Rxivist logo

SE(3)-Equivariant Energy-based Models for End-to-End Protein Folding

By Jiaxiang Wu, Tao Shen, Haidong Lan, Yatao Bian, Junzhou Huang

Posted 07 Jun 2021
bioRxiv DOI: 10.1101/2021.06.06.447297

Accurate prediction of protein structures is critical for understanding the biological function of proteins. Nevertheless, most structure optimization methods are built upon pre-defined statistical energy functions, which may be sub-optimal in formulating the conformation space. In this paper, we propose an end-to-end approach for protein structure optimization, powered by SE(3)-equivariant energy-based models. The conformation space is characterized by a SE(3)-equivariant graph neural network, with substantial modifications to embed the protein-specific domain knowledge. Furthermore, we introduce continuously-annealed Langevin dynamics as a novel sampling algorithm, and demonstrate that such process converges to native protein structures with theoretical guarantees. Extensive experiments indicate that SE(3)-Fold achieves comparable structure optimization accuracy, compared against state-of-the-art baselines, with over 1-2 orders of magnitude speed-up.

Download data

  • Downloaded 1,158 times
  • Download rankings, all-time:
    • Site-wide: 21,195
    • In bioinformatics: 2,433
  • Year to date:
    • Site-wide: 3,437
  • Since beginning of last month:
    • Site-wide: 13,193

Altmetric data

Downloads over time

Distribution of downloads per paper, site-wide