About Us

 

Transforming drug discovery

The Accelerating Therapeutics for Opportunities in Medicine (ATOM) consortium is a public-private partnership with the mission of transforming drug discovery by accelerating the development of more effective therapies for patients.

 
 
 

History

In June 2016, GSK, the Department of Energy, and the National Cancer Institute announced their intent to create the ATOM partnership as one of the Cancer Moonshot task forces, with funding support under the 21st Century Cures Act.

The ATOM consortium was officially established in October 2017.

ATOM founding members are GSK, Lawrence Livermore National Laboratory, Frederick National Laboratory for Cancer Research, and the University of California, San Francisco. 

 

In March 2021, the U.S. Department of Energy’s Argonne, Brookhaven and Oak Ridge National Laboratories joined the ATOM Consortium to further develop ATOM’s artificial intelligence (AI) - driven drug discovery platform.

 

Vision

Our goal is to transform drug discovery from a slow, sequential, and high-failure process into a rapid, integrated, and patient-centric model. We are integrating high performance computing, diverse biological data, and emerging biotechnologies to create a new pre-competitive platform for drug discovery.

 
 

What We Do

 

ATOM is developing a pre-clinical drug design and optimization platform that leads with computation to help shorten the drug discovery timeline. ATOM’s approach employs data-driven modeling and generative molecular design to determine design criteria that consider pharmacology, safety, efficacy, and developability in the context of lead optimization. ATOM’s active learning design platform aims to selectively incorporate results from mechanistic simulation and human-relevant experimentation to generate and optimize new drug candidates significantly faster and with greater success than conventional processes.

 

Consortium Members

 

UC San Francisco is providing expertise from a long-history of innovation in medicine and drug discovery combined with its strengths in cancer and translation of technologies and therapeutics to improve the lives of patients.

Frederick National Laboratory, on behalf of the National Cancer Institute, is contributing scientific expertise in precision oncology, computational chemistry and cancer biology, as well as support for open sharing of datasets and predictive modeling and simulation tools. 

 
 

Lawrence Livermore National Laboratory is contributing its best-in-class supercomputers, including its next-generation system Sierra, as well as its expertise and innovative approaches to modeling and simulation, cognitive computing, machine learning, and algorithm development. More broadly, by applying high-performance computing to the ambitious problem of cancer therapy, the Department of Energy and National Nuclear Security Administration hopes to accelerate technologies vital to its core missions.

 
 

Argonne National Laboratory will leverage its Leadership Computing Facility to perform advanced simulations in life sciences, including molecular biology, microbiology, protein chemistry, bioinformatics, computational biology, environmental sciences and other scientific fields.

Brookhaven National Laboratory will contribute scalable high-performance computing frameworks and software that support optimal experimental design active-learning workflows for advanced simulations. These frameworks employ machine learning that can enhance cancer drug therapy research and design.

 
 

Oak Ridge National Laboratory will apply its unique capabilities in high-performance computing, data-intensive science and biological systems to examine the complex and dynamic interactions between candidate molecules and the human body, with the goal of boosting the success rate when molecules go to clinical trials.

 
 
The goals of ATOM are tightly aligned with those of the 21st Century Cures Act, which aims in part to enable a greater number of therapies to reach more patients more quickly.
— David Heimbrook, Former Laboratory Director at FNLCR

ATOM Webinar Series

Join Jim Brase, ATOM Co-lead, in our latest Webinar, as he explored ATOM’s molecular design approach for accelerated drug discovery.

In the webinar, Jim Brase, talked about ATOM’s molecular design approach, how ATOM has successfully demonstrated multiparameter property optimization across efficacy, safety, pharmacokinetics, and developability, and how these systems have the potential to guide and optimize experimental data collection and design validation, and how ATOM is working towards closing the computing-experimental feedback loop.

