High-throughput virtual laboratory for drug discovery using massive datasets

Glaser, Jens; Vermaas, Josh V.; Rogers, David M.; Larkin, Jeff; LeGrand, Scott; Boehm, Swen; Baker, Matthew B.; Scheinberg, Aaron; Tillack, Andreas F.; Thavappiragasam, Mathialakan; Sedova, Ada; Hernandez, Oscar

doi:10.1177/10943420211001565

High-throughput virtual laboratory for drug discovery using massive datasets

Journal Article · Tue Mar 23 00:00:00 EDT 2021 · International Journal of High Performance Computing Applications

DOI:https://doi.org/10.1177/10943420211001565· OSTI ID:1772255

^[1]; ^[1]; ^[1]; Larkin, Jeff ^[2]; LeGrand, Scott ^[2]; Boehm, Swen ^[3]; Baker, Matthew B. ^[3]; Scheinberg, Aaron ^[4]; Tillack, Andreas F. ^[5]; Thavappiragasam, Mathialakan ^[6]; Sedova, Ada ^[6]; Hernandez, Oscar ^[3]

National Center for Computational Sciences, Oak Ridge National Laboratory, Oak Ridge, TN, USA
NVIDIA Corporation, Santa Clara, CA, USA
Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA
Jubilee Development, Cambridge, MA, USA
Scripps Research, San Diego, CA, USA
Biosciences Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA

Time-to-solution for structure-based screening of massive chemical databases for COVID-19 drug discovery has been decreased by an order of magnitude, and a virtual laboratory has been deployed at scale on up to 27,612 GPUs on the Summit supercomputer, allowing an average molecular docking of 19,028 compounds per second. Over one billion compounds were docked to two SARS-CoV-2 protein structures with full optimization of ligand position and 20 poses per docking, each in under 24 hours. GPU acceleration and high-throughput optimizations of the docking program produced 350× mean speedup over the CPU version (50× speedup per node). GPU acceleration of both feature calculation for machine-learning based scoring and distributed database queries reduced processing of the 2.4 TB output by orders of magnitude. The resulting 50× speedup for the full pipeline reduces an initial 43 day runtime to 21 hours per protein for providing high-scoring compounds to experimental collaborators for validation assays.

View Journal Article

Research Organization:: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Sponsoring Organization:: USDOE; USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)

Grant/Contract Number:: AC05-00OR22725

OSTI ID:: 1772255

Alternate ID(s):: OSTI ID: 1811403

Journal Information:: International Journal of High Performance Computing Applications, Journal Name: International Journal of High Performance Computing Applications Journal Issue: 5 Vol. 35; ISSN 1094-3420

Publisher:: SAGE PublicationsCopyright Statement

Country of Publication:: United States

Language:: English

References (33)

