Data underlying the chapter: Performance of Meta's Universal Model for Atoms Across the Conformational and Configurational Space of Diverse Transition-Metal Catalysts

We used Meta's Machine Learning Interatomic Potential (MLIP) UMA to evaluate how well it reproduces the energy rankings as calculated by DFT. The code to redo the calculations using UMA and to redo statistical analysis are present next to all used molecular structures.

我们采用Meta开发的机器学习原子间势（Machine Learning Interatomic Potential，MLIP）UMA，以评估其复现由密度泛函理论（Density Functional Theory，DFT）计算所得能量排序结果的能力。所有已使用的分子结构旁均附带了可复现UMA计算与统计分析的代码。