Design of CO2-philic molecular units with large language models.
Design of CO2-philic molecular units with large language models.
Konstantinos D. Vogiatzis
TLDR
The capabilities of LLMs for generating novel molecular structures with enhanced CO2 affinity for the development of novel physisorption-based carbon capture technologies are explored and emergent design strategies that aligned with domain knowledge and experimental precedent are showcased.
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.