Ig-VAE: Generative modeling of protein structure by direct 3D coordinate generation |
| |
Authors: | Raphael R Eguchi Christian A Choe Po-Ssu Huang |
| |
Institution: | 1. Department of Biochemistry, Stanford University, Stanford, California, United States of America;2. Department of Statistics, Stanford University, Stanford, California, United States of America;3. Department of Bioengineering, Stanford University, Stanford, California, United States of America; University of Kansas, UNITED STATES |
| |
Abstract: | While deep learning models have seen increasing applications in protein science, few have been implemented for protein backbone generation—an important task in structure-based problems such as active site and interface design. We present a new approach to building class-specific backbones, using a variational auto-encoder to directly generate the 3D coordinates of immunoglobulins. Our model is torsion- and distance-aware, learns a high-resolution embedding of the dataset, and generates novel, high-quality structures compatible with existing design tools. We show that the Ig-VAE can be used with Rosetta to create a computational model of a SARS-CoV2-RBD binder via latent space sampling. We further demonstrate that the model’s generative prior is a powerful tool for guiding computational protein design, motivating a new paradigm under which backbone design is solved as constrained optimization problem in the latent space of a generative model. |
| |
Keywords: | |
|
|