Large dataset of molecular and reaction energies from multi-level quantum chemical methods

Well curated extensive datasets have have helped spur intense molecular machine learning(ML) method development activities over last few years encouraging non-chemists to be part of the effort as well. QM9 dataset is the one of the benchmark database for small molecules with molecular energies based on B3LYP functional. G4MP2 based energies of these molecules were published later. To enable a widely variety of ML tasks with QM9 molecules, in this article, we introduce a new dataset with QM9 molecule energies estimated with 76 different DFT functionals and three different basis sets (228 energy numbers for each molecule). We additionally enumerated all possible A <-> B molecular conversions within the QM9 dataset and provide the reaction energies based on these 76 functionals, and basis sets. Lastly, we also provide the bond changes for all the 162 million reactions with the dataset to enable structure and bond based reaction energy prediction tools based on ML.