#theATOMapproach

 

Speaker: Jim Brase, ATOM Co-lead

Jim Brase is the Deputy Associate Director for Computing at Lawrence Livermore National Laboratory (LLNL). He leads LLNL research in the application of high-performance computing, large-scale data science, and simulation to a broad range of national security and science missions. Jim is Co-lead of the ATOM Consortium for computational acceleration of drug discovery, and on the leadership team of the COVID-19 HPC Consortium. Jim’s research interests focus on the intersection of machine learning, simulation, and high-performance computing. He is currently leading efforts on large-scale computing for life science, biosecurity, and nuclear security applications. In his previous position as LLNL’s Deputy Program Director for Intelligence, Jim led efforts in intelligence and cybersecurity R&D.

 

Webinar Take Away

  • Computing and machine learning can accelerate molecular optimization for applications ranging from cancer to infectious disease therapeutics

  • ATOM has successfully demonstrated multiparameter property optimization across efficacy, safety, pharmacokinetics, and developability

  • These systems have the potential to guide and optimize experimental data collection and design validation but much work remains in closing the computing-experimental feedback loop


Find Past Webinar Presentations & Recording

John Baldoni: An Alternative Approach and Business Model to Accelerate Drug Discovery

Jim Brase: The ATOM molecular design approach for accelerated drug discovery

We must do all that we can to reduce the time it takes to get medicines to patients.
— John Baldoni, ATOM Founder
membership.png

Scientific Overview

 

ATOM Modeling Pipeline (AMPL)

 
 

An open-source, modular, extensible software pipeline for building and sharing models to advance in silico drug discovery


The ATOM Modeling PipeLine (AMPL) extends the functionality of DeepChem and supports an array of machine learning and molecular featurization tools. AMPL is an end-to-end data-driven modeling pipeline to generate machine learning models that can predict key safety and pharmacokinetic-relevant parameters. AMPL has been benchmarked on a large collection of pharmaceutical datasets covering a wide range of parameters. The AMPL manuscript was accepted for publication in American Chemical Society and it is available on GitHub.

 
 
 

Introducing the AMPL Tutorial Series

Our tutorial series is set up for our user community to take a hands-on approach to employing AMPL in a step-by-step guide. These tutorials assume that you are an intermediate Python user or new to machine learning to build a foundational framework that you can use to do meaningful work.

The tutorials present an end-to-end pipeline that builds machine learning models for predicting chemical properties. We have created easy to follow tutorials that walk through the steps necessary to install AMPL, curate a dataset, effectively train and evaluate a machine learning model, and use that model to make predictions.

 

Current Research Projects

 

Scientists at ATOM are tackling a wide range of challenges in drug design. Read our recent abstracts to learn more about our ongoing projects.

 
 
Bringing the experience and expertise from three additional DOE national laboratories to ATOM’s current partners,…., reinforces ATOM as a valuable national resource to create powerful new capabilities for the cancer research community, building collaborations and driving advances in translational research to develop treatments more quickly.
— Eric Stahlberg, director of the Biomedical Informatics and Data Science group at FNL and co-lead of the ATOM consortium 
leadership.png

Leadership

 

Leadership Team & Joint Research Committee (JRC)

Jim Brase.jpg

Jim Brase, M.S.

ATOM Co-lead / ATOM JRC Member / Deputy Associate Director for Computation / Lawrence Livermore National Laboratory
 

Eric Stahlberg.png

Eric Stahlberg, Ph.D

ATOM Co-lead / ATOM JRC Member / Director, Biomedical Informatics and Data Science / Frederick National Laboratory for Cancer Research

FJAlexander_headshot.jpg

Francis J. Alexander, Ph.D. 

ATOM JRC Member / Deputy Director, Computational Science Initiative / Brookhaven National Laboratory

Belinda Akpa, Ph.D.

ATOM JRC Member / Senior Staff Scientist, Quantitative Systems Biology / Oak Ridge National Laboratory

Michelle Arkin.jpg

Michelle Arkin, Ph.D.

