Accelerating Therapeutics for Opportunities in Medicine: A Paradigm Shift in Drug Discovery
Abstract
Conventional drug discovery is long and costly, and suffers from high attrition rates, often leaving patients with limited or expensive treatment options. Recognizing the overwhelming need to accelerate this process and increase success, the ATOM consortium was formed by government, industry, and academic partners in October 2017. ATOM applies a team science and open-source approach to foster a paradigm shift in drug discovery. ATOM is developing and validating a precompetitive, preclinical, small molecule drug discovery platform that simultaneously optimizes pharmacokinetics, toxicity, protein-ligand interactions, systems-level models, molecular design, and novel compound generation. To achieve this, the ATOM Modeling Pipeline (AMPL) has been developed to enable advanced and emerging machine learning (ML) approaches to build models from diverse historical drug discovery data. This modular pipeline has been designed to couple with a generative algorithm that optimizes multiple parameters necessary for drug discovery. ATOM's approach is to consider the full pharmacology and therapeutic window of the drug concurrently, through computationally-driven design, thereby reducing the number of molecules that are selected for experimental validation. Here, we discuss the role of collaborative efforts such as consortia and public-private partnerships in accelerating cross disciplinary innovation and the development of opensource tools for drug discovery.
- Authors:
- Publication Date:
- Research Org.:
- Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC)
- OSTI Identifier:
- 1635417
- Alternate Identifier(s):
- OSTI ID: 1817145
- Grant/Contract Number:
- AC52-07NA27344
- Resource Type:
- Published Article
- Journal Name:
- Frontiers in Pharmacology
- Additional Journal Information:
- Journal Name: Frontiers in Pharmacology Journal Volume: 11; Journal ID: ISSN 1663-9812
- Publisher:
- Frontiers Media SA
- Country of Publication:
- Switzerland
- Language:
- English
- Subject:
- 60 APPLIED LIFE SCIENCES; artificial intelligence; machine learning; drug discovery and development; data science; in silico modeling
Citation Formats
Hinkson, Izumi V., Madej, Benjamin, and Stahlberg, Eric A. Accelerating Therapeutics for Opportunities in Medicine: A Paradigm Shift in Drug Discovery. Switzerland: N. p., 2020.
Web. doi:10.3389/fphar.2020.00770.
Hinkson, Izumi V., Madej, Benjamin, & Stahlberg, Eric A. Accelerating Therapeutics for Opportunities in Medicine: A Paradigm Shift in Drug Discovery. Switzerland. https://doi.org/10.3389/fphar.2020.00770
Hinkson, Izumi V., Madej, Benjamin, and Stahlberg, Eric A. Tue .
"Accelerating Therapeutics for Opportunities in Medicine: A Paradigm Shift in Drug Discovery". Switzerland. https://doi.org/10.3389/fphar.2020.00770.
@article{osti_1635417,
title = {Accelerating Therapeutics for Opportunities in Medicine: A Paradigm Shift in Drug Discovery},
author = {Hinkson, Izumi V. and Madej, Benjamin and Stahlberg, Eric A.},
abstractNote = {Conventional drug discovery is long and costly, and suffers from high attrition rates, often leaving patients with limited or expensive treatment options. Recognizing the overwhelming need to accelerate this process and increase success, the ATOM consortium was formed by government, industry, and academic partners in October 2017. ATOM applies a team science and open-source approach to foster a paradigm shift in drug discovery. ATOM is developing and validating a precompetitive, preclinical, small molecule drug discovery platform that simultaneously optimizes pharmacokinetics, toxicity, protein-ligand interactions, systems-level models, molecular design, and novel compound generation. To achieve this, the ATOM Modeling Pipeline (AMPL) has been developed to enable advanced and emerging machine learning (ML) approaches to build models from diverse historical drug discovery data. This modular pipeline has been designed to couple with a generative algorithm that optimizes multiple parameters necessary for drug discovery. ATOM's approach is to consider the full pharmacology and therapeutic window of the drug concurrently, through computationally-driven design, thereby reducing the number of molecules that are selected for experimental validation. Here, we discuss the role of collaborative efforts such as consortia and public-private partnerships in accelerating cross disciplinary innovation and the development of opensource tools for drug discovery.},
doi = {10.3389/fphar.2020.00770},
journal = {Frontiers in Pharmacology},
number = ,
volume = 11,
place = {Switzerland},
year = {Tue Jun 30 00:00:00 EDT 2020},
month = {Tue Jun 30 00:00:00 EDT 2020}
}
https://doi.org/10.3389/fphar.2020.00770
Works referenced in this record:
Drug discovery and development: Role of basic biological research
journal, November 2017
- Mohs, Richard C.; Greig, Nigel H.
