Protein Ensemble Generation through Variational Autoencoder Latent Space Sampling

Abstract

AbstractMapping the ensemble of protein conformations that contribute to function and can be targeted by small molecule drugs remains an outstanding challenge. Here we explore the use of soft-introspective variational autoencoders for reducing the challenge of dimensionality in the protein structure ensemble generation problem. We convert high-dimensional protein structural data into a continuous, low-dimensional representation, carry out search in this space guided by a structure quality metric, then use RoseTTAFold to generate 3D structures. We use this approach to generate ensembles for the cancer relevant protein K-Ras, training the VAE on a subset of the available K-Ras crystal structures and MD simulation snapshots, and assessing the extent of sampling close to crystal structures withheld from training. We find that our latent space sampling procedure rapidly generates ensembles with high structural quality and is able to sample within 1 angstrom of held out crystal structures, with a consistency higher than MD simulation or AlphaFold2 prediction. The sampled structures sufficiently recapitulate the cryptic pockets in the held-out K-Ras structures to allow for small molecule docking.