CaTS: Toward Scalable and Efficient Transition State Screening for Catalyst Discovery

Large-scale screening of materials via machine learning is emerging as an effective strategy for accelerating scientific discovery and industrial applications. Machine learning methods for transition state (TS)-based screening for catalysts remain underexplored due to the scarcity of TS data sets and the inherent challenges of TS searching tasks. Here, we present a framework for large-scale transition states screening for catalysts (CaTS), which uniquely bridges microscopic reaction kinetics and macroscopic computational efficiency by leveraging TS energy, a mechanistically rigorous yet computationally prohibitive descriptor. CaTS integrates automated structure generation with a machine learning force field-based nudged elastic band (NEB) method, enabling high-throughput TS exploration at 104 the speed of density functional theory (DFT). Initially optimized and validated on a small-molecule TS database comprising 10,000 reactions (achieving sub-0.2 eV errors in TS energy prediction) and further applied to a metal–organic complex catalyst (0.16 eV MAE with only 327 training samples), CaTS achieves DFT-level accuracy at 0.01% computational cost. Scaling to over 1000 unseen metal–organic complex structures, it identifies top candidates validated by rigorous DFT. AI-assisted analysis using ChatGPT o3 and SHAP confirms that the predictions are consistent with mechanistic heuristics, providing theoretical validation for large-scale prediction. This paradigm shift from static descriptors to kinetic-resolution screening enables industrial-scale catalyst discovery with atomistic precision.