Scalable HPC & AI infrastructure for COVID-19 therapeutics

Hyungro Lee; Andre Merzky; Li Tan; Mikhail Titov; Matteo Turilli; Dario Alfe; Agastya Bhati; Alex Brace; Austin Clyde; Peter Coveney; Heng Ma; Arvind Ramanathan; Rick Stevens; Anda Trifan; Hubertus Van Dam; Shunzhou Wan; Sean Wilkinson; Shantenu Jha

doi:10.1145/3468267.3470573

Scalable HPC & AI infrastructure for COVID-19 therapeutics

Hyungro Lee, Andre Merzky, Li Tan, Mikhail Titov, Matteo Turilli, Dario Alfe, Agastya Bhati, Alex Brace, Austin Clyde, Peter Coveney, Heng Ma, Arvind Ramanathan, Rick Stevens, Anda Trifan, Hubertus Van Dam, Shunzhou Wan, Sean Wilkinson, Shantenu Jha

Workflow and Ecosystem Services

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

13 Scopus citations

Abstract

COVID-19 has claimed more than 2.7 × 106 lives and resulted in over 124 × 106 infections. There is an urgent need to identify drugs that can inhibit SARS-CoV-2. We discuss innovations in computational infrastructure and methods that are accelerating and advancing drug design. Specifically, we describe several methods that integrate artificial intelligence and simulation-based approaches, and the design of computational infrastructure to support these methods at scale. We discuss their implementation, characterize their performance, and highlight science advances that these capabilities have enabled.

Original language	English
Title of host publication	Proceedings of the Platform for Advanced Scientific Computing Conference, PASC 2021
Publisher	Association for Computing Machinery, Inc
ISBN (Electronic)	9781450385633
DOIs	https://doi.org/10.1145/3468267.3470573
State	Published - Jul 5 2021
Event	2021 Platform for Advanced Scientific Computing Conference, PASC 2021 - Virtual, Online, Switzerland Duration: Jul 5 2021 → Jul 9 2021

Publication series

Name	Proceedings of the Platform for Advanced Scientific Computing Conference, PASC 2021

Conference

Conference	2021 Platform for Advanced Scientific Computing Conference, PASC 2021
Country/Territory	Switzerland
City	Virtual, Online
Period	07/5/21 → 07/9/21

Funding

Research was supported by the DOE Office of Science through the National Virtual Biotechnology Laboratory; as part of the CANDLE project by the ECP (17-SC-20-SC); UK MRC Medical Bioinformatics project (grant no. MR/L016311/1), UKCOMES (grant no. EP/L00030X/1); EU H2020 CompBioMed2 Centre of Excellence (grant no. 823712), and support from the UCL Provost. Access to SuperMUC-NG (LRZ) was made possible by a special COVID-19 allocation award from the Gauss Centre for Supercomputing in Germany. Anda Trifan acknowledges support from the United States Department of Energy through the Computational Sciences Graduate Fellowship (DOE CSGF) under grant number: DE-SC0019323. We acknowledge support and allocation from TACC and OLCF. The effectiveness and impact of the infrastructure are evidenced by its use to sustain a campaign on multiple heterogeneous platforms over months to generate valuable scientific insight (§5). This work is a harbinger of the evolving role of supercomputers, viz., increasingly important generators of data for powerful ML models (e.g., WF1). In general, supercomputers will have to support campaigns with diverse components, viz., physics-based simulations, data generation and analysis, and ML/AI tasks. These individual workflows have different computational characteristics and performance challenges. They encompass high-throughput function calls, ensembles of MPI-based simulations, and AI-driven HPC simulations. There are no “turnkey solutions” to support such campaigns across multiple heterogeneous platforms, with the necessary performance and scale to ensure the required throughput. This has necessitated the design, development, and iterative improvement of infrastructure to advance therapeutics for COVID-19 and beyond. Acknowledgements: Research was supported by the DOE Office of Science through the National Virtual Biotechnology Laboratory; as part of the CANDLE project by the ECP (17-SC-20-SC); UK MRC Medical Bioinformatics project (grant no. MR/L016311/1), UKCOMES (grant no. EP/L00030X/1); EU H2020 CompBioMed2 Centre of Excellence (grant no. 823712), and support from the UCL Provost. Access to SuperMUC-NG (LRZ) was made possible by a special COVID-19 allocation award from the Gauss Centre for Supercomputing in Germany. Anda Trifan acknowledges support from the United States Department of Energy through the Computational Sciences Graduate Fellowship (DOE CSGF) under grant number: DE-SC0019323. We acknowledge support and allocation from TACC and OLCF.

Funders	Funder number
Gauss Centre for Supercomputing
H2020 CompBioMed2 Centre of Excellence	823712
National Virtual Biotechnology Laboratory	17-SC-20-SC
OLCF
TACC
UCL Provost
UKCOMES	EP/L00030X/1
U.S. Department of Energy	DE-SC0019323
Office of Science
Medical Research Council	MR/L016311/1

Keywords

COVID-19
Docking molecular dynamics
Free energy estimation
High-performance computing
Machine learning
Workflows

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1145/3468267.3470573

Cite this

Lee, H., Merzky, A., Tan, L., Titov, M., Turilli, M., Alfe, D., Bhati, A., Brace, A., Clyde, A., Coveney, P., Ma, H., Ramanathan, A., Stevens, R., Trifan, A., Van Dam, H., Wan, S., Wilkinson, S., & Jha, S. (2021). Scalable HPC & AI infrastructure for COVID-19 therapeutics. In Proceedings of the Platform for Advanced Scientific Computing Conference, PASC 2021 (Proceedings of the Platform for Advanced Scientific Computing Conference, PASC 2021). Association for Computing Machinery, Inc. https://doi.org/10.1145/3468267.3470573

