DiffMaSIF: Surface-based Protein-Protein Docking with Diffusion Models - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

DiffMaSIF: Surface-based Protein-Protein Docking with Diffusion Models

Mehmet Akdel
  • Function : Author
Dylan Abramson
  • Function : Author
Alexander Goncearenco
  • Function : Author
Yusuf Adeshina
  • Function : Author
Daniel Kovtun
  • Function : Author
Céline Marquet
  • Function : Author
Xuejin Zhang
  • Function : Author
David Baugher
  • Function : Author
Zachary Carpenter
  • Function : Author
Luca Naef
  • Function : Author
Michael M Bronstein
  • Function : Author

Abstract

Predicting protein-protein complexes is a central challenge of computational structural biology. Existing state-of-the-art methods rely on co-evolution learned on large amino acid sequence datasets and thus often fall short on both transient and engineered interfaces (which are of particular interest in therapeutic applications) where co-evolutionary signals are absent or minimal. To address this, we introduce DIFFMASIF, a novel score-based diffusion model for rigid protein-protein docking. Instead of sequence-based features, DIFFMASIF uses a protein molecular surfacebased encoder-decoder architecture to effectively learn physical complementarity. The encoder uses learned geometric features extracted from protein surface point clouds. It directly learns binding site complementary through prediction of contact sites as an auxiliary loss, and also allows for specification of known binding sites during inference. It is followed by a decoder predicting rotation and translation via SO(3) diffusion. We show that DIFFMASIF achieves state-of-the-art among deep Llearning methods for rigid body docking, in particular on structurally novel interfaces and low sequence conservation. This provides a significant advance towards accurate modelling of low co-evolution protein interactions and their many practical applications.
Fichier principal
Vignette du fichier
DiffMaSIF_Surface-based_Protein-Protein_Docking_with_Diffusion_Models.pdf (8.72 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Licence

Dates and versions

hal-04360638 , version 1 (21-12-2023)

Licence

Identifiers

  • HAL Id : hal-04360638 , version 1

Cite

Freyr Sverrisson, Mehmet Akdel, Dylan Abramson, Jean Feydy, Alexander Goncearenco, et al.. DiffMaSIF: Surface-based Protein-Protein Docking with Diffusion Models. Machine Learning in Structural Biology workshop at NeurIPS 2023, Dec 2023, New Orleans, United States. ⟨hal-04360638⟩
535 View
197 Download

Share

Gmail Mastodon Facebook X LinkedIn More