PulseTrendingJournal ClubResearchersJournalsExplore
Instagram
HomeTrendingJournal ClubExplore
Synapse
⌘+K
Synapse
April 19, 2026JACS AuOpen Access

SAKE-PP: A Spatial-Attention Equivariant Network for Accurate Ranking of Protein–Protein Interaction Models

View Full Paper
Ask AI
Bookmark
Share

Authors

YXYuzhi XuWXWei XiaCZChao Zhang

Discussion

Loading...

Member takes

Overview

This research develops SAKE-PP to enhance protein-protein interaction model ranking, suggesting improved prediction accuracy for structural biology applications.

Key Points

  • The aim is to improve the accuracy of ranking near-native protein-protein interaction models using SAKE-PP.
  • Developed a spatial-attention equivariant graph neural network (SAKE-PP)
  • Utilized a hierarchical iRMSD-guided sampling strategy
  • Trained on the PDBBind dataset to assess protein interactions
  • Evaluated using the 2024PDB benchmark with 176 heterodimers
  • Conducted zero-shot evaluations on 139 antibody-antigen complexes.
  • SAKE-PP improved AF3-decoy selection by 13.75% in iRMSD and 12.5% in DockQ
  • Exhibited better rankings than AF3 in overlap, hit-rate, and correlation metrics
  • Increased correlation by 0.4 in zero-shot evaluation on antibody-antigen complexes
  • Enhanced model selection by favoring geometrically near-native and energetically plausible interfaces

Cite This Study

Xu et al. (2026) studied this question.

synapsesocial.com/papers/69e47193010ef96374d8dddchttps://doi.org/10.1021/jacsau.6c00166
View Full Paper
Ask AI
Bookmark
Share