Metal–organic frameworks (MOFs) are among the most structurally diverse classes of crystalline nanomaterials, offering exceptional tunability, porosity, and chemical modularity. These characteristics have positioned MOFs as promising platforms for nanomedicine, bioimaging, and integrated nanotheranostic applications. However, the rational design of MOFs that satisfy stringent biomedical requirements, including high drug loading capacity, controlled and stimuli responsive release, selective targeting, physiological stability, biodegradability, and multimodal imaging capability, remains challenging due to the vast combinatorial design space and the complex interplay between physicochemical properties and biological responses. The objective of this review is to critically examine recent advances in artificial intelligence approaches based on Transformer architectures for the design and optimization of MOFs aimed at next-generation nanotheranostics. In contrast to prior reviews that broadly survey machine learning methods for MOF research, this article focuses specifically on Transformer-based models and their ability to capture long-range, hierarchical, and multiscale relationships governing MOF structure, chemistry, and functional behavior. We review state-of-the-art models, including MOFormer, MOFNet, MOFTransformer, and Uni MOF, and discuss graph-based and sequence-based representations used to encode MOF topology and composition. This review highlights how Transformer-based models enable predictive assessment of properties directly relevant to nanotheranostic performance, such as adsorption energetics, framework stability, diffusion pathways, pore accessibility, and surface functionality. By explicitly linking these predictive capabilities to drug delivery efficiency, imaging performance, targeted therapeutic action, and combined diagnostic and therapeutic applications, this work delineates the specific contribution of Transformer-based artificial intelligence to biomedical translation. Finally, we discuss emerging opportunities and remaining challenges, including generative Transformer models for inverse MOF design, self-supervised learning on hybrid experimental and computational datasets, and integration with autonomous synthesis and screening workflows. By defining the scope, novelty, and contribution of Transformer-based design strategies, this review provides a focused roadmap for accelerating the development of MOF-based platforms for next-generation nanotheranostics.
Rodríguez et al. (Fri,) studied this question.