Multi-Type Point Cloud Autoencoder: A Complete Equivariant Embedding for Molecule Conformation and Pose

The point cloud is a flexible representation for a wide variety of data types, and is a particularly natural fit for the 3D conformations of molecules. Extant molecule embedding/representation schemes typically focus on internal degrees of freedom, ignoring the global 3D orientation. For tasks that depend on knowledge of both molecular conformation and 3D orientation, such as the generation of molecular dimers, clusters, or condensed phases, we require a representation which is provably complete in the types and positions of atomic nuclei and roto-inversion equivariant with respect to the input point cloud. We develop, train, and evaluate a new type of autoencoder, molecular O(3) encoding net (Mo3ENet), for multi-type point clouds, for which we propose a new reconstruction loss, capitalizing on a Gaussian mixture representation of the input and output point clouds. Mo3ENet is end-to-end equivariant, meaning the learned representation can be manipulated on O(3), a practical bonus for downstream learning tasks. An appropriately trained Mo3ENet latent space comprises a universal embedding for scalar and vector molecule property prediction tasks, as well as other downstream tasks incorporating the 3D molecular pose.