CANcer Distributed Learning Environment (CANDLE) is an artificial intelligence-based computer code that brings together machine learning, deep learning, and cancer research to accelerate the discovery of new cancer therapies and treatments.

CANDLE is led by Argonne in collaboration with three other U.S. Department of Energy (DOE) national laboratories – Lawrence Livermore, Oak Ridge, and Los Alamos – and the National Cancer Institute (NCI) of the National Institutes of Health. This project couples the laboratories’ strength in high performance computing, machine learning, and data analytics with NCI’s expertise in cancer biology and healthcare delivery to apply the full promise of exascale computing to cancer and precision medicine.

This unique and powerful platform aims to solve three major challenges in cancer. First, it analyzes protein behaviors in tumor cells. Second, it looks at the relationship between tumors and drugs. Third, it can analyze biomedical records to extract new patterns and information.

In addition, scientists are using CANDLE codes to check the performance of the most advanced DOE computing systems including Argonne’s upcoming Aurora exascale supercomputer.

This research was supported by the Exascale Computing Project (17-SC-20-SC), a collaborative effort of the U.S. Department of Energy Office of Science and the National Nuclear Security Administration.