Researchers from PNNL and Parallel Works, Inc., applied machine learning methods to predict how much oxygen and nutrients are used by microorganisms in river sediments.

Lauren Charles, a chief data scientist at PNNL, showcased the vital research coming out of her program at The National Academies Forum workshop in Washington, D.C., January 15–16, 2025.

Over the next four years, PNNL and University of Arizona will develop open-source computational tools to better identify and characterize the viruses associated with the human microbiome.

Armed with some of the world’s most advanced instrumentation, researchers at PNNL are working to analyze huge amounts of data and uncover hidden biological connections.

Nine national laboratories, including PNNL, bring together over 1,000 scientists for a day to use AI to accelerate scientific discovery.

Scientists plumbed the depths of nearly 3,000 soil samples from around the globe to compile the heftiest atlas of soil viruses ever created.

A cross-institutional team of scientists developed PeakQC, a new software tool for automated quality control of mass spectrometry data.

Neeraj Kumar discusses how AI can transform scientific research at the Platform for Advanced Scientific Computing Conference and Trillion Parameter Consortium European Workshop.

Despite the widespread presence of RNA viruses in soils, little is known about the relative contributions and interactions of biological and environmental factors shaping the composition of soil RNA viral communities.

Researchers will explore climate, pathogens and energy-efficient microelectronics using 3 million node hours on the nation’s supercomputers.

Scientists unravel a secret to oil production in plants, opening up the possibility of increasing production for biofuels and other applications.

The Rapid Assessment of Platform Technologies to Expedite Response project aims to prepare against future pandemics.

Data-driven autonomous technology to rapidly design and deliver antiviral interventions targeting SARS-CoV-2 to reduce drug discovery timeline and advance bio preparedness capabilities.

Parallel graph neural networks identify protein-ligand 3-D structural interactions to aid in protein function prediction and drug discovery.