PNNL researchers present challenges and opportunities for fusing graph neural networks with deep reinforcement learning.

ACMD staff contributed to 30 years of atmospheric data collection for the Department of Energy’s Atmospheric Radiation Measurement user facility.

This study profiled the 24-hour rhythmicity in bile salt hydrolase enzyme activity using simple fluorescence assay and the results showed that this rhythmicity is influenced by feeding patterns of the host.

PNNL has named Biomedical Scientist Tom Metz, an expert on metabolomics and multi-omics within the Biological Sciences Division, a 2023 Laboratory Fellow.

PNNL’s wide-ranging report maps the current nanobiotechnology landscape, flags potential concerns, and details the need for an organizing body to coordinate currently disparate disciplines.

Across the United States, organic carbon concentration imposes a primary control on river sediment respiration, with additional influences from organic matter chemistry.

Small teams in the Biological Sciences Division at PNNL and at EMSL—the Environmental and Molecular Sciences Laboratory, an Office of Science user facility at PNNL—are pros at preparation.

Scientists have taken an important step forward in predicting who will develop Type 1 diabetes months before symptoms appear.

Joshua Adkins and Jamie Lo will lead PMedIC, Pacific Northwest National Laboratory and Oregon Health & Science University’s joint research institute.

PNNL scientists are creating new ways to learn more about the vast sea of chemicals that haven't been identified—yet.

Lauren Charles, a chief data scientist at PNNL, joined the editorial board of the largest open access journal published by Nature Research.

New research from PNNL and Washington State University collaborators connects the microbiome in the gut to circadian rhythms, suggesting a role for the microbiome as an internal regulator.

PNNL researchers outline open problems in different scientific areas in the Journal of Combinatorics.

Adam Attarian led a new panel session, titled National Labs and the GEOINT Mission, at the GEOINT 2023 Symposium, held May 21–24, 2023.

By mimicking nature, scientists make a breakthrough in breaking down wood.

The popular approach of organizing soil bacteria into fast- or slow-growing groups is problematic because most bacteria grow at comparable rates in soil.

Metabolomics analysis revealed differences in metabolome profiles for two distinct modes of fungal wood decay.

To overcome high-performance computing bottlenecks, a research team at PNNL proposed using graph theory, a mathematical field that explores relationships and connections between a number, or cluster, of points in a space.

The ChemSpace Tool, when fully developed, is intended to divide chemical space into three subsets: the detectable space, the identifiable space, and the region that includes compounds that are not detectable or identifiable.

Methods review suggests ways to use artificial intelligence and machine learning to handle missing data when integrating two or more omics approaches.