ProtComposer: Compositional Protein Structure Generation with 3D Ellipsoids
Hannes Stark, Bowen Jing, Tomas Geffner, Jason Yim, Tommi Jaakkola, Arash Vahdat, Karsten Kreis
Abstract
We develop ProtComposer to generate protein structures conditioned on spatial protein layouts that are specified via a set of 3D ellipsoids capturing substructure shapes and semantics. At inference time, we condition on ellipsoids that are hand-constructed, extracted from existing proteins, or from a statistical model, with each option unlocking new capabilities. Hand-specifying ellipsoids enables users to control the location, size, orientation, secondary structure, and approximate shape of protein substructures. Conditioning on ellipsoids of existing proteins enables redesigning their substructure's connectivity or editing substructure properties. By conditioning on novel and diverse ellipsoid layouts from a simple statistical model, we improve protein generation with expanded Pareto frontiers between designability, novelty, and diversity. Further, this enables sampling designable proteins with a helix-fraction that matches PDB proteins, unlike existing generative models that commonly oversample conceptually simple helix bundles. Code is available at https://github.com/NVlabs/protcomposer.
BibTeX
@inproceedings{
stark2025protcomposer,
title={ProtComposer: Compositional Protein Structure Generation with 3D Ellipsoids},
author={Hannes Stark and Bowen Jing and Tomas Geffner and Jason Yim and Tommi Jaakkola and Arash Vahdat and Karsten Kreis},
booktitle={The Thirteenth International Conference on Learning Representations},
year={2025},
url={https://openreview.net/forum?id=0ctvBgKFgc}
}