AFsample: improving multimer prediction with AlphaFold using massive sampling.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
Read More Add to Saved list
  • Author(s): Wallner B;Wallner B
  • Source:
    Bioinformatics (Oxford, England) [Bioinformatics] 2023 Sep 02; Vol. 39 (9).
  • Publication Type:
    Journal Article; Research Support, Non-U.S. Gov't
  • Language:
    English
  • Additional Information
    • Source:
      Publisher: Oxford University Press Country of Publication: England NLM ID: 9808944 Publication Model: Print Cited Medium: Internet ISSN: 1367-4811 (Electronic) Linking ISSN: 13674803 NLM ISO Abbreviation: Bioinformatics Subsets: MEDLINE
    • Publication Information:
      Original Publication: Oxford : Oxford University Press, c1998-
    • Subject Terms:
      Proteins*/chemistry ; Neural Networks, Computer*; Protein Conformation ; Benchmarking
    • Abstract:
      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.
      (© The Author(s) 2023. Published by Oxford University Press.)
    • References:
      Bioinformatics. 2015 Mar 15;31(6):926-32. (PMID: 25398609)
      Nat Commun. 2022 Mar 10;13(1):1265. (PMID: 35273146)
      Phys Rev Lett. 2022 Dec 2;129(23):238101. (PMID: 36563190)
      Proteins. 2004 Dec 1;57(4):702-10. (PMID: 15476259)
      Antibodies (Basel). 2019 Dec 03;8(4):. (PMID: 31816964)
      Nat Struct Mol Biol. 2021 Sep;28(9):704-705. (PMID: 34376855)
      Bioinformatics. 2013 Nov 1;29(21):2722-8. (PMID: 23986568)
      Nat Methods. 2022 Jun;19(6):679-682. (PMID: 35637307)
      PLoS One. 2016 Aug 25;11(8):e0161879. (PMID: 27560519)
      Proteins. 2023 Aug 7;:. (PMID: 37548092)
      Nature. 2021 Aug;596(7873):583-589. (PMID: 34265844)
      Nucleic Acids Res. 2017 Jan 4;45(D1):D170-D176. (PMID: 27899574)
      Front Bioinform. 2022 Sep 26;2:959160. (PMID: 36304330)
      Nat Commun. 2018 Jun 29;9(1):2542. (PMID: 29959318)
    • Accession Number:
      0 (Proteins)
    • Publication Date:
      Date Created: 20230915 Date Completed: 20230929 Latest Revision: 20231013
    • Publication Date:
      20231013
    • Accession Number:
      PMC10534052
    • Accession Number:
      10.1093/bioinformatics/btad573
    • Accession Number:
      37713472