박현 (University of Illinois at Urbana-Champaign, 현 Absci) | 한빛사논문 > 한빛사

한빛사논문

조회382

University of Illinois at Urbana-Champaign, 현 Absci

Proc. Natl. Acad. Sci. USA, June 24, 2024, 121 (27) | https://doi.org/10.1073/pnas.2311888121 APACE: AlphaFold2 and advanced computing as a service for accelerated discovery in biophysics

Hyun Park^a,b,c, Parth Patel^a,d,e, Roland Haas^e, and E. A. Huerta^a,f,g,1

^aData Science and Learning Division, Argonne National Laboratory, Lemont, IL 60439;

^bTheoretical and Computational Biophysics Group,Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL 61801;

^cCenter for Biophysics and Quantitative Biology, University of Illinois at Urbana-Champaign, Urbana, IL 61801;

^dDepartment of Computer Science, Universityof Illinois at Urbana-Champaign, Urbana, IL 61801;

^eNational Center for Supercomputing Applications,University of Illinois at Urbana-Champaign, Urbana, IL 61801;

^fDepartment of Computer Science, The University of Chicago, Chicago, IL 60637; and

^gDepartment ofPhysics, University of Illinois at Urbana-Champaign, Urbana, IL 61801

¹To whom correspondence may be addressed. : E. A. Huerta

Abstract

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.

논문정보

형식Research article
게재일2024년 06월 (BRIC 등록일 2024-06-26)
연구진국외 연구진
분야 생명과학 > 생물공학

댓글 작성 로그인

CV 열람하기

연락처 보기