Wednesday, October 7, 2026Every story links to its original source.

Genomes News

Genomics news, traced to the source.

Reading

archive1 min read

Graph neural network ties single-cell brain data to Alzheimer's disease traits

Figure 1: Chenfeng He et al. AI-based characterization of Alzheimer’s disease phenotypes from population-scale single-cell data. Nature Medicine (2026).Image licenceFull-size image

A graph neural network called PASCode sifted through single-cell data from 584 brain donors and flagged about 1.5 million cells linked to Alzheimer's disease traits, Nature Medicine reports. The tissue came from the prefrontal cortex, part of a dataset of more than 1,000 brains. Comparing 27 cell subclasses, researchers identified reactive astrocyte subtypes with altered neuroprotective and neurotoxic gene expression linked to cognitive resilience. Astrocytes tied to both Alzheimer's and depression showed inflammation and endoplasmic reticulum stress pathways.

The findings give researchers specific cellular targets in the brain for studying cognitive resilience and depression tied to Alzheimer's disease.

Written by the Genomes desk from the primary source cited and linked above and checked against it. Research use only; not medical advice. Corrections: [email protected].

More from the archive

Back to the latest · Archive