Unified AI framework to uncover deep interrelationships between | ResearchBunny

Index

Abstract

This paper introduces MD-AD, a multi-task deep learning framework designed to analyze heterogeneous Alzheimer's Disease (AD) datasets. MD-AD leverages the synergy between deep neural networks and multi-cohort settings to uncover complex, non-linear relationships between gene expression and AD neuropathologies, overcoming limitations of conventional methods. The framework identifies subtle disease signals, reveals sex-specific relationships between microglial immune response and neuropathology, and demonstrates generalizability across species and tissues.

Publisher

Nature Communications

Published On

Sep 10, 2021

Authors

Nicasia Beebe-Wang, Safiye Celik, Ethan Weinberger, Pascal Sturmfels, Philip L. De Jager, Sara Mostafavi, Su-In Lee

Related Publications

Explore these studies to deepen your understanding of the subject.

Psychology

Haploinsufficiency of the Parkinson’s disease gene synaptojanin1 is associated with abnormal responses to psychomotor stimulants and mesolimbic dopamine signaling

J. I. Mejaes, J. Saenz, et al.

Medicine and Health

DNA methylation and gene expression analysis in adipose tissue to identify new loci associated with T2D development in obesity

P. Baca, F. Barajas-olmos, et al.

Medicine and Health

Design and Analysis of a Deep Learning Ensemble Framework Model for the Detection of COVID-19 and Pneumonia Using Large-Scale CT Scan and X-ray Image Datasets

X. Xue, S. Chinnaperumal, et al.

Interdisciplinary Studies

Cultures in the laboratory: mapping similarities and differences between Māori and non-Māori in engaging with gene-editing technologies in Aotearoa, New Zealand

L. Kathlene, D. Munshi, et al.

Listen, Learn & Level Up

Over 10,000 hours of research content in 25+ fields, available in 12+ languages.

No more digging through PDFs—just hit play and absorb the world's latest research in your language, on your time.

listen to research audio papers with researchbunny