Abstract
The QM9 dataset [Scientific Data, Vol. 1, 140022 (2014)] became a standard dataset to benchmark machine learning methods, especially on molecular graphs. It contains geometries as well as multiple computed molecular properties of 133,885 compounds at B3LYP/6-31G(2df,p) level of theory, including frontier orbitals (HOMO and LUMO) energies. However, the accuracy of HOMO/LUMO predictions from density functional theory, including hybrid methods such as B3LYP, is limited for many applications. In contrast, the GW method significantly improves HOMO/LUMO prediction accuracy, with mean unsigned errors in the GW100 benchmark dataset of 100 meV. In this work, we present a new dataset of HOMO/LUMO energies for the QM9 compounds, computed using the GW method. This database may serve as a benchmark of HOMO/LUMO prediction, delta-learning, and transfer learning, particularly for larger molecules where GW is the most accurate but still numerically feasible method. We expect this dataset to enable the development of more accurate machine learning models for predicting molecular properties