g-schnet
Symmetry-adapted generation of 3d point sets for the targeted discovery of molecules
Niklas Gebauer, Michael Gastegger, Kristof Schütt
Neural Information Processing Systems http://nips.cc/
- Europe > Germany > Berlin (0.04)
- North America > Canada (0.04)
Symmetry-adapted generation of 3d point sets for the targeted discovery of molecules
Niklas Gebauer, Michael Gastegger, Kristof Schütt
Neural Information Processing Systems http://nips.cc/
- Europe > Germany > Berlin (0.04)
- North America > Canada > British Columbia > Metro Vancouver Regional District > Vancouver (0.04)
enough that generating 3d molecular geometries is an independent, quite novel task and not to be confused with 2
We agree that our notation of the focus token was confusing.
Inverse design of 3d molecular structures with conditional generative neural networks
Gebauer, Niklas W. A., Gastegger, Michael, Hessmann, Stefaan S. P., Müller, Klaus-Robert, Schütt, Kristof T.
The rational design of molecules with desired properties is a long-standing challenge in chemistry. Generative neural networks have emerged as a powerful approach to sample novel molecules from a learned distribution. Here, we propose a conditional generative neural network for 3d molecular structures with specified structural and chemical properties. This approach is agnostic to chemical bonding and enables targeted sampling of novel molecules from conditional distributions, even in domains where reference calculations are sparse. We demonstrate the utility of our method for inverse design by generating molecules with specified composition or motifs, discovering particularly stable molecules, and jointly targeting multiple electronic properties beyond the training regime.
- Health & Medicine > Pharmaceuticals & Biotechnology (1.00)
- Energy (1.00)
- Materials > Chemicals (0.68)
Symmetry-adapted generation of 3d point sets for the targeted discovery of molecules
Gebauer, Niklas W. A., Gastegger, Michael, Schütt, Kristof T.
Deep learning has proven to yield fast and accurate predictions of quantum-chemical properties to accelerate the discovery of novel molecules and materials. As an exhaustive exploration of the vast chemical space is still infeasible, we require generative models that guide our search towards systems with desired properties. While graph-based models have previously been proposed, they are restricted by a lack of spatial information such that they are unable to recognize spatial isomerism and non-bonded interactions. Here, we introduce a generative neural network for 3d point sets that respects the rotational invariance of the targeted structures. We apply it to the generation of molecules and demonstrate its ability to approximate the distribution of equilibrium structures using spatial metrics as well as established measures from chemoinformatics. As our model is able to capture the complex relationship between 3d geometry and electronic properties, we bias the distribution of the generator towards molecules with a small HOMO-LUMO gap - an important property for the design of organic solar cells.