Intelligent resolution: Integrating Cryo-EM with AI-driven multi-resolution simulations to observe the severe acute respiratory syndrome coronavirus-2 replication-transcription machinery in action

Anda Trifan; Defne Gorgun; Michael Salim; Zongyi Li; Alexander Brace; Maxim Zvyagin; Heng Ma; Austin Clyde; David Clark; David J. Hardy; Tom Burnley; Lei Huang; John McCalpin; Murali Emani; Hyenseung Yoo; Junqi Yin; Aristeidis Tsaris; Vishal Subbiah; Tanveer Raza; Jessica Liu; Noah Trebesch; Geoffrey Wells; Venkatesh Mysore; Thomas Gibbs; James Phillips; S. Chakra Chennubhotla; Ian Foster; Rick Stevens; Anima Anandkumar; Venkatram Vishwanath; John E. Stone; Emad Tajkhorshid; Sarah A. Harris; Arvind Ramanathan

doi:10.1177/10943420221113513

Intelligent resolution: Integrating Cryo-EM with AI-driven multi-resolution simulations to observe the severe acute respiratory syndrome coronavirus-2 replication-transcription machinery in action

Anda Trifan, Defne Gorgun, Michael Salim, Zongyi Li, Alexander Brace, Maxim Zvyagin, Heng Ma, Austin Clyde, David Clark, David J. Hardy, Tom Burnley, Lei Huang, John McCalpin, Murali Emani, Hyenseung Yoo, Junqi Yin, Aristeidis Tsaris, Vishal Subbiah, Tanveer Raza, Jessica LiuNoah Trebesch, Geoffrey Wells, Venkatesh Mysore, Thomas Gibbs, James Phillips, S. Chakra Chennubhotla, Ian Foster, Rick Stevens, Anima Anandkumar, Venkatram Vishwanath, John E. Stone, Emad Tajkhorshid, Sarah A. Harris, Arvind Ramanathan

Analytics and AI Methods at Scale

Research output: Contribution to journal › Article › peer-review

5 Scopus citations

Abstract

The severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) replication transcription complex (RTC) is a multi-domain protein responsible for replicating and transcribing the viral mRNA inside a human cell. Attacking RTC function with pharmaceutical compounds is a pathway to treating COVID-19. Conventional tools, e.g. cryo-electron microscopy and all-atom molecular dynamics (AAMD), do not provide sufficiently high resolution or timescale to capture important dynamics of this molecular machine. Consequently, we develop an innovative workflow that bridges the gap between these resolutions, using mesoscale fluctuating finite element analysis (FFEA) continuum simulations and a hierarchy of AI-methods that continually learn and infer features for maintaining consistency between AAMD and FFEA simulations. We leverage a multi-site distributed workflow manager to orchestrate AI, FFEA, and AAMD jobs, providing optimal resource utilization across HPC centers. Our study provides unprecedented access to study the SARS-CoV-2 RTC machinery, while providing general capability for AI-enabled multi-resolution simulations at scale.

Original language	English
Pages (from-to)	603-623
Number of pages	21
Journal	International Journal of High Performance Computing Applications
Volume	36
Issue number	5-6
DOIs	https://doi.org/10.1177/10943420221113513
State	Published - Nov 2022

