Physics-Constrained Predictive Molecular Latent Space Discovery with Graph Scattering Variational Autoencoder
This work addresses the challenge of computational materials modeling for researchers in chemistry and materials science, though it appears incremental as it builds on existing generative deep learning methods.
The paper tackles the problem of predictive molecular design in the small data regime by proposing a graph scattering variational autoencoder with physical constraints for energetically stable molecules, resulting in a model that generates molecules with desired target properties.
Recent advances in artificial intelligence have propelled the development of innovative computational materials modeling and design techniques. Generative deep learning models have been used for molecular representation, discovery, and design. In this work, we assess the predictive capabilities of a molecular generative model developed based on variational inference and graph theory in the small data regime. Physical constraints that encourage energetically stable molecules are proposed. The encoding network is based on the scattering transform with adaptive spectral filters to allow for better generalization of the model. The decoding network is a one-shot graph generative model that conditions atom types on molecular topology. A Bayesian formalism is considered to capture uncertainties in the predictive estimates of molecular properties. The model's performance is evaluated by generating molecules with desired target properties.