FireWorks: a dynamic workflow system designed for high-throughput applications: FireWorks: A Dynamic Workflow System Designed for High-Throughput Applications Jain, Anubhav; Ong, Shyue Ping; Chen, Wei Concurrency and Computation: Practice and Experience, Vol. 27, Issue 17 https://doi.org/10.1002/cpe.3505	journal	May 2015
AutoDock4 and AutoDockTools4: Automated docking with selective receptor flexibility Morris, Garrett M.; Huey, Ruth; Lindstrom, William Journal of Computational Chemistry, Vol. 30, Issue 16 https://doi.org/10.1002/jcc.21256	journal	December 2009
AutoDock Vina: Improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading Trott, Oleg; Olson, Arthur J. Journal of Computational Chemistry https://doi.org/10.1002/jcc.21334	journal	January 2009
DOCK 6: Impact of new features and current docking performance Allen, William J.; Balius, Trent E.; Mukherjee, Sudipto Journal of Computational Chemistry, Vol. 36, Issue 15 https://doi.org/10.1002/jcc.23905	journal	April 2015
Rapid Identification of Potential Inhibitors of SARS‐CoV‐2 Main Protease by Deep Docking of 1.3 Billion Compounds Ton, Anh‐Tien; Gentile, Francesco; Hsing, Michael Molecular Informatics, Vol. 39, Issue 8 https://doi.org/10.1002/minf.202000028	journal	March 2020
From machine learning to deep learning: Advances in scoring functions for protein–ligand docking Shen, Chao; Ding, Junjie; Wang, Zhe WIREs Computational Molecular Science, Vol. 10, Issue 1 https://doi.org/10.1002/wcms.1429	journal	June 2019
D3R Grand Challenge 4: prospective pose prediction of BACE1 ligands with AutoDock-GPU Santos-Martins, Diogo; Eberhardt, Jerome; Bianco, Giulia Journal of Computer-Aided Molecular Design, Vol. 33, Issue 12 https://doi.org/10.1007/s10822-019-00241-9	journal	November 2019
Selecting machine-learning scoring functions for structure-based virtual screening Ballester, Pedro J. Drug Discovery Today: Technologies, Vol. 32-33 https://doi.org/10.1016/j.ddtec.2020.09.001	journal	December 2019
Improved Method of Structure-Based Virtual Screening via Interaction-Energy-Based Learning Yasuo, Nobuaki; Sekijima, Masakazu Journal of Chemical Information and Modeling, Vol. 59, Issue 3 https://doi.org/10.1021/acs.jcim.8b00673	journal	October 2018
Deep Docking: A Deep Learning Platform for Augmentation of Structure Based Drug Discovery Gentile, Francesco; Agrawal, Vibudh; Hsing, Michael ACS Central Science, Vol. 6, Issue 6 https://doi.org/10.1021/acscentsci.0c00229	journal	May 2020
Rational design of quinazoline-based irreversible inhibitors of human erythrocyte purine nucleoside phosphorylase Dempcy, Robert O.; Skibo, Edward B. Biochemistry, Vol. 30, Issue 34 https://doi.org/10.1021/bi00098a028	journal	August 1991
FRED Pose Prediction and Virtual Screening Accuracy McGann, Mark Journal of Chemical Information and Modeling, Vol. 51, Issue 3 https://doi.org/10.1021/ci100436p	journal	February 2011
Accelerating Molecular Docking Calculations Using Graphics Processing Units Korb, Oliver; Stützle, Thomas; Exner, Thomas E. Journal of Chemical Information and Modeling, Vol. 51, Issue 4 https://doi.org/10.1021/ci100459b	journal	March 2011
Stochastic Voyages into Uncharted Chemical Space Produce a Representative Library of All Possible Drug-Like Compounds Virshup, Aaron M.; Contreras-García, Julia; Wipf, Peter Journal of the American Chemical Society, Vol. 135, Issue 19 https://doi.org/10.1021/ja401184g	journal	May 2013
Using shape complementarity as an initial screen in designing ligands for a receptor binding site of known three-dimensional structure DesJarlais, Renee L.; Sheridan, Robert P.; Seibel, George L. Journal of Medicinal Chemistry, Vol. 31, Issue 4 https://doi.org/10.1021/jm00399a006	journal	April 1988
Glide: A New Approach for Rapid, Accurate Docking and Scoring. 1. Method and Assessment of Docking Accuracy Friesner, Richard A.; Banks, Jay L.; Murphy, Robert B. Journal of Medicinal Chemistry, Vol. 47, Issue 7 https://doi.org/10.1021/jm0306430	journal	March 2004
Rational design of potent sialidase-based inhibitors of influenza virus replication von Itzstein, Mark; Wu, Wen-Yang; Kok, Gaik B. Nature, Vol. 363, Issue 6428 https://doi.org/10.1038/363418a0	journal	June 1993
Structural plasticity of SARS-CoV-2 3CL Mpro active site cavity revealed by room temperature X-ray crystallography Kneller, Daniel W.; Phillips, Gwyndalyn; O’Neill, Hugh M. Nature Communications, Vol. 11, Issue 1 https://doi.org/10.1038/s41467-020-16954-7	journal	June 2020