ATOM JRC Member / Professor, Department of Pharmaceutical Chemistry / University of California, San Francisco

Thomas+Brettin+v2.jpg

Thomas Brettin, M.S.

ATOM JRC Member / Strategic Program Manager / Argonne National Laboratory

Dwight Nissley.png

Dwight Nissley, Ph.D.

ATOM JRC Member / Director, Cancer Research Technology Program / Frederick National Laboratory for Cancer Research

Rick+Stevens.jpg

Rick Stevens, Ph.D.

ATOM JRC Member / Associate Laboratory Director for Computing, Environment and Life Sciences / Professor of Computer Science, University of Chicago / Argonne National Laboratory

 

Governing Board

Screen Shot 2021-03-15 at 4.48.49 PM.png

John Baldoni, Ph.D.

ATOM Governing Board Chair / ATOM Founder
 

Alan Ashworth.jpg

Alan Ashworth, Ph.D., F.R.S.

President / UCSF Helen Diller Family Comprehensive Cancer Center / University of California, San Francisco

Ethan Dmitrovsky 2.jpg

Ethan Dmitrovsky, M.D.

Laboratory Director / Frederick National Laboratory for Cancer Research

Patricia Falcone 3.jpg

Patricia Falcone, Ph.D.

Deputy Director for Science and Technology / Lawrence Livermore National Laboratory

Freedman-+Pic.jpg

Leonard P. Freedman, Ph.D.

Chief Science Officer / Frederick National Laboratory for Cancer Research

Screen Shot 2021-05-06 at 2.51.32 PM.png

Mohammad A. Khaleel, Ph.D

Deputy of Science and Technology (Interim) and Projects / Oak Ridge National Laboratory

Barry Selick.png

Barry Selick, Ph.D.

Vice Chancellor, Business Development, Innovation, and Partnerships / University of California, San Francisco

Screen Shot 2021-05-11 at 9.14.51 AM.png

Stephen K. Streiffer, Ph.D.

Deputy Laboratory Director for Science and Technology and Interim Associate Laboratory Director for Photon Sciences / Argonne National Laboratory

Screen Shot 2021-05-11 at 9.23.21 AM.png

Robert Tribble, Ph.D.

Deputy Director for Science and Technology / Brookhaven National Laboratory

John MacWilliams.jpg
 

John MacWilliams, J.D., M.S.

ATOM Governing Board Chair Emeritus

 
 
 
Across the pharmaceutical industry, people are beginning to realize that AI has the ability to speed things up considerably. Different organizations can bring different things to the table — in our case [Argonne National Laboratory], it’s advanced computing and machine learning expertise.
— Thomas Brettin, Strategic Program Manager at Argonne National Laboratory, ATOM Joint Research member
Screen Shot 2021-09-23 at 2.12.05 PM.png

Publications

 

DOI: https://doi.org/10.1016/j.aichem.2023.100004

Date: June 2023

Journal: Artificial Intelligence Chemistry

Evaluating point-prediction uncertainties in neural networks for protein-ligand binding prediction

Ja Ju Fan, Jonathan E. Allen, Kevin S. McLoughlin, Da Shi, Brian J. Bennion, Xiaohua Zhang, Felice C. Lightstone

DOI: https://doi.org/10.5912/jcb954

Access From

Date: December 11, 2020

Journal: Journal of Commercial Biotechnology

Solving Hard Problems with AI: Dramatically Accelerating Drug Discovery Through a Unique Public-Private Partnership

John Baldoni, Edmon Begoli, Dimitri Kusnezov, John MacWilliams

High-Throughput Virtual Screening of Small Molecule Inhibitors for SARS-CoV-2 Protein Targets with Deep Fusion Models

