Performance of Meta’s Universal Model for Atoms across the Conformational and Configurational Space of Diverse Transition-Metal Catalysts

Machine Learning Interatomic Potentials (MLIPs) promise to transform computational catalysis by delivering near-density functional theory (DFT) accuracy at a fraction of the computational cost. Here, we evaluate the Universal Machine Learning Potential for Atoms (UMA) on two data sets of transition-metal complexes. UMA enables high-throughput evaluations in seconds per structure on consumer-grade GPUs. Analysis of per-ligand Spearman rank correlations (ρ > 0.6, <i>p</i> < 0.05) reveals variability in ranking reliability that is not captured by aggregate metrics such as <i>R</i>² or RMSE. However, these inaccuracies are shown to mainly occur in the near-DFT accuracy regime where these complexes are practically indistinguishable. For square-planar Ni complexes, reliable rankings are obtained for 84% of ligands in rigid Ni-Cl₂ complexes and drop to 53% for flexible asymmetric coordination environments, particularly only when conformers differ by <2 kJ/mol. Data set 2 shows a similar trend, with 61% and 44% reliability for Ru(II) and Mn(I) complexes, respectively, and, as expected, challenges for fluxional systems with small (<5 kJ/mol) relative energy gaps. These findings highlight the promise of MLIPs for both rigid, well-defined systems and highly flexible or fluxional catalysts, while underscoring the need to combine the speed of ML with validation and domain expertise to ensure robust and meaningful chemical insights.