Skip to content
DraconiticResearch
Search Sources API
197,578 studies31 sourcesUpdated 54 min ago
PreprintCC BY-NCbioRxiv

Disentangling Context-Specific Alzheimer's Disease Progression Signatures through an Explainable AI Framework

  1. 1University of Washington

Abstract

Alzheimer's disease (AD) progression involves stage-dependent transcriptional changes that are often masked by dominant cellular and biological variation. Here, we present ADVISE (Alzheimer's Disease Variational Isolation of Signal Embeddings), an interpretable deep generative framework designed to disentangle Braak stage-associated transcriptional signals from background biological variation through separate latent representations. Using explainable AI, ADVISE prioritizes genes and pathways contributing to the disease-specific representation. Applying ADVISE to large-scale single-nucleus RNA sequencing data from the human prefrontal cortex, we identify shared and context-specific signatures of AD progression across global, sex-specific, and cell-type-specific analyses, revealing convergent molecular programs involving synaptic transmission, HSF1-associated proteostatic stress responses, and SLIT/ROBO axon guidance. Notably, ADVISE prioritizes ROBO2 as a progression-associated candidate in excitatory neurons. Experimental validation using CRISPR activation in hiPSC-derived excitatory neurons demonstrates that ROBO2 activation reduces the phosphorylated Tau-to-total Tau ratio. ADVISE thus reveals context-dependent molecular signatures of AD progression and bridges human single-cell discoveries with experimental validation of candidate regulators of AD pathology.

Related

  1. Disentangling maternal pregnancy and fetal-specific plasma signatures through integrated proteomics and site-specific N-glycoproteomics
    S. Jager, S. Kalaidopoulou Nteak, G. Reznikov +5
    bioRxivPreprintCC BY-NCFull textDevelopmental biologybioRxiv
  2. Disentangling the temporal signatures of conditioned pupil dilation: Distinct valence- and prediction-error-related components revealed by mega-analysis
    J. B. Finke, A. M. Schippers, H. Schaechinger +1
    bioRxivPreprintCC BY-NC-NDFull textNeurosciencebioRxiv
  3. Microbiota-derived metabolite signatures in Alzheimer’s disease across the cognitive aging continuum: a human-focused systematic review and evidence-weighted knowledge graph
    Xiaoteng He, Lili Zhang, Caiqiu Song +1
    Frontiers in microbiologyPeer-reviewedCC BYFull textMicrobiologyEurope PMC
  4. Divergent amyloid trajectories distinguish normal aging from Alzheimer's disease progression
    M. Tong, T. Gao, Y. Upadhyaya +5
    bioRxivPreprintCC BYFull textNeurosciencebioRxiv
  5. A functional connectome identifies vulnerability to cognitive decline and Alzheimer’s disease progression
    Kanhao Zhao, Hua Xie, Gregory A. Fonzo +7
    Science AdvancesPeer-reviewedCC BY-NC 4.0Full textNeuroscienceSci. Adv.CrossrefPMC
BibTeX
@misc{li2026disentangling,
  title = {{Disentangling Context-Specific Alzheimer's Disease Progression Signatures through an Explainable AI Framework}},
  author = {A. W. Li and W. Qiu and C. Arian and J. E. Young and S.-I. Lee},
  howpublished = {bioRxiv},
  year = {2026},
  month = nov,
  doi = {10.64898/2026.11.02.763789},
  url = {https://www.biorxiv.org/content/10.64898/2026.11.02.763789v1},
  note = {CC BY-NC},
}
RIS
TY  - UNPB
TI  - Disentangling Context-Specific Alzheimer's Disease Progression Signatures through an Explainable AI Framework
AU  - A. W. Li
AU  - W. Qiu
AU  - C. Arian
AU  - J. E. Young
AU  - S.-I. Lee
PY  - 2026
DA  - 2026/11/02
PB  - bioRxiv
DO  - 10.64898/2026.11.02.763789
UR  - https://www.biorxiv.org/content/10.64898/2026.11.02.763789v1
AB  - Alzheimer's disease (AD) progression involves stage-dependent transcriptional changes that are often masked by dominant cellular and biological variation. Here, we present ADVISE (Alzheimer's Disease Variational Isolation of Signal Embeddings), an interpretable deep generative framework designed to disentangle Braak stage-associated transcriptional signals from background biological variation through separate latent representations. Using explainable AI, ADVISE prioritizes genes and pathways contributing to the disease-specific representation. Applying ADVISE to large-scale single-nucleus RNA sequencing data from the human prefrontal cortex, we identify shared and context-specific signatures of AD progression across global, sex-specific, and cell-type-specific analyses, revealing convergent molecular programs involving synaptic transmission, HSF1-associated proteostatic stress responses, and SLIT/ROBO axon guidance. Notably, ADVISE prioritizes ROBO2 as a progression-associated candidate in excitatory neurons. Experimental validation using CRISPR activation in hiPSC-derived excitatory neurons demonstrates that ROBO2 activation reduces the phosphorylated Tau-to-total Tau ratio. ADVISE thus reveals context-dependent molecular signatures of AD progression and bridges human single-cell discoveries with experimental validation of candidate regulators of AD pathology.
ER  -