Hierarchical protein backbone generation with latent and structure diffusion

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

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 18 functions out of this paper's own repositories and ran 9 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• aqlaboratory/genie2

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2504.09374")
get_code_for_paper("2504.09374")
have("2504.09374")

Connect an agent — have() is free.