NCI-Department of Energy Collaboration
About the Collaboration
Since 2016, NCI and the U.S. Department of Energy (DOE) have engaged in a strategic, interagency collaboration to simultaneously accelerate advances in precision oncology and scientific computing, including the use of artificial intelligence. The NCI-DOE Collaboration is part of the Cancer MoonshotSM, dedicated to ending cancer as we know it.
![Boxes conveying a listing of Department of Energy projects stacked one on top of another, showing how they are aligned, with the following text. First section: “NCI-DOE Collaboration” “[The collaboration] fosters a growing predictive oncology community” and “[The collaboration] provides open access to FAIR AI/ML resources, including datasets and computational models.” Second section: “NCI-DOE Projects.” This includes “MOSSAIC - Modeling Outcomes Using Surveillance Data and Scalable AI for Cancer,” “ADMIRRAL - AI-Driven Multiscale Investigation of the RAS/RAF Activation Lifecycle,” “IMPROVE - Innovative Methodologies and New Data for Predictive Oncology Model Evaluation," and “ATOM - Accelerating Therapeutics for Opportunities in Medicine.” Third section: “Infrastructure.” This includes “CANDLE - CANcer Distributed Learning Environment," "Computational Resources for Cancer Research," and "MoDaC - NCI Predictive Oncology Model and Data Clearinghouse.” The NCI logo is present on the footer, reading "NIH National Cancer Institute."](/sites/default/files/2024-08/JDACS4CInfographic22V10-01-MDT_0.png)
Projects Within the Collaboration
MOSSAIC: Modeling Outcomes Using Surveillance Data and Scalable Artificial Intelligence for Cancer
MOSSAIC (using data from NCI’s Surveillance, Epidemiology, and End Results [SEER] Program) applies natural language processing and transformer models to automate cancer surveillance and population-level research. MOSSAIC advances computational and informatics solutions to support SEER and lays the foundation for an integrative data-driven approach to modeling cancer outcomes at scale and in real time.
ADMIRRAL: AI-Driven Multiscale Investigation of the RAS/RAF Activation Lifecycle
ADMIRRAL aims to develop a mechanistic understanding of RAS-RAF-driven cancer initiation and growth. Combining machine learning (ML), high performance computing, and experimentation, the project involves delineating large-scale domain rearrangement (with molecular resolution) of the RAS-RAF complex and simulating the activation of RAF kinase.
IMPROVE: Innovative Methodologies and New Data for Predictive Oncology Model Evaluation
IMPROVE develops approaches and a framework for comparing and evaluating deep learning drug response prediction models. The IMPROVE project team, together with the broader scientific community, is discovering methods to identify deep learning model attributes—and new data—that contribute to prediction performance and reproducibility to improve future models.
ATOM: Accelerating Therapeutics for Opportunities in Medicine
ATOM accelerates drug discovery through the development of an integrated artificial intelligence (AI), high performance computing, and biomedical data open platform. ATOM employs active learning to identify and optimize new compounds to satisfy multiple pharmaceutical parameters concurrently. In addition, you can shorten the time to discovery and optimization of molecules, including new treatments, probe molecules, and imaging agents by using ATOM’s open models, data, and software.
NCI's Center for Biomedical Informatics and Information Technology is conducting a survey to assess the compute-intensive resource needs of the cancer research community. Regardless of your area of cancer research, your insights will contribute to a better understanding of computing needs and challenges for research that involves large amounts of data and analysis. By participating, you’ll help NCI to shape strategy that could enhance overall efficiency to drive cancer research outcomes, including making compute resources easier to access. We appreciate your willingness to participate in this survey. Your input matters, and we value your candid feedback.
Take the survey
The NCI-DOE Collaboration’s Infrastructure
CANDLE: CANcer Distributed Learning Environment
CANDLE is an open source, collaboratively developed software platform that provides deep learning methodologies for accelerating cancer research. You can access CANDLE via GitHub as well as on the NIH Biowulf cluster.
MoDaC: NCI Predictive Oncology Modeling and Data Clearinghouse
MoDaC is a public repository hosting predictive oncology data sets, software tools, and computational models. Through MoDaC, you can easily access NCI-DOE Collaboration computational resources, emphasizing data sets and associated models. You can download and use annotated data sets and models in this publicly searchable resource.
Computational Resources for Cancer Research Portal
With the Computational Resources for Cancer Research portal, you can search cross-referenced catalogs of software tools, computational models, and computationally derived data sets that the NCI-DOE Collaboration and other NCI projects and programs have developed. The portal also hosts corresponding publications, educational use cases and tutorials, and a community engagement section highlighting relevant collaborations, opportunities, and events. The portal is also integrated and interoperable with MoDaC.
NCI’s Role
The interdisciplinary projects under the NCI-DOE Collaboration are led jointly by NCI and DOE, with representation from the agencies’ Federally Funded Research and Development Centers:
- NCI’s Frederick National Laboratory for Cancer Research (FNLCR)
- Argonne National Laboratory (DOE)
- Brookhaven National Laboratory (DOE)
- Lawrence Livermore National Laboratory (DOE)
- Oak Ridge National Laboratory (DOE)
- Pacific Northwest National Laboratory (DOE)
Multiple NCI divisions and centers provide leadership and subject matter expertise for the NCI-DOE Collaboration projects.
- The Center for Biomedical Informatics and Information Technology (CBIIT), in conjunction with NCI’s FNLCR, provides overarching strategic direction, program management, engagement, cross-disciplinary workshops, and leadership in community building and development of new collaborative research areas.
- The Division of Cancer Control and Population Sciences (DCCPS) and the SEER Program provide scientific leadership, subject matter expertise, and data for the MOSSAIC project.
- The Division of Cancer Biology (DCB) provides leadership and subject matter expertise for the IMPROVE project.
Connecting with the Cancer Community
The Computational Cancer Community (formerly hosted on the NCI Hub) now exists on the Computational Resources for Cancer Research portal.
Building on the NCI-DOE Collaboration, this community is an incubator for new collaboration areas at the intersection of cancer, AI, and data science. Scientists from more than 50 public and private organizations at all career levels have participated in interactive Computational Cancer Community workshops and “idea labs” to share their ideas and expertise, develop use cases, and explore new interdisciplinary research opportunities (in topics such as cancer patient digital twins and predictive radiation oncology).
Join the interdisciplinary community to stay abreast of news, events, and opportunities for collaboration. Email any questions, comments, or feedback to the Computational Cancer Community.
You can also email the community if you’d like to contribute a computational resource for cancer (e.g., model, software, data set).
Additional Information
AI/ML Resources and Publications
As previously mentioned, you can get NCI-DOE Collaboration resources through the new Computational Resources for Cancer Research portal, which provides access to computational models, software, and data sets contributed by the research community. You can also stay up to date with the scientific publications resulting from the NCI-DOE Collaboration via this portal.
Educational Resources
The portal provides access to educational tutorials, use cases, event information, and insight on emerging AI/ML topics, including digital twins. Visit the “Connect & Learn” webpage for more information.
Need Help?
For more information about the NCI-DOE Collaboration projects or infrastructure, email the team.
If you need assistance with the Computational Resources for Cancer Research portal, fill out the form with your questions and/or comments. You may also use this form to learn about collaborations, contribute resources, and/or sign up for email notifications.