Skip to main content
ORNL, VA and Harvard researchers developed a sparse matrix full of anonymized information on what is thought to be the largest cohort of healthcare data used for this type of research in the U.S. The matrix can be probed with different methods, such as KESER, to gain new insights into human health. Credit: Nathan Armistead/ORNL, U.S. Dept. of Energy

A team of researchers has developed a novel, machine learning–based  technique to explore and identify relationships among medical concepts using electronic health record data across multiple healthcare providers.

ORNL scientists created a new microbial trait mapping process that improves on classical protoplast fusion techniques to identify the genes that trigger desirable genetic traits like improved biomass processing. Credit: Nathan Armistead/ORNL, U.S. Dept. of Energy. Reprinted with the permission of Oxford University Press, publisher of Nucleic Acids Research

ORNL scientists had a problem mapping the genomes of bacteria to better understand the origins of their physical traits and improve their function for bioenergy production.

ORNL’s Brenda Pracheil, left, and Kristine Moody collect water samples at Melton Hill Lake using a sophisticated instrument that collects DNA in the water to determine fish species and number of fish in the water, which could prove useful for monitoring hydropower impacts. Credit: Carlos Jones, ORNL/U.S Dept. of Energy

Researchers at Oak Ridge National Laboratory are using a novel approach in determining environmental impacts to aquatic species near hydropower facilities, potentially leading to smarter facility designs that can support electrical grid reliability.

A new process developed by Oak Ridge National Laboratory leverages deep learning techniques to study cell movements in a simulated environment, guided by simple physics rules similar to video-game play. Credit: MSKCC and UTK

Scientists have developed a novel approach to computationally infer previously undetected behaviors within complex biological environments by analyzing live, time-lapsed images that show the positioning of embryonic cells in C. elegans, or roundworms. Their published methods could be used to reveal hidden biological activity. 

This protein drives key processes for sulfide use in many microorganisms that produce methane, including Thermosipho melanesiensis. Researchers used supercomputing and deep learning tools to predict its structure, which has eluded experimental methods such as crystallography.  Credit: Ada Sedova/ORNL, U.S. Dept. of Energy

A team of scientists led by the Department of Energy’s Oak Ridge National Laboratory and the Georgia Institute of Technology is using supercomputing and revolutionary deep learning tools to predict the structures and roles of thousands of proteins with unknown functions.