Funding

We thank the Argonne Leadership Computing Facility supported by the DOE under DE-AC02-06CH11357, the Oak Ridge Leadership Computing Facility at Oak Ridge National Laboratory supported by the DOE under Contract DE-AC05-00OR22725, and the National Energy Research Scientific Computing Center at Lawrence Berkeley National Laboratory supported by the DOE under Contract No. DE-AC02-05CH11231. We also thank the Texas Advanced Computing Center Frontera team, especially D. Stanzione and T. Cockerill, and for compute time made available through a Director’s Discretionary Allocation (NSF MCB-20024). NAMD and VMD are funded by NIH P41-GM104601. The NAMD team thanks Intel and M. Brown for contributing the AVX-512 tile list kernels. Anda Trifan acknowledges support from a DOE CSGF (DE-FG02-97ER25308). This research was supported by the Exascale Computing Project (17-SC-20-SC), a collaborative effort of the US DOE Office of Science and the National Nuclear Security Administration. Research was supported by the DOE through the National Virtual Biotechnology Laboratory, a consortium of DOE national laboratories focused on response to COVID-19, with funding from the Coronavirus CARES Act. This work used resources, services, and support from the COVID-19 HPC Consortium (https://covid19-hpc-consortium.org/), a private-public effort uniting government, industry, and academic leaders who are volunteering free compute time and resources in support of COVID-19 research. The author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: This work was supported by the U.S. Department of Energy and National Institutes of Health. We thank the Argonne Leadership Computing Facility supported by the DOE under DE-AC02-06CH11357, the Oak Ridge Leadership Computing Facility at Oak Ridge National Laboratory supported by the DOE under Contract DE-AC05-00OR22725, and the National Energy Research Scientific Computing Center at Lawrence Berkeley National Laboratory supported by the DOE under Contract No. DE-AC02-05CH11231. We also thank the Texas Advanced Computing Center Frontera team, especially D. Stanzione and T. Cockerill, and for compute time made available through a Director’s Discretionary Allocation (NSF MCB-20024). NAMD and VMD are funded by NIH P41-GM104601. The NAMD team thanks Intel and M. Brown for contributing the AVX-512 tile list kernels. Anda Trifan acknowledges support from a DOE CSGF (DE-FG02-97ER25308). This research was supported by the Exascale Computing Project (17-SC-20-SC), a collaborative effort of the US DOE Office of Science and the National Nuclear Security Administration. Research was supported by the DOE through the National Virtual Biotechnology Laboratory, a consortium of DOE national laboratories focused on response to COVID-19, with funding from the Coronavirus CARES Act. This work used resources, services, and support from the COVID-19 HPC Consortium ( https://covid19-hpc-consortium.org/ ), a private-public effort uniting government, industry, and academic leaders who are volunteering free compute time and resources in support of COVID-19 research.

Funders	Funder number
National Virtual Biotechnology Laboratory
Texas Advanced Computing Center Frontera
National Science Foundation	MCB-20024
National Institutes of Health	P41-GM104601
U.S. Department of Energy	17-SC-20-SC, DE-AC05-00OR22725, DE-AC02-06CH11357, DE-FG02-97ER25308
Intel Corporation	AVX-512
National Nuclear Security Administration
National Energy Research Scientific Computing Center	DE-AC02-05CH11231

Keywords

High performance computing
Multi-resolution simulations
artificial intelligence
coronavirus 2019
severe acute respiratory syndrome coronavirus-2

UN SDGs

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

Access to Document

10.1177/10943420221113513

Cite this

Trifan, A., Gorgun, D., Salim, M., Li, Z., Brace, A., Zvyagin, M., Ma, H., Clyde, A., Clark, D., Hardy, D. J., Burnley, T., Huang, L., McCalpin, J., Emani, M., Yoo, H., Yin, J., Tsaris, A., Subbiah, V., Raza, T., ... Ramanathan, A. (2022). Intelligent resolution: Integrating Cryo-EM with AI-driven multi-resolution simulations to observe the severe acute respiratory syndrome coronavirus-2 replication-transcription machinery in action. International Journal of High Performance Computing Applications, 36(5-6), 603-623. https://doi.org/10.1177/10943420221113513

