$\nabla^2$DFT: A Universal Quantum Chemistry Dataset of Drug-Like Molecules and a Benchmark for Neural Network Potentials

TL;DR

The paper introduces $ abla^2$DFT, a comprehensive quantum chemistry dataset with diverse molecular data and a benchmark for neural network potentials, enhancing drug discovery research and NNP evaluation.

Contribution

It presents a new, extensive dataset and benchmark for neural network potentials, including relaxation trajectories and multiple molecular properties, advancing the development and assessment of NNPs.

Findings

Dataset contains twice as many structures as previous datasets.

Includes relaxation trajectories for drug-like molecules.

Provides a framework and 10 models for training NNPs.

Abstract

Methods of computational quantum chemistry provide accurate approximations of molecular properties crucial for computer-aided drug discovery and other areas of chemical science. However, high computational complexity limits the scalability of their applications. Neural network potentials (NNPs) are a promising alternative to quantum chemistry methods, but they require large and diverse datasets for training. This work presents a new dataset and benchmark called $\nabla^2$DFT that is based on the nablaDFT. It contains twice as much molecular structures, three times more conformations, new data types and tasks, and state-of-the-art models. The dataset includes energies, forces, 17 molecular properties, Hamiltonian and overlap matrices, and a wavefunction object. All calculations were performed at the DFT level ($\omega$B97X-D/def2-SVP) for each conformation. Moreover, $\nabla^2$DFT is the first dataset that contains relaxation trajectories for a substantial number of drug-like molecules. We also introduce a novel benchmark for evaluating NNPs in molecular property prediction, Hamiltonian prediction, and conformational optimization tasks. Finally, we propose an extendable framework for training NNPs and implement 10 models within it.