Unifying machine learning and quantum chemistry with a deep neural network for molecular wavefunctions

By Kristof T. Schütt, Michael Gastegger, Alexandre Tkatchenko, K. Müller, R. Maurer. Nature Communications, 2019

448 citations recorded by the source corpus.

Machine learning advances chemistry and materials science by enabling large-scale exploration of chemical space based on quantum chemical calculations. While these models supply fast and accurate predictions of atomistic chemical properties, they do not explicitly capture the electronic degrees of freedom of a molecule, which limits their applicability for reactive chemistry and chemical analysis. Here we present a deep learning framework for the prediction of the quantum mechanical wavefunction in a local basis of atomic orbitals from which all other ground-state properties can be derived. This approach retains full access to the electronic structure via the wavefunction at force-field-like efficiency and captures quantum mechanics in an analytically differentiable representation. On several examples, we demonstrate that this opens promising avenues to perform inverse design of molecular structures for targeting electronic property optimisation and a clear path towards increased synergy of machine learning and quantum chemistry. Machine learning models can accurately predict atomistic chemical properties but do not provide access to the molecular electronic structure. Here the authors use a deep learning approach to predict the quantum mechanical wavefunction at high efficiency from which other ground-state properties can be derived.

Subfields: Computational Theory and Mathematics, Materials Chemistry, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/333e80cb1be31236c6b20ab7813cb264604d5d9f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Materials Chemistry

In Molecular Biology

Citations in the corpus

QMugs, quantum mechanical properties of drug-like molecules (2022, methodology): “…progress has been made in quantum-based machine learning (QML) methods 4 , which aim to accurately and computationally inexpensively predict the governing properties of atomistic systems, such as energies and forces 5–12 , dipole moments 13 , wave functions 14,15 and electron densities 16,17 .”
Geometric deep learning on molecular representations (2021, methodology): “SchNet-like architectures were used to predict quantum mechanical wavefunctions in the form of Hartree-Fock and DFT density matrices [81], and differences in quantum properties obtained by DFT and coupled cluster level-of-theory calculations [82].”
Artificial intelligence to deep learning: machine intelligence approach for drug discovery (2021, background): “With these data, we can determine the electronic properties of molecules, the arrangement of chemical bonds around a molecule, and the location of reactive sites [78].”
Provably efficient machine learning for quantum many-body problems (2021, unknown): “Promising insights into quantum many-body physics are already beingobtainedusingclassicalMLbased on classical simulation data ( 10 , 12 , 14 , 17 , 19 , 20 , 23 – 25 , 37 , 38 ).”
Deep-neural-network solution of the electronic Schrödinger equation (2019, methodology): “SchNet has been previously extended and used outside its original scope to represent finite-basis expansions of electronic wave functions (Schütt et al., 2019).”
Ensemble learning of coarse-grained molecular dynamics force fields with a kernel approach. (2020, background): “In the past several years, machine learning (ML) techniques have been increasingly applied in molecular simulation 9,32–34 .”