@article{3cecea8c76644650bcf27d21686c3b38,

title = "Intelligent resolution: Integrating Cryo-EM with AI-driven multi-resolution simulations to observe the severe acute respiratory syndrome coronavirus-2 replication-transcription machinery in action",

abstract = "The severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) replication transcription complex (RTC) is a multi-domain protein responsible for replicating and transcribing the viral mRNA inside a human cell. Attacking RTC function with pharmaceutical compounds is a pathway to treating COVID-19. Conventional tools, e.g. cryo-electron microscopy and all-atom molecular dynamics (AAMD), do not provide sufficiently high resolution or timescale to capture important dynamics of this molecular machine. Consequently, we develop an innovative workflow that bridges the gap between these resolutions, using mesoscale fluctuating finite element analysis (FFEA) continuum simulations and a hierarchy of AI-methods that continually learn and infer features for maintaining consistency between AAMD and FFEA simulations. We leverage a multi-site distributed workflow manager to orchestrate AI, FFEA, and AAMD jobs, providing optimal resource utilization across HPC centers. Our study provides unprecedented access to study the SARS-CoV-2 RTC machinery, while providing general capability for AI-enabled multi-resolution simulations at scale.",

keywords = "High performance computing, Multi-resolution simulations, artificial intelligence, coronavirus 2019, severe acute respiratory syndrome coronavirus-2",

author = "Anda Trifan and Defne Gorgun and Michael Salim and Zongyi Li and Alexander Brace and Maxim Zvyagin and Heng Ma and Austin Clyde and David Clark and Hardy, {David J.} and Tom Burnley and Lei Huang and John McCalpin and Murali Emani and Hyenseung Yoo and Junqi Yin and Aristeidis Tsaris and Vishal Subbiah and Tanveer Raza and Jessica Liu and Noah Trebesch and Geoffrey Wells and Venkatesh Mysore and Thomas Gibbs and James Phillips and Chennubhotla, {S. Chakra} and Ian Foster and Rick Stevens and Anima Anandkumar and Venkatram Vishwanath and Stone, {John E.} and Emad Tajkhorshid and Harris, {Sarah A.} and Arvind Ramanathan",

note = "Publisher Copyright: {\textcopyright} The Author(s) 2022.",

year = "2022",

month = nov,

doi = "10.1177/10943420221113513",

language = "English",

volume = "36",

pages = "603--623",

journal = "International Journal of High Performance Computing Applications",

issn = "1094-3420",

publisher = "SAGE Publications",

number = "5-6",

}

Trifan, A, Gorgun, D, Salim, M, Li, Z, Brace, A, Zvyagin, M, Ma, H, Clyde, A, Clark, D, Hardy, DJ, Burnley, T, Huang, L, McCalpin, J, Emani, M, Yoo, H, Yin, J, Tsaris, A, Subbiah, V, Raza, T, Liu, J, Trebesch, N, Wells, G, Mysore, V, Gibbs, T, Phillips, J, Chennubhotla, SC, Foster, I, Stevens, R, Anandkumar, A, Vishwanath, V, Stone, JE, Tajkhorshid, E, Harris, SA & Ramanathan, A 2022, 'Intelligent resolution: Integrating Cryo-EM with AI-driven multi-resolution simulations to observe the severe acute respiratory syndrome coronavirus-2 replication-transcription machinery in action', International Journal of High Performance Computing Applications, vol. 36, no. 5-6, pp. 603-623. https://doi.org/10.1177/10943420221113513

Intelligent resolution: Integrating Cryo-EM with AI-driven multi-resolution simulations to observe the severe acute respiratory syndrome coronavirus-2 replication-transcription machinery in action. / Trifan, Anda; Gorgun, Defne; Salim, Michael et al.
In: International Journal of High Performance Computing Applications, Vol. 36, No. 5-6, 11.2022, p. 603-623.

Research output: Contribution to journal › Article › peer-review

TY - JOUR

T1 - Intelligent resolution

T2 - Integrating Cryo-EM with AI-driven multi-resolution simulations to observe the severe acute respiratory syndrome coronavirus-2 replication-transcription machinery in action

AU - Trifan, Anda

AU - Gorgun, Defne

AU - Salim, Michael

AU - Li, Zongyi

AU - Brace, Alexander

AU - Zvyagin, Maxim

AU - Ma, Heng

AU - Clyde, Austin

AU - Clark, David

AU - Hardy, David J.