Ultra-large library docking for discovering new chemotypes Lyu, Jiankun; Wang, Sheng; Balius, Trent E. Nature, Vol. 566, Issue 7743 https://doi.org/10.1038/s41586-019-0917-9	journal	February 2019
An open-source drug discovery platform enables ultra-large virtual screens Gorgulla, Christoph; Boeszoermenyi, Andras; Wang, Zi-Fu Nature, Vol. 580, Issue 7805 https://doi.org/10.1038/s41586-020-2117-z	journal	March 2020
Protein-Ligand Blind Docking Using QuickVina-W With Inter-Process Spatio-Temporal Integration Hassan, Nafisa M.; Alhossary, Amr A.; Mu, Yuguang Scientific Reports, Vol. 7, Issue 1 https://doi.org/10.1038/s41598-017-15571-7	journal	November 2017
Performance of machine-learning scoring functions in structure-based virtual screening Wójcikowski, Maciej; Ballester, Pedro J.; Siedlecki, Pawel Scientific Reports, Vol. 7, Issue 1 https://doi.org/10.1038/srep46710	journal	April 2017
How to Discover Antiviral Drugs Quickly Parks, Jerry M.; Smith, Jeremy C. New England Journal of Medicine, Vol. 382, Issue 23 https://doi.org/10.1056/NEJMcibr2007042	journal	June 2020
Machine learning classification can reduce false positives in structure-based virtual screening Adeshina, Yusuf O.; Deeds, Eric J.; Karanicolas, John Proceedings of the National Academy of Sciences, Vol. 117, Issue 31 https://doi.org/10.1073/pnas.2000585117	journal	July 2020
Fast, accurate, and reliable molecular docking with QuickVina 2 Alhossary, Amr; Handoko, Stephanus Daniel; Mu, Yuguang Bioinformatics, Vol. 31, Issue 13 https://doi.org/10.1093/bioinformatics/btv082	journal	February 2015
GPU-Accelerated Drug Discovery with Docking on the Summit Supercomputer: Porting, Optimization, and Application to COVID-19 Research LeGrand, Scott; Scheinberg, Aaron; Tillack, Andreas F. BCB '20: 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, Proceedings of the 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics https://doi.org/10.1145/3388440.3412472	conference	September 2020
Empirical evaluation across multiple GPU-accelerated DBMSes Chu, Hawon; Kim, Seounghyun; Lee, Joo-Young SIGMOD/PODS '20: International Conference on Management of Data, Proceedings of the 16th International Workshop on Data Management on New Hardware https://doi.org/10.1145/3399666.3399907	conference	June 2020
High performance in silico virtual drug screening on many-core processors McIntosh-Smith, Simon; Price, James; Sessions, Richard B. The International Journal of High Performance Computing Applications, Vol. 29, Issue 2 https://doi.org/10.1177/1094342014528252	journal	April 2014
Multilevel Parallelization of AutoDock 4.2 Norgan, Andrew P.; Coffman, Paul K.; Kocher, Jean-Pierre A. Journal of Cheminformatics, Vol. 3, Issue 1 https://doi.org/10.1186/1758-2946-3-12	journal	April 2011
Open Drug Discovery Toolkit (ODDT): a new open-source player in the drug discovery field Wójcikowski, Maciej; Zielenkiewicz, Piotr; Siedlecki, Pawel Journal of Cheminformatics, Vol. 7, Issue 1 https://doi.org/10.1186/s13321-015-0078-2	journal	June 2015
rDock: A Fast, Versatile and Open Source Program for Docking Ligands to Proteins and Nucleic Acids Ruiz-Carmona, Sergio; Alvarez-Garcia, Daniel; Foloppe, Nicolas PLoS Computational Biology, Vol. 10, Issue 4 https://doi.org/10.1371/journal.pcbi.1003571	journal	April 2014
Ligand Pose and Orientational Sampling in Molecular Docking Coleman, Ryan G.; Carchia, Michael; Sterling, Teague PLoS ONE, Vol. 8, Issue 10 https://doi.org/10.1371/journal.pone.0075992	journal	October 2013
GeauxDock: Accelerating Structure-Based Virtual Screening with Heterogeneous Computing Fang, Ye; Ding, Yun; Feinstein, Wei P. PLOS ONE, Vol. 11, Issue 7 https://doi.org/10.1371/journal.pone.0158898	journal	July 2016

Similar Records

Supercomputer-Based Ensemble Docking Drug Discovery Pipeline with Application to Covid-19

Journal Article · Tue Dec 15 23:00:00 EST 2020 · Journal of Chemical Information and Modeling · OSTI ID:1778008

Supercomputer-Based Ensemble Docking Drug Discovery Pipeline with Application to Covid-19

Journal Article · Tue Dec 15 19:00:00 EST 2020 · Journal of Chemical Information and Modeling · OSTI ID:1755144

Related Subjects

97 MATHEMATICS AND COMPUTING
GPU acceleration
drug discovery
high-performance database query
high-throughput virtual screening

High-throughput virtual laboratory for drug discovery using massive datasets

Citation Formats

References (33)

Similar Records

Related Subjects