Recent developments in cancer-specific “big data” and experimental technologies, coupled with advances in data analysis and high-performance computational capabilities, are creating unprecedented opportunities to advance understanding of cancer at greater and more precise scales.
Building on these developments and on the goals of the Precision Medicine Initiative and the Cancer Moonshot℠, NCI has created numerous initiatives to promote a national learning healthcare system for cancer to unleash the power of data.
The Joint Design of Advanced Computing Solutions for Cancer (JDACS4C) program was created in 2016 to accelerate cancer research using emerging exascale computing capabilities (capable of a billion billion calculations per second). Announced as part of the Cancer Moonshot, it is an innovative cross-agency collaboration that is designed to equally benefit NCI and the Department of Energy (DOE).
Investigators from NCI and the Frederick National Laboratory for Cancer Research work collaboratively with experts in computational, data, and physical sciences from four DOE national laboratories: Argonne, Los Alamos, Lawrence Livermore, and Oak Ridge.
Goals of the JDACS4C Program
- Identify promising new treatment options using advanced computation to rapidly develop, test, and validate predictive preclinical models for precision oncology
- Deepen understanding of cancer biology using molecular, functional, and structural data from the NCI RAS initiative through improved dynamic computer simulations and predictive models
- Transform cancer surveillance by applying advanced computational capabilities to population-based cancer data to understand the impact of new diagnostics, treatments, and patient factors
JDACS4C Research Pilots
The JDACS4C program has three research pilots that align with several existing NCI and DOE programs and are jointly led by DOE and NCI scientists. All three pilots embody a multi-disciplinary, team science approach.
Together, these pilot projects are intended to pioneer new approaches to research and attain greater understanding of cancer biology, diagnostics, prognostics, and treatment. The pilots utilize increasingly large-scale multimodal data analysis combined with advanced computational methods and algorithms from the DOE Exascale Computing Project.
- Molecular Level: Improving Outcomes for RAS-related Cancers
- Cellular Level: Predictive Modeling for Pre-Clinical Screening
- Population Level: Population Information Integration, Analysis, and Modeling for Precision Surveillance
Deep Learning for Pilots
The exascale CANcer Distributed Learning Environment (CANDLE) project provides the latest deep learning capabilities to each pilot.
Uncertainty Quantification for Pilots
Uncertainty Quantification (UQ) encompasses methods development for understanding and quantifying error and uncertainty as it propagates through experiment, simulation, and data analytics. UQ for machine learning targets developing machine learning methods that can appropriately manage the errors and report uncertainty in predictions.