High Resolution Image Download MS PowerPoint Slide Artificial intelligence (AI) is rapidly transforming reticular chemistry by enabling more efficient screening, design, and optimization of porous framework materials. To date, these advances have focused primarily on metal–organic frameworks (MOFs), largely because of the availability of extensive structural databases. As enthusiasm and resources increasingly converge on digitally enabled MOF discovery, covalent organic frameworks (COFs) remain comparatively underrepresented in AI-driven research. This imbalance reflects not only the relative scarcity of large, standardized COF datasets but also challenges associated with covalent linkage chemistry, layer stacking, crystallinity, and synthetic accessibility. COFs have robust covalent structures, high porosity, and modular design, which support a wide range of chemical and biological applications, including gas separation, catalysis, energy storage, optoelectronics, and drug delivery. In this Perspective, we assess the current use of AI in studying different applications of COFs, discuss the main challenges that limit its broader adoption, and highlight future opportunities for integrating AI into the COF field to significantly accelerate materials design, discovery, synthesis, and property optimization.
Aksu et al. (Fri,) studied this question.