Hierarchical Protein Backbone Generation with Latent and Structure Diffusion

Jason Yim, Marouane Jaakik, Ge Liu, Jacob Gershon, Karsten Kreis, David Baker, Regina Barzilay, Tommi Jaakkola

Track: Machine learning: computational method and/or computational results

Nature Biotechnology: Yes

Keywords: Proteins, latent diffusion

TL;DR: By leveraging latent and structure diffusion, we propose a hierarchical protein backbone generative model with guidance towards lower PAE and more diverse folds.

Abstract: We propose a hierarchical protein backbone generative model that separates coarse and fine-grained details. Our approach called LSD consists of two stages: sampling latents which are decoded into a contact map then sampling atomic coordinates conditioned on the contact map. LSD allows new ways to control protein generation towards desirable properties while scaling to large datasets. In particular, the AlphaFold DataBase (AFDB) is appealing due as its diverse structure topologies but suffers from poor designability. We train LSD on AFDB and show latent diffusion guidance towards AlphaFold2 Predicted Alignment Error and long range contacts can explicitly balance designability, diversity, and noveltys in the generated samples. Our results are competitive with structure diffusion models and outperforms prior latent diffusion models.

Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.

Presenter: ~Jason_Yim1

Format: Yes, the presenting author will definitely attend in person because they attending ICLR for other complementary reasons.

Funding: No, the presenting author of this submission does *not* fall under ICLR’s funding aims, or has sufficient alternate funding.

Submission Number: 33