EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

APACE: AlphaFold2 and advanced computing as a service for accelerated discovery in biophysics

Hyun Park, Parth Patel iD, Roland Haas iD, E A Huerta iD

Proceedings of the National Academy of Sciences · 2024

DOI: 10.1073/pnas.2311888121 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the National Academy of Sciences, 2024. Verfasst von Hyun Park und 3 weiteren Autor:innen. Beteiligte Einrichtung: Data Science and Learning Division, Argonne National Laboratory, Lemont, IL 60439. Hauptthemen laut MEDLINE: Algorithms, Proteins, Biophysics. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NIGMS NIH HHS, National Science Foundation (NSF), U.S. Department of Energy (DOE).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The prediction of protein 3D structure from amino acid sequence is a computational grand challenge in biophysics and plays a key role in robust protein structure prediction algorithms, from drug discovery to genome interpretation. The advent of AI models, such as AlphaFold, is revolutionizing applications that depend on robust protein structure prediction algorithms. To maximize the impact, and ease the usability, of these AI tools we introduce APACE, AlphaFold2 and advanced computing as a service, a computational framework that effectively handles this AI model and its TB-size database to conduct accelerated protein structure prediction analyses in modern supercomputing environments. We deployed APACE in the Delta and Polaris supercomputers and quantified its performance for accurate protein structure predictions using four exemplar proteins: 6AWO, 6OAN, 7MEZ, and 6D6U. Using up to 300 ensembles, distributed across 200 NVIDIA A100 GPUs, we found that APACE is up to two orders of magnitude faster than off-the-self AlphaFold2 implementations, reducing time-to-solution from weeks to minutes. This computational approach may be readily linked with robotics laboratories to automate and accelerate scientific discovery.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsProteinsBiophysicsProtein ConformationSoftwareComputational BiologyModels, Molecular

Stichwörter der Autor:innen

AI for scienceautomationbiophysicssupercomputing

Substanzen

Proteins

Autor:innen und Institutionen

  • Data Science and Learning Division, Argonne National Laboratory, Lemont, IL 60439.
  • Theoretical and Computational Biophysics Group, Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL 61801.
  • Center for Biophysics and Quantitative Biology, University of Illinois at Urbana-Champaign, Urbana, IL 61801.
  • Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, IL 61801.
  • National Center for Supercomputing Applications, University of Illinois at Urbana-Champaign, Urbana, IL 61801.
  • Department of Computer Science, The University of Chicago, Chicago, IL 60637.

ORCID-Profile: Parth Patel, Roland Haas, E A Huerta

Förderung

  • NIGMS NIH HHS
  • National Science Foundation (NSF)
  • U.S. Department of Energy (DOE)

Zitieren

APA

Park, H., Patel, P., Haas, R., & Huerta, E. A. (2024). APACE: AlphaFold2 and advanced computing as a service for accelerated discovery in biophysics. Proceedings of the National Academy of Sciences. https://doi.org/10.1073/pnas.2311888121

Vancouver

Park H, Patel P, Haas R, Huerta EA. APACE: AlphaFold2 and advanced computing as a service for accelerated discovery in biophysics. Proceedings of the National Academy of Sciences. 2024. doi:10.1073/pnas.2311888121

BibTeX
@article{Park2024,
  author = {Park, Hyun and Patel, Parth and Haas, Roland and Huerta, E A},
  title = {APACE: AlphaFold2 and advanced computing as a service for accelerated discovery in biophysics},
  journal = {Proceedings of the National Academy of Sciences},
  year = {2024},
  doi = {10.1073/pnas.2311888121}
}
Kostenlos starten →