What is the Computational Cancer Community?

The Computational Cancer Community (formerly ECICC) arose from the NCI-DOE Collaboration and is dedicated to accelerating computational oncology and developing new research collaborations at the intersection of cancer research, advanced scientific computing, and AI. The Community has become an incubator for successfully seeding new areas of interdisciplinary collaboration, such as biomedical digital twins and predictive radiation oncology. 


Members of the Community have presented their work at national and international conferences, including AACR, Bio-IT World and Bio-IT World Europe, CompBioMed, the Computational Approaches for Cancer Workshop at the annual SC supercomputing conference, and the HPC Applications of Precision Medicine workshop at the annual ISC Conference in Germany, to name a few. Scientists from over 50 national and international academic, government, and industry organizations have come together to participate in interdisciplinary events.


Thanks to broader engagement with the research community, new resources and collaborative research opportunities found on this portal are shaping the future of predictive oncology, drug discovery, and clinical applications! 


In 2019, the NCI-DOE Collaboration hosted an interdisciplinary, highly interactive Scoping Meeting comprised of 74 cancer researchers, computational scientists, and AI experts who identified cancer challenge areas that push the limits of current cancer research computational practices and compel the development of innovative computational technologies:

-Generation of synthetic data sets for training, modeling, and research

-Hypothesis generation using machine learning (ML)

-Creating digital twin technology

-Development of adaptive treatments

In 2020, we hosted a cancer patient digital twin Ideas Lab resulting in five interdisciplinary seed projects funded jointly by NCI and DOE. Two of these projects went on to submit Bridge2AI applications and another grew into an NCI-funded R01 grant. More recently, NCI and DOE co-sponsored a NASEM study on "Foundational Research Gaps and Future Directions for Digital Twins."


Current Focus Areas

The Computational Cancer Community currently focuses on cancer patient digital twin and predictive radiation oncology.

News Bulletins, Select Publications, Presentations, and Videos from the Community

Read our Latest News Bulletins!

May 2024

February 2024

May 2023

March 2023

February 2023

January 2023

October 2022


Select Publications from the Community

Select publications written by members of the community are listed below. For the full list of publications related to the computational resources, see the Publications Library


Towards global model generalizability: independent cross-site feature evaluation for patient-level risk prediction models using the OHDSI networkJCO Clinical Cancer Informatics (2024)


Path-BigBird: An AI-Driver Transformer Approach to Classification of Cancer Pathology Reports, Journal of American Medical Informatics Association (2024)


Modeling Strategies for Drug Response Prediction in Cancer, Cancers-Special Issue (2023)

Videos from the Community


"Virtual Humans" explains how virtual humans, enabled by supercomputer simulations and virtual modeling at multiples scales - can help drive personalized medicine for the future.


"Wonder What we Mean by Digitial Twin?"  Vascular Digital Twins are vital to ongoing research and treatment of everything from heart conditions to cancer. At Duke University Pratt School of Engineering in the Randles Lab, we're working to develop high-fidelity digital twins and expand their use.


Presentations from the Community

The Current State of Data and Model Transparency 

Source: NCI-CBIIT AI & HPC Journal Club 

Presented by: Aaron Y. Lee MD MSCI, University of Washington

NCI AI Events and Funding Opportunitieshttps://www.cancer.gov/research/resources/ai-cancer-research.


DARPA's Automatic Scientific Knowledge Extraction and Modeling (ASKEM) program. ASKEM aims to create a knowledge-modeling-simulation ecosystem, empowered with the AI approaches and tools needed for the agile creation, sustainment, and enhancement of the complex models and simulators necessary to support expert knowledge -- and data-informed decision-making in diverse missions and scientific domains. The goal is to enable experts to maintain, reuse, and adapt large collections of heterogeneous data, knowledge, and models -- with traceability across knowledge sources, model assumptions, and model fitness.


Interagency Modeling and Analysis Group (IMAG): IMAG and the Multiscale Modeling Consortium (MSM) consist of program officials from multiple federal government agencies supporting research funding for modeling and analysis of biomedical, biological, and behavioral systems. Visit the wiki for more information about meetings and resources.

Join the Community!

Join us in navigating the frontiers of cancer data science and driving impactful change, united in the mission to end cancer as we know it.


Explore the computational resources on this portal to help:

- evolve the computational resources

- increase and advance the scientific impact

- build the community 


You can get involved in various ways: 

Share your feedback about the portal and how we can make it more impactful to you

Sign up for email updates

Join a new User Group

Connect with other researchers in the User Forum (coming soon)


If you would like to contribute resources or learn more about collaborations, contact us at computational-cancer@nih.gov. We look forward to hearing from you!