Garrett A. Stevenson, Derek Jones, Hyojin Kim, W. F. Drew Bennett, Brian J. Bennion, Monica Borucki, Feliza Bourguet, Aidan Epstein, Magdalena Franco, Brooke Harmon, Stewart He, Max P. Katz, Daniel Kirshner, Victoria Lao, Edmond Y. Lau, Jacky Lo, Kevin McLoughlin, Richard Mosesso, Deepa K. Murugesh, Oscar A. Negrete, Edwin A. Saada, Brent Segelke, Maxwell Stefan, Marisa W. Torres, Dina Weilhammer, Sergio Wong, Yue Yang, Adam Zemla, Xiaohua Zhang, Fangqiang Zhu, Felice C. Lightstone, Jonathan E. Allen

DOI: https://doi.org/10.1145/3458817.3476193

Date: November 13, 2021

Proceedings: SC '21: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis November 2021 Article No.: 74Pages 1–13

Enabling rapid COVID-19 small molecule drug design through scalable deep learning of generative models

Sam Ade Jacobs, Tim Moon, Kevin McLoughlin, Derek Jones, David Hysom, Dong H. Ahn, John Gyllenhaal, Pythagoras Watson, Felice C. Lightstone, Jonathan E. Allen, Ian Karlin, Brian Van Essen

DOI:  https://doi.org/10.1177/10943420211010930

Date: May 3, 2021

Journal: International Journal of High Performance Computing Applications

DOI: https://doi.org/10.1021/acs.jcim.0c01306

Date: March 23, 2021

Journal: Journal of Chemical Information and Modeling

Improved Protein-ligand Binding Affinity Prediction with Structure-Based Deep Fusion Inference

Derek Jones, Hyojin Kim, Xiaohua Zhang, Adam Zemla, Garrett Stevenson, W. F. Drew Bennett, Daniel Kirshner, Sergio E. Wong, Felice C. Lightstone, and Jonathan E. Allen

DOI: https://doi.org/10.1016/j.chembiol.2021.01.016

Date: March 18, 2021

Journal: Cell Chemical Biology

Reimagining dots and dashes: visualizing structure and function of organelles for high-content imaging analysis

Marcus Y.Chin, Jether Amos Espinosa, Grace Pohan, Michelle R. Arkin, Sarine Markossian

DOI: https://doi.org/10.1002/cpz1.75

Date: March 18, 2021

Journal: Current Protocols

Real-Time Assessment of Mitochondrial Toxicity in HepG2 Cells Using the Seahorse Extracellular Flux Analyzer

Amos Espinosa; Grace Pohan; Michelle Arkin; Sarine Markossian

DOI: https://doi.org/10.1021/acs.jcim.0c00950

Date: January 27, 2021

Journal: Journal of Chemical Information and Modeling

Machine Learning Models to Predict Inhibitors of the Bile Salt Export Pump 

Kevin S. McLoughlin, Claire G. Jeong, Thomas D. Sweitzer, Amanda J. Minnich, Margaret J. Tse, Brian J. Bennion, Jonathan E. Allen, Stacie Calad-Thomson, Thomas S. Rush, and James M. Brase

DOI: https://doi.org/10.1124/dmd.120.000202

Date: February 2021

Journal: Drug Metabolism & Disposition 

Predicting Volume of Distribution in Humans: Performance of in silico Methods for Large Set of Structurally Diverse Clinical Compounds

Neha Murad, Kishore K. Pasikanti, Benjamin D. Madej, Amanda Minnich, Juliet M. McComas, Sabrinia Crouch, Joseph W. Polli and Andrew D. Weber

DOI: https://doi.org/10.1002/cpch.90

Date: December 14, 2020

Journal: Current Protocols in Chemical Biology

Multiparametric High-Content Assays to Measure Cell Health and Oxidative Damage as a Model for Drug-Induced Liver Injury

Grace Pohan, Jether Amos Espinosa, Steven Chen, Kenny K. Ang, Michelle R. Arkin, Sarine Markossian

DOI: https://doi.org/10.3389/fphar.2020.00770

 Date: June 30, 2020

Journal: Frontiers in Pharmacology Translational Pharmacology

Accelerating Therapeutics for Opportunities in Medicine: A Paradigm Shift in Drug Discovery 

