Computational and AI-Assisted Rational Design of MOF-Based Catalysts for DCPD Hydrogenation
Metal–organic frameworks (MOFs) have emerged as versatile platforms for heterogeneous catalysis, owing to their structural tunability, well-defined active sites, and tailorable pore environments. Achieving efficient hydrogenation of complex molecules under mild conditions, however, remains challenging because the catalytic performance is highly sensitive to the local electronic and structural microenvironment of active sites. The stepwise hydrogenation of dicyclopentadiene (DCPD), which involves multiple unsaturated bonds and competing reaction pathways, provides a representative model system for elucidating these structure–activity relationships. Over the past decade, MOF-based catalysts, including pristine frameworks, single-atom catalysts (SACs), and nanocluster/nanoparticle-loaded systems, have shown significant potential for hydrogenation reactions. Nevertheless, rational catalyst design remains difficult because framework topology, electronic structure, defect distribution, and metal–support interactions are strongly coupled across multiple length scales. As a result, establishing generalizable design principles through empirical approaches alone can be challenging. In this Account, we present an integrated strategy for the rational design of MOF-based catalysts for DCPD hydrogenation by combining computational chemistry with artificial intelligence (AI). This framework bridges atomistic-level mechanistic understanding with synthesis optimization, enabling precise control of the catalytic performance. At the atomic and electronic levels, density functional theory (DFT) calculations and descriptor-based analyses reveal key mechanistic factors governing hydrogen activation, charge redistribution, and reaction energetics. These studies guide the rational design of frustrated Lewis pairs (FLPs) in pristine MOFs through the optimization of charge distributions for heterolytic H2 cleavage. Extending this concept to SACs, electronic structure engineering demonstrates how metal–support interactions and d-band modulation regulate the adsorption behavior and reaction pathways. At larger scales, investigations of nanometer clusters and nanoparticle-loaded systems further highlight the critical role of interfacial electronic structures, including electron transfer and hydrogen spillover, in enhancing the catalytic activity. Complementing these mechanistic insights, machine learning (ML) and large language model (LLM) driven approaches are employed to address the complexity of MOF synthesis. Data-driven models efficiently explore high-dimensional synthetic parameter spaces, enabling defect engineering and multiobjective optimization of catalytic properties. Furthermore, the integration of LLMs with retrieval-augmented generation (RAG) supports closed-loop synthesis frameworks in which the experimental design, data analysis, and knowledge extraction are autonomously coordinated. These AI-assisted methodologies significantly accelerate catalyst optimization and the precise regulation of active-site structures. Through this integrated computational and AI-assisted strategy, MOF-based catalysts achieve complete conversion and high selectivity for DCPD hydrogenation under mild conditions. More broadly, this work establishes a generalizable paradigm in which mechanistic modeling and data-driven methodologies are synergistically integrated to guide the rational design of heterogeneous catalysts.