- Alzheimer's & Dementia: Translational Research & Clinical Interventions, Vol. 3, Issue 4
Lessons from 60 years of pharmaceutical innovation
journal, December 2009
- Munos, Bernard
- Nature Reviews Drug Discovery, Vol. 8, Issue 12
Innovation in the pharmaceutical industry: New estimates of R&D costs
journal, May 2016
- DiMasi, Joseph A.; Grabowski, Henry G.; Hansen, Ronald W.
- Journal of Health Economics, Vol. 47
The cornucopia of meaningful leads: Applying deep adversarial autoencoders for new molecule development in oncology
journal, December 2016
- Kadurin, Artur; Aliper, Alexander; Kazennov, Andrey
- Oncotarget, Vol. 8, Issue 7
Deep Neural Nets as a Method for Quantitative Structure–Activity Relationships
journal, February 2015
- Ma, Junshui; Sheridan, Robert P.; Liaw, Andy
- Journal of Chemical Information and Modeling, Vol. 55, Issue 2
Reinforced Adversarial Neural Computer for de Novo Molecular Design
journal, May 2018
- Putin, Evgeny; Asadulaev, Arip; Ivanenkov, Yan
- Journal of Chemical Information and Modeling, Vol. 58, Issue 6
Automated design of ligands to polypharmacological profiles
journal, December 2012
- Besnard, Jérémy; Ruda, Gian Filippo; Setola, Vincent
- Nature, Vol. 492, Issue 7428
Analyzing Learned Molecular Representations for Property Prediction
journal, July 2019
- Yang, Kevin; Swanson, Kyle; Jin, Wengong
- Journal of Chemical Information and Modeling, Vol. 59, Issue 8
Bringing together the academic drug discovery community
journal, October 2013
- Slusher, Barbara S.; Conn, P. Jeffrey; Frye, Stephen
- Nature Reviews Drug Discovery, Vol. 12, Issue 11
Be open about drug failures to speed up research
journal, November 2018
- Alteri, Enrica; Guizzaro, Lorenzo
- Nature, Vol. 563, Issue 7731
Molecular Generative Model Based on an Adversarially Regularized Autoencoder
journal, December 2019
- Hong, Seung Hwan; Ryu, Seongok; Lim, Jaechang
- Journal of Chemical Information and Modeling, Vol. 60, Issue 1
Mitigating risk in academic preclinical drug discovery
journal, April 2015
- Dahlin, Jayme L.; Inglese, James; Walters, Michael A.
- Nature Reviews Drug Discovery, Vol. 14, Issue 4
Deep learning enables rapid identification of potent DDR1 kinase inhibitors
journal, September 2019
- Zhavoronkov, Alex; Ivanenkov, Yan A.; Aliper, Alex
- Nature Biotechnology, Vol. 37, Issue 9
PotentialNet for Molecular Property Prediction
journal, November 2018
- Feinberg, Evan N.; Sur, Debnil; Wu, Zhenqin
- ACS Central Science, Vol. 4, Issue 11
De Novo Design of Bioactive Small Molecules by Artificial Intelligence
journal, January 2018
- Merk, Daniel; Friedrich, Lukas; Grisoni, Francesca
- Molecular Informatics, Vol. 37, Issue 1-2
The Current Status of Drug Discovery and Development as Originated in United States Academia: The Influence of Industrial and Academic Collaboration on Drug Discovery and Development
journal, July 2018
- Takebe, Tohru; Imai, Ryoka; Ono, Shunsuke
- Clinical and Translational Science, Vol. 11, Issue 6
Predictive Multitask Deep Neural Network Models for ADME-Tox Properties: Learning from Large Data Sets
journal, October 2018
- Wenzel, Jan; Matter, Hans; Schmidt, Friedemann
- Journal of Chemical Information and Modeling, Vol. 59, Issue 3
Opening Up to Precompetitive Collaboration
journal, October 2010
- Altshuler, J. S.; Balogh, E.; Barker, A. D.
