ADInteractome: discovering Alzheimer's disease-associated gene interactions from single-nucleus RNA-seq data through neural interaction states.

ADInteractome identifies cell-type-specific, AD-associated gene interaction circuits from single-nucleus RNA-seq by extracting neural interaction states from a classifier trained on AD versus non-AD donors.

• Why it matters: Molecular mechanisms in Alzheimer’s disease remain unclear, and existing network approaches may miss biologically meaningful gene interactions linked to cellular heterogeneity.
• What they did: The framework trains an interpretable neural model on snRNA-seq from the Seattle Alzheimer's Disease Brain Cell Atlas, then uses internal interaction states plus virtual knock-out/knock-in tests to validate predicted circuits.
• The result: Compared with traditional co-expression networks, it shows stronger enrichment for known AD-associated gene interactions and reveals novel interaction patterns supported by literature and the virtual perturbations.

AI summary of the abstract · may contain errors · not medical advice · read the paper.