tmQMg Δ-ML graphs

This dataset contains graph representations of 73,821 unique transition metal complexes from the tmQMg dataset ready for use in Δ-machine learning frameworks. The graph representations were generated with the HyDGL Python package according to the u-NatQG specification and are based on electronic structure data at two different levels of theory: 

1. Geometry optimization: GFN2-xTB // Single-point refinement: PBE0-D3BJ/def2-TZVP (low-fidelity)
2. Geometry optimization: GFN2-xTB // Single-point refinement: LSDA/LANL2DZ (ultra-low-fidelity)

The corresponding benchmark graphs obtained in previous work are also supplied (high-fidelity). The target properties calculated at the high-, low- and ultra-low-fidelity levels of theory are additionally provided in a separate CSV file.