Graph learning and single-cell genomics may unlock more accurate gene regulatory network inference
Peer-Reviewed Publication
Updates every hour. Last Updated: 31-Oct-2026 03:16 ET (31-Oct-2026 07:16 GMT/UTC)
A new graph-based deep learning framework may improve the reconstruction of gene regulatory networks from single-cell RNA sequencing (scRNA-seq) data by integrating global network structure learning with biologically informed statistical modeling, according to a study published in Computational Biomedicine.
Researchers from LMU and Cornell University reveal that zebrafish and fruit flies share the same internal compass mechanism.
Florian Weinberger conducts his research within the Regeneration Program at the CNIC.
New research from the University of St Andrews has shown that higher extinction risk is associated with higher frequency of decreasing local prevalence of species, in an analysis of one of the most comprehensive long-term databases ever created, BioTIME – a major tool to study biodiversity change also developed at the University of St Andrews. Researchers from the School of Biology alongside a team of international partners, analysed over 60 000 populations of 2362 species across 978 marine and terrestrial assemblages. These populations have been sampled comprehensively over at least 20 years. The picture that emerged was of complex links between the two factors, but a clear signal also emerged that decreasing temporal trends were associated with higher extinction risk compared to the other trends. Overall, fewer than 10% of populations showed either increasing or decreasing prevalence over time
Reported June 23 in Nature Biomedical Engineering, researchers at Vanderbilt Health and centers in Hong Kong have created a versatile uncertainty-aware AI framework broadly adaptable as a wrapper for digital pathology AI systems. (An AI wrapper acts as an interface layer that customizes, formats and automates how users interact with the underlying intelligence.) They demonstrate their wrapper, called TRUECAM, primarily with reference to non-small cell lung cancer (NSCLC) subtyping using whole-slide images.
UCLA scientists are calling for a large-scale initiative to understand how human cells influence one another — a missing layer of biology that could reveal how cellular interactions drive disease and inform new therapies.