanced CO₂ affinity for the development of novel physisorption-based carbon capture technologies. By integrating LLM-generated candidates with DFT-based evaluation, we identified promising physisorption agents and highlighted the synergy between AI and expert-guided chemical research. Notably, LLM-generated structures showcased emergent design strategies, such as cooperative binding motifs, that aligned with domain knowledge and experimental precedent.