EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AFsample: improving multimer prediction with AlphaFold using massive sampling

Björn Wallner iD

Bioinformatics · 02.09.2023 · 39 (9)

DOI: 10.1093/bioinformatics/btad573 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 15.09.2023. Verfasst von Björn Wallner. Beteiligte Einrichtung: Division of Bioinformatics, Department of Physics, Chemistry and Biology, Linköping University, SE-581 83 Linköping, Sweden. Hauptthemen laut MEDLINE: Proteins, Neural Networks, Computer. Die Arbeit wurde bisher 200-mal zitiert (Crossref) und nennt 16 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Wallenberg AI, Autonomous System and Software Program, Swedish e-Science Research Center.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Summary The AlphaFold2 neural network model has revolutionized structural biology with unprecedented performance. We demonstrate that by stochastically perturbing the neural network by enabling dropout at inference combined with massive sampling, it is possible to improve the quality of the generated models. We generated ∼6000 models per target compared with 25 default for AlphaFold-Multimer, with v1 and v2 multimer network models, with and without templates, and increased the number of recycles within the network. The method was benchmarked in CASP15, and compared with AlphaFold-Multimer v2 it improved the average DockQ from 0.41 to 0.55 using identical input and was ranked at the very top in the protein assembly category when compared with all other groups participating in CASP15. The simplicity of the method should facilitate the adaptation by the field, and the method should be useful for anyone interested in modeling multimeric structures, alternate conformations, or flexible structures. Availability and implementation AFsample is available online at http://wallnerlab.org/AFsample.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ProteinsNeural Networks, ComputerProtein Conformation

Substanzen

Proteins

Autor:innen und Institutionen

  • Division of Bioinformatics, Department of Physics, Chemistry and Biology, Linköping University, SE-581 83 Linköping, Sweden.

ORCID-Profile: Björn Wallner

Förderung

  • Wallenberg AI, Autonomous System and Software Program
  • Swedish e-Science Research Center

Zitieren

APA

Wallner, B. (2023). AFsample: improving multimer prediction with AlphaFold using massive sampling. Bioinformatics, 39(9). https://doi.org/10.1093/bioinformatics/btad573

Vancouver

Wallner B. AFsample: improving multimer prediction with AlphaFold using massive sampling. Bioinformatics. 2023;39(9). doi:10.1093/bioinformatics/btad573

BibTeX
@article{Wallner2023,
  author = {Wallner, Björn},
  title = {AFsample: improving multimer prediction with AlphaFold using massive sampling},
  journal = {Bioinformatics},
  year = {2023},
  volume = {39},
  number = {9},
  doi = {10.1093/bioinformatics/btad573}
}
Kostenlos starten →