Izumi V. Hinkson, Benjamin Madej, and Eric A. Stahlberg on behalf of the ATOM Consortium

DOI: https://doi.org/10.1021/acs.jcim.9b01053

 Date: April 3, 2020

Journal: Journal of Chemical Information and Models

AMPL: A Data-Driven Modeling Pipeline for Drug Discovery

Amanda J. Minnich, Kevin McLoughlin, Margaret Tse, Jason Deng, Andrew Weber, Neha Murad, Benjamin D. Madej, Bharath Ramsundar, Tom Rush, Stacie Calad-Thomson, Jim Brase, and Jonathan E. Allen

DOI: https://doi.org/10.1038/s41573-019-0050-3

 Date: December 4, 2019

Journal: Nature Reviews Drug Discovery

Rethinking drug design in the artificial intelligence era

Petra Schneider, W. Patrick Walters, Alleyn T. Plowright, Norman Sieroka, Jennifer Listgarten, Robert A. Goodnow Jr., Jasmin Fisher, Johanna M. Jansen, José S. Duca, Thomas S. Rush, Matthias Zentgraf, John Edward Hill, Elizabeth Krutoholow, Matthias Kohler, Jeff Blaney, Kimito Funatsu, Chris Luebkemann & Gisbert Schneider

Artificial Intelligence and Pharmacometrics: Time to Embrace, Capitalize, and Advance?

Ayyappa Chaturvedula, Stacie Calad-Thomson, Chao Liu, Mark Sale, Nandu Gattu, Navin Goyal

DOI: https://doi.org/10.1002/psp4.12418

 Date: April 21, 2019

Journal: CPT: Pharmacometrics & Systems Pharmacology

UCSF scientists and clinicians have long been leaders in drug discovery, therapeutics, and cancer biology with the UCSF Helen Diller Family Comprehensive Care Center among the top-ranked cancer institutes in the country. Our role with ATOM is therefore in lock step with UCSF’s mission of advancing health worldwide.
— Sam Hawgood, MBBS, UCSF Chancellor
membership.png

Membership

 

Benefits of Membership

 

 

ATOM is actively seeking additional partnerships with organizations who share in our vision. Member benefits include access to:


                    1.    Algorithms and generated data for a member-benefit period
                    2.    Training and capability development for employees
                    3.    Best-in-class computational resources
                    4.    Expertise of the group and leaders in their industries
                    5.    Unique collaboration and incubation environment
                    6.    Workflow for internal drug discovery and commercialization

 
 
We need to get better medicines to patients faster. This project aims to do that.
— Alan Ashworth, President of UCSF Helen Diller Family Comprehensive Cancer Center
contact.png

Contact

 
 

The ATOM Consortium is actively seeking additional partnerships with qualified pharma, biotech, technology, academic, government, and other organizations.

 
 
 

Headquarters

499 Illinois Street
3rd floor
San Francisco,
CA 94158

info@atomscience.org

Connect with us

If you would like to learn more about ATOM, contact us using the link below and one of our team members will get back to you.

GSK is working to set a precedent with pharmaceutical companies by sharing data on failed compounds.
— John Baldoni, ATOM Founder
ATOM is a novel public-private partnership that draws on the lab’s unique capabilities to create a paradigm change in drug development
— Bill Goldstein, Director of LLNL
atom-in-the-news.png

News & Events

News Releases

 
 
 

ATOM Blog

 
 
 

Stay informed with periodic updates from our Leadership and Technical teams.

 

News

 
 

Events

 
 
 

Media Contacts

 

Laura Kurtzman

Senior Public Information Officer University of California San Francisco

415-476-3163 laura.kurtzman@ucsf.edu

Mary Ellen Hackett

Manager, Public Affairs and Communications,
Frederick National Laboratory for Cancer Research

301-360-3389
maryellen.hacket@nih.gov

 
 

Jeremy Thomas

Public Information Officer,
Lawrence Livermore National Laboratory

925-423-7602
925-422-5539