Argonne National Laboratory (ANL) is a U.S. Department of Energy-funded facility. It is a multidisciplinary science and engineering research center, where scientists and engineers work together to answer the biggest questions facing humanity, from how to obtain affordable clean energy, to protecting ourselves and our envi- ronment.
At ANL, Cerebras is working with research staff in the Computing, Environment, and Life Sciences (CELS) directorate to accelerate groundbreaking scientific and technical innovation in biology and life sciences.
Researchers at ANL are working with the U.S. National Cancer Institute (NCI) and the National Institutes of Health (NIH) to develop treatments for cancer. They are using machine learning (ML) and large computational simulations to do this. One of the largest projects is aimed at addressing the “drug response problem.”
The drug response problem is the complex challenge of modeling the response of a disease to candidate therapeutic compounds to accelerate development of treatments. ANL aims to develop AI-powered predictive models for drug response that can be used to optimize pre-clinical drug screening and to drive precision medicine-based treatments for cancer patients.
ANL’s IT environment has thousands of graphics processing units (GPUs), as well as several of the largest supercomputers in the world. Why were these machines not sufficient to do the AI computational work required?