Uncovering the Folding Landscape of RNA Secondary Structure with Deep Graph Embeddings
This work addresses the challenge of analyzing biomolecular folding landscapes for researchers in computational biology and geometric deep learning, but it is incremental as it builds on existing methods like geometric scattering transforms and variational autoencoders.
The paper tackled the problem of organizing biomolecular graphs to reveal meaningful relationships and variations, specifically for RNA secondary structures, by proposing a geometric scattering autoencoder (GSAE) network that learns graph embeddings. The result showed that GSAE organizes RNA graphs by structure and energy, accurately reflecting bistable RNA structures, and can generate new folding trajectories.
Biomolecular graph analysis has recently gained much attention in the emerging field of geometric deep learning. Here we focus on organizing biomolecular graphs in ways that expose meaningful relations and variations between them. We propose a geometric scattering autoencoder (GSAE) network for learning such graph embeddings. Our embedding network first extracts rich graph features using the recently proposed geometric scattering transform. Then, it leverages a semi-supervised variational autoencoder to extract a low-dimensional embedding that retains the information in these features that enable prediction of molecular properties as well as characterize graphs. We show that GSAE organizes RNA graphs both by structure and energy, accurately reflecting bistable RNA structures. Also, the model is generative and can sample new folding trajectories.