Δ-Quantum machine-learning for medicinal chemistry

Atz, Kenneth; Isert, Clemens; Böcker, Markus N. A.; Jiménez-Luna, José; Schneider, Gisbert

doi:10.1039/d2cp00834c

Cited by 44 publications

(36 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Remarkably, for models using default ground-state features (Fig. 3C, red lines), we noticed a rank reversal behavior between direct-learning and delta-learning models as more training samples became available, mirroring similar observations from a recent Atomistic ML study (56). The absence of this cross-over when (D β h , D β p ) are provided (Fig.…”

Section: Resultssupporting

confidence: 82%

Informing geometric deep learning with electronic interactions to accelerate quantum chemistry

Qiao

Christensen²,

Welborn³

et al. 2022

Proc. Natl. Acad. Sci. U.S.A.

View full text Add to dashboard Cite

Predicting electronic energies, densities, and related chemical properties can facilitate the discovery of novel catalysts, medicines, and battery materials. However, existing machine learning techniques are challenged by the scarcity of training data when exploring unknown chemical spaces. We overcome this barrier by systematically incorporating knowledge of molecular electronic structure into deep learning. By developing a physics-inspired equivariant neural network, we introduce a method to learn molecular representations based on the electronic interactions among atomic orbitals. Our method, OrbNet-Equi, leverages efficient tight-binding simulations and learned mappings to recover high-fidelity physical quantities. OrbNet-Equi accurately models a wide spectrum of target properties while being several orders of magnitude faster than density functional theory. Despite only using training samples collected from readily available small-molecule libraries, OrbNet-Equi outperforms traditional semiempirical and machine learning–based methods on comprehensive downstream benchmarks that encompass diverse main-group chemical processes. Our method also describes interactions in challenging charge-transfer complexes and open-shell systems. We anticipate that the strategy presented here will help to expand opportunities for studies in chemistry and materials science, where the acquisition of experimental or reference training data is costly.

show abstract

Section: Resultssupporting

confidence: 82%

Informing geometric deep learning with electronic interactions to accelerate quantum chemistry

Qiao

Christensen²,

Welborn³

et al. 2022

Proc. Natl. Acad. Sci. U.S.A.

View full text Add to dashboard Cite

show abstract

“…For many applications such as organic electronics, organic photovoltaics, and organic lightemitting diodes, the energy of the highest occupied molecular orbital (HOMO), the lowest unoccupied MO (LUMO), and the optical gap are of high importance for the device efficiency. These properties can therefore be found in numerous databases 62,90,[173][174][175][176][177] . Related properties include (transition) dipole moment 62,178 , ionization potential, and electron affinity 90 .…”

Section: Applicationsmentioning

confidence: 99%

Graph neural networks for materials science and chemistry

et al. 2022

View full text Add to dashboard Cite

Machine learning plays an increasingly important role in many areas of chemistry and materials science, being used to predict materials properties, accelerate simulations, design new structures, and predict synthesis routes of new materials. Graph neural networks (GNNs) are one of the fastest growing classes of machine learning models. They are of particular relevance for chemistry and materials science, as they directly work on a graph or structural representation of molecules and materials and therefore have full access to all relevant information required to characterize materials. In this Review, we provide an overview of the basic principles of GNNs, widely used datasets, and state-of-the-art architectures, followed by a discussion of a wide range of recent applications of GNNs in chemistry and materials science, and concluding with a road-map for the further development and application of GNNs.

show abstract

“…86,87 For small molecules, state-of-the-art methods range from fast bond charge corrections applied to charges derived from semiempirical quantum chemical methods (such as AM1-BCC 28,29 or CGenFF charge increments 47 ) to expensive multiconformer restrained electrostatic potential (RESP) fits to high-level quantum chemistry. 88,89 Surprisingly little attention has been paid to the divergence of methods used for assigning partial charges to small molecules and biopolymers, and the potential impact this inconsistency has on accuracy or ease of use—indeed, developing charges for post-translational modifications to biopolymer residues 90,91 or covalent ligands can prove to be a significant technical challenge in attempting to bridge these two worlds.…”

Section: Espaloma Can Learn Self-consistent Charge Models In An End-t...mentioning

confidence: 99%

End-to-end differentiable construction of molecular mechanics force fields

et al. 2022

View full text Add to dashboard Cite

show abstract

Δ-Quantum machine-learning for medicinal chemistry

Abstract: Many molecular design tasks benefit from fast and accurate calculations of quantum-mechanical (QM) properties. 3D message-passing neural networks for Δ-quantum machine-learning enable fast access to DFT-level QM properties for drug-like molecules.

Cited by 44 publications

References 78 publications

Informing geometric deep learning with electronic interactions to accelerate quantum chemistry

Informing geometric deep learning with electronic interactions to accelerate quantum chemistry

Graph neural networks for materials science and chemistry

End-to-end differentiable construction of molecular mechanics force fields

Contact Info

Product

Resources

About