AU - Burnley, Tom

AU - Huang, Lei

AU - McCalpin, John

AU - Emani, Murali

AU - Yoo, Hyenseung

AU - Yin, Junqi

AU - Tsaris, Aristeidis

AU - Subbiah, Vishal

AU - Raza, Tanveer

AU - Liu, Jessica

AU - Trebesch, Noah

AU - Wells, Geoffrey

AU - Mysore, Venkatesh

AU - Gibbs, Thomas

AU - Phillips, James

AU - Chennubhotla, S. Chakra

AU - Foster, Ian

AU - Stevens, Rick

AU - Anandkumar, Anima

AU - Vishwanath, Venkatram

AU - Stone, John E.

AU - Tajkhorshid, Emad

AU - Harris, Sarah A.

AU - Ramanathan, Arvind

PY - 2022/11

Y1 - 2022/11

N2 - The severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) replication transcription complex (RTC) is a multi-domain protein responsible for replicating and transcribing the viral mRNA inside a human cell. Attacking RTC function with pharmaceutical compounds is a pathway to treating COVID-19. Conventional tools, e.g. cryo-electron microscopy and all-atom molecular dynamics (AAMD), do not provide sufficiently high resolution or timescale to capture important dynamics of this molecular machine. Consequently, we develop an innovative workflow that bridges the gap between these resolutions, using mesoscale fluctuating finite element analysis (FFEA) continuum simulations and a hierarchy of AI-methods that continually learn and infer features for maintaining consistency between AAMD and FFEA simulations. We leverage a multi-site distributed workflow manager to orchestrate AI, FFEA, and AAMD jobs, providing optimal resource utilization across HPC centers. Our study provides unprecedented access to study the SARS-CoV-2 RTC machinery, while providing general capability for AI-enabled multi-resolution simulations at scale.

AB - The severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) replication transcription complex (RTC) is a multi-domain protein responsible for replicating and transcribing the viral mRNA inside a human cell. Attacking RTC function with pharmaceutical compounds is a pathway to treating COVID-19. Conventional tools, e.g. cryo-electron microscopy and all-atom molecular dynamics (AAMD), do not provide sufficiently high resolution or timescale to capture important dynamics of this molecular machine. Consequently, we develop an innovative workflow that bridges the gap between these resolutions, using mesoscale fluctuating finite element analysis (FFEA) continuum simulations and a hierarchy of AI-methods that continually learn and infer features for maintaining consistency between AAMD and FFEA simulations. We leverage a multi-site distributed workflow manager to orchestrate AI, FFEA, and AAMD jobs, providing optimal resource utilization across HPC centers. Our study provides unprecedented access to study the SARS-CoV-2 RTC machinery, while providing general capability for AI-enabled multi-resolution simulations at scale.

KW - High performance computing

KW - Multi-resolution simulations

KW - artificial intelligence

KW - coronavirus 2019

KW - severe acute respiratory syndrome coronavirus-2

UR - http://www.scopus.com/inward/record.url?scp=85130366071&partnerID=8YFLogxK

U2 - 10.1177/10943420221113513

DO - 10.1177/10943420221113513

M3 - Article

AN - SCOPUS:85130366071

SN - 1094-3420

VL - 36

SP - 603

EP - 623

JO - International Journal of High Performance Computing Applications

JF - International Journal of High Performance Computing Applications

IS - 5-6

ER -

Trifan A, Gorgun D, Salim M, Li Z, Brace A, Zvyagin M et al. Intelligent resolution: Integrating Cryo-EM with AI-driven multi-resolution simulations to observe the severe acute respiratory syndrome coronavirus-2 replication-transcription machinery in action. International Journal of High Performance Computing Applications. 2022 Nov;36(5-6):603-623. doi: 10.1177/10943420221113513

Intelligent resolution: Integrating Cryo-EM with AI-driven multi-resolution simulations to observe the severe acute respiratory syndrome coronavirus-2 replication-transcription machinery in action

Abstract

Funding

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this