@inproceedings{63e613b3c30b4ae8afa09334dc324b85,

title = "Scalable HPC & AI infrastructure for COVID-19 therapeutics",

abstract = "COVID-19 has claimed more than 2.7 × 106 lives and resulted in over 124 × 106 infections. There is an urgent need to identify drugs that can inhibit SARS-CoV-2. We discuss innovations in computational infrastructure and methods that are accelerating and advancing drug design. Specifically, we describe several methods that integrate artificial intelligence and simulation-based approaches, and the design of computational infrastructure to support these methods at scale. We discuss their implementation, characterize their performance, and highlight science advances that these capabilities have enabled.",

keywords = "COVID-19, Docking molecular dynamics, Free energy estimation, High-performance computing, Machine learning, Workflows",

author = "Hyungro Lee and Andre Merzky and Li Tan and Mikhail Titov and Matteo Turilli and Dario Alfe and Agastya Bhati and Alex Brace and Austin Clyde and Peter Coveney and Heng Ma and Arvind Ramanathan and Rick Stevens and Anda Trifan and {Van Dam}, Hubertus and Shunzhou Wan and Sean Wilkinson and Shantenu Jha",

note = "Publisher Copyright: {\textcopyright} 2021 ACM.; 2021 Platform for Advanced Scientific Computing Conference, PASC 2021 ; Conference date: 05-07-2021 Through 09-07-2021",

year = "2021",

month = jul,

day = "5",

doi = "10.1145/3468267.3470573",

language = "English",

series = "Proceedings of the Platform for Advanced Scientific Computing Conference, PASC 2021",

publisher = "Association for Computing Machinery, Inc",

booktitle = "Proceedings of the Platform for Advanced Scientific Computing Conference, PASC 2021",

}

Lee, H, Merzky, A, Tan, L, Titov, M, Turilli, M, Alfe, D, Bhati, A, Brace, A, Clyde, A, Coveney, P, Ma, H, Ramanathan, A, Stevens, R, Trifan, A, Van Dam, H, Wan, S, Wilkinson, S & Jha, S 2021, Scalable HPC & AI infrastructure for COVID-19 therapeutics. in Proceedings of the Platform for Advanced Scientific Computing Conference, PASC 2021. Proceedings of the Platform for Advanced Scientific Computing Conference, PASC 2021, Association for Computing Machinery, Inc, 2021 Platform for Advanced Scientific Computing Conference, PASC 2021, Virtual, Online, Switzerland, 07/5/21. https://doi.org/10.1145/3468267.3470573

Scalable HPC & AI infrastructure for COVID-19 therapeutics. / Lee, Hyungro; Merzky, Andre; Tan, Li et al.
Proceedings of the Platform for Advanced Scientific Computing Conference, PASC 2021. Association for Computing Machinery, Inc, 2021. (Proceedings of the Platform for Advanced Scientific Computing Conference, PASC 2021).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Scalable HPC & AI infrastructure for COVID-19 therapeutics

AU - Lee, Hyungro

AU - Merzky, Andre

AU - Tan, Li

AU - Titov, Mikhail

AU - Turilli, Matteo

AU - Alfe, Dario

AU - Bhati, Agastya

AU - Brace, Alex

AU - Clyde, Austin

AU - Coveney, Peter

AU - Ma, Heng

AU - Ramanathan, Arvind

AU - Stevens, Rick

AU - Trifan, Anda

AU - Van Dam, Hubertus

AU - Wan, Shunzhou

AU - Wilkinson, Sean

AU - Jha, Shantenu

PY - 2021/7/5

Y1 - 2021/7/5

N2 - COVID-19 has claimed more than 2.7 × 106 lives and resulted in over 124 × 106 infections. There is an urgent need to identify drugs that can inhibit SARS-CoV-2. We discuss innovations in computational infrastructure and methods that are accelerating and advancing drug design. Specifically, we describe several methods that integrate artificial intelligence and simulation-based approaches, and the design of computational infrastructure to support these methods at scale. We discuss their implementation, characterize their performance, and highlight science advances that these capabilities have enabled.

AB - COVID-19 has claimed more than 2.7 × 106 lives and resulted in over 124 × 106 infections. There is an urgent need to identify drugs that can inhibit SARS-CoV-2. We discuss innovations in computational infrastructure and methods that are accelerating and advancing drug design. Specifically, we describe several methods that integrate artificial intelligence and simulation-based approaches, and the design of computational infrastructure to support these methods at scale. We discuss their implementation, characterize their performance, and highlight science advances that these capabilities have enabled.

KW - COVID-19

KW - Docking molecular dynamics

KW - Free energy estimation

KW - High-performance computing

KW - Machine learning

KW - Workflows

UR - http://www.scopus.com/inward/record.url?scp=85114333699&partnerID=8YFLogxK

U2 - 10.1145/3468267.3470573

DO - 10.1145/3468267.3470573

M3 - Conference contribution

AN - SCOPUS:85114333699

T3 - Proceedings of the Platform for Advanced Scientific Computing Conference, PASC 2021

BT - Proceedings of the Platform for Advanced Scientific Computing Conference, PASC 2021

PB - Association for Computing Machinery, Inc

T2 - 2021 Platform for Advanced Scientific Computing Conference, PASC 2021

Y2 - 5 July 2021 through 9 July 2021

ER -

Scalable HPC & AI infrastructure for COVID-19 therapeutics

Abstract

Publication series

Conference

Funding

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this