loading page

Massive sampling strategy for antibody-antigen targets in CAPRI Round 55 with MassiveFold
  • Nessim Raouraoua,
  • Marc Lensink,
  • Guillaume Brysbaert
Nessim Raouraoua
Unite de Glycobiologie Structurale et Fonctionnelle
Author Profile
Marc Lensink
Unite de Glycobiologie Structurale et Fonctionnelle
Author Profile
Guillaume Brysbaert
Unite de Glycobiologie Structurale et Fonctionnelle

Corresponding Author:[email protected]

Author Profile

Abstract

Massive sampling with AlphaFold2 improves protein-protein complex predictions. This has been shown during the last CASP15-CAPRI blind prediction round by the AFsample tool. However, more difficult targets including antibody-antigen binding remain challenging. CAPRI Round 55 consisted of three antibody-antigen targets and one heterotrimer. We used our AlphaFold2-based MassiveFold, running 6 prediction pools, each with their own set of parameters, to produce in total more than 6000 predictions per target. We show here that massive sampling categorically produces acceptable to high quality predictions, however it is clear that the AlphaFold confidence score cannot be used to identify the best models in the set. We also show that, contrary to what was done before for CASP15-CAPRI with AFsample, increasing the sampling without activating the dropout does provide the best models in most cases.
06 Sep 2024Submitted to PROTEINS: Structure, Function, and Bioinformatics
09 Sep 2024Review(s) Completed, Editorial Evaluation Pending
09 Sep 2024Submission Checks Completed
09 Sep 2024Assigned to Editor
22 Sep 2024Reviewer(s) Assigned
01 Nov 2024Editorial Decision: Revise Major