- Science Translational Medicine, Vol. 2, Issue 52
Entangled Conditional Adversarial Autoencoder for de Novo Drug Discovery
journal, September 2018
- Polykovskiy, Daniil; Zhebrak, Alexander; Vetrov, Dmitry
- Molecular Pharmaceutics, Vol. 15, Issue 10
Rethinking drug design in the artificial intelligence era
journal, December 2019
- Schneider, Petra; Walters, W. Patrick; Plowright, Alleyn T.
- Nature Reviews Drug Discovery, Vol. 19, Issue 5
Curing Consortium Fatigue
journal, August 2013
- Papadaki, M.; Hirsch, G.
- Science Translational Medicine, Vol. 5, Issue 200
The application of discovery toxicology and pathology towards the design of safer pharmaceutical lead candidates
journal, August 2007
- Kramer, Jeffrey A.; Sagartz, John E.; Morris, Dale L.
- Nature Reviews Drug Discovery, Vol. 6, Issue 8
Generating Focused Molecule Libraries for Drug Discovery with Recurrent Neural Networks
journal, December 2017
- Segler, Marwin H. S.; Kogej, Thierry; Tyrchan, Christian
- ACS Central Science, Vol. 4, Issue 1
Catalyzing the critical path initiative: FDA's progress in drug development activities
journal, January 2015
- Parekh, A.; Buckman-Garner, S.; McCune, S.
- Clinical Pharmacology & Therapeutics, Vol. 97, Issue 3
Can open-source R&D reinvigorate drug research?
journal, August 2006
- Munos, Bernard
- Nature Reviews Drug Discovery, Vol. 5, Issue 9
Does size matter in R&D productivity? If not, what does?
journal, October 2013
- Ringel, Michael; Tollman, Peter; Hersch, Greg
- Nature Reviews Drug Discovery, Vol. 12, Issue 12
Molecular de-novo design through deep reinforcement learning
journal, September 2017
- Olivecrona, Marcus; Blaschke, Thomas; Engkvist, Ola
- Journal of Cheminformatics, Vol. 9, Issue 1
Deep Reinforcement Learning for Multiparameter Optimization in de novo Drug Design
journal, June 2019
- Ståhl, Niclas; Falkman, Göran; Karlsson, Alexander
- Journal of Chemical Information and Modeling, Vol. 59, Issue 7
Is open innovation the way forward for big pharma?
journal, February 2010
- Hunter, Jackie; Stephens, Susie
- Nature Reviews Drug Discovery, Vol. 9, Issue 2
How to improve R&D productivity: the pharmaceutical industry's grand challenge
journal, February 2010
- Paul, Steven M.; Mytelka, Daniel S.; Dunwiddie, Christopher T.
- Nature Reviews Drug Discovery, Vol. 9, Issue 3
Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules
journal, January 2018
- Gómez-Bombarelli, Rafael; Wei, Jennifer N.; Duvenaud, David
- ACS Central Science, Vol. 4, Issue 2
Application of Generative Autoencoder in De Novo Molecular Design
journal, December 2017
- Blaschke, Thomas; Olivecrona, Marcus; Engkvist, Ola
- Molecular Informatics, Vol. 37, Issue 1-2
ESOL: Estimating Aqueous Solubility Directly from Molecular Structure
journal, May 2004
- Delaney, John S.
- Journal of Chemical Information and Computer Sciences, Vol. 44, Issue 3
Artificial Intelligence and Pharmacometrics: Time to Embrace, Capitalize, and Advance?
journal, June 2019
- Chaturvedula, Ayyappa; Calad‐Thomson, Stacie; Liu, Chao
- CPT: Pharmacometrics & Systems Pharmacology
Applications of machine learning in drug discovery and development
journal, April 2019
- Vamathevan, Jessica; Clark, Dominic; Czodrowski, Paul
- Nature Reviews Drug Discovery, Vol. 18, Issue 6
The Role of Public–Private Partnerships in Catalyzing the Critical Path
journal, July 2017
- Maxfield, Kimberly E.; Buckman‐Garner, ShaAvhrée; Parekh, Ameeta
- Clinical and Translational Science, Vol. 10, Issue 6