Network Diffusion-Constrained Variational Generative Models for Investigating the Molecular Dynamics of Brain Connectomes Under Neurodegeneration.

Publisher: MDPI Country of Publication: Switzerland NLM ID: 101092791 Publication Model: Electronic Cited Medium: Internet ISSN: 1422-0067 (Electronic) Linking ISSN: 14220067 NLM ISO Abbreviation: Int J Mol Sci Subsets: MEDLINE

Original Publication: Basel, Switzerland : MDPI, [2000-

Connectome*/methods ; Alzheimer Disease*/metabolism ; Alzheimer Disease*/pathology ; Alzheimer Disease*/diagnostic imaging ; Brain*/metabolism ; Brain*/diagnostic imaging ; Brain*/pathology ; Neurodegenerative Diseases*/metabolism ; Neurodegenerative Diseases*/diagnostic imaging; Humans ; Bayes Theorem ; Amyloid beta-Peptides/metabolism ; Magnetic Resonance Imaging ; Models, Neurological ; tau Proteins/metabolism ; Computer Simulation

Alzheimer's disease (AD) is a complex and progressive neurodegenerative condition with significant societal impact. Understanding the temporal dynamics of its pathology is essential for advancing therapeutic interventions. Empirical and anatomical evidence indicates that network decoupling occurs as a result of gray matter atrophy. However, the scarcity of longitudinal clinical data presents challenges for computer-based simulations. To address this, a first-principles-based, physics-constrained Bayesian framework is proposed to model time-dependent connectome dynamics during neurodegeneration. This temporal diffusion network framework segments pathological progression into discrete time windows and optimizes connectome distributions for biomarker Bayesian regression, conceptualized as a learning problem. The framework employs a variational autoencoder-like architecture with computational enhancements to stabilize and improve training efficiency. Experimental evaluations demonstrate that the proposed temporal meta-models outperform traditional static diffusion models. The models were evaluated using both synthetic and real-world MRI and PET clinical datasets that measure amyloid beta, tau, and glucose metabolism. The framework successfully distinguishes normative aging from AD pathology. Findings provide novel support for the "decoupling" hypothesis and reveal eigenvalue-based evidence of pathological destabilization in AD. Future optimization of the model, integrated with real-world clinical data, is expected to improve applications in personalized medicine for AD and other neurodegenerative diseases.

Yonsei Med J. 2017 May;58(3):479-488. (PMID: 28332351)
PLoS Comput Biol. 2014 Nov 20;10(11):e1003956. (PMID: 25412207)
J R Soc Interface. 2019 Oct 31;16(159):20190356. (PMID: 31615329)
Neuroimage. 2021 Aug 15;237:118126. (PMID: 33957234)
Commun Biol. 2021 Sep 9;4(1):1054. (PMID: 34504272)
Alzheimers Res Ther. 2010 Aug 31;2(4):23. (PMID: 20807454)
Nat Aging. 2024 May;4(5):694-708. (PMID: 38514824)
Alzheimers Dement. 2023 Feb;19(2):646-657. (PMID: 35633518)
Annu Rev Neurosci. 2011;34:185-204. (PMID: 21456963)
Inf Process Med Imaging. 2023 Jun;13939:208-221. (PMID: 38680427)
J Neurotrauma. 2008 Dec;25(12):1483-97. (PMID: 19125684)
Brain. 2008 Dec;131(Pt 12):3277-85. (PMID: 19022861)
Int J Biol Sci. 2021 May 27;17(9):2181-2192. (PMID: 34239348)
PLoS Comput Biol. 2012;8(8):e1002582. (PMID: 22915996)
Front Neurol. 2017 Nov 07;8:580. (PMID: 29163343)
Alzheimers Dement. 2025 Jan;21(1):e14373. (PMID: 39641322)
Alzheimers Dement (N Y). 2018 Sep 06;4:575-590. (PMID: 30406177)
J Alzheimers Dis. 2023;92(2):411-424. (PMID: 36776048)
Neuron. 2012 Mar 22;73(6):1204-15. (PMID: 22445347)
Front Aging Neurosci. 2021 May 06;13:624330. (PMID: 34025386)
Alzheimers Res Ther. 2010 Jan 22;2(1):1. (PMID: 20122289)
Ageing Res Rev. 2024 Nov;101:102481. (PMID: 39236855)
Neuron. 2009 Apr 16;62(1):42-52. (PMID: 19376066)
Nat Neurosci. 2024 Nov;27(11):2130-2137. (PMID: 39294489)
Immunol Rev. 2024 Oct;327(1):8-32. (PMID: 39470038)
Lancet. 2021 Apr 24;397(10284):1577-1590. (PMID: 33667416)
J Neurosci. 2009 Feb 11;29(6):1860-73. (PMID: 19211893)
Nature. 2017 Dec 20;552(7685):355-361. (PMID: 29293211)
Front Neurosci. 2020 Dec 23;14:566876. (PMID: 33424532)
Acta Pharmacol Sin. 2017 Sep;38(9):1205-1235. (PMID: 28713158)
Neuroimage. 2021 Jul 15;235:117980. (PMID: 33823273)
Proc Natl Acad Sci U S A. 2006 Jun 6;103(23):8864-9. (PMID: 16735465)
J Alzheimers Dis. 2016;51(2):377-89. (PMID: 26890769)
Front Cell Neurosci. 2015 Jul 01;9:248. (PMID: 26190973)
Trends Neurosci. 2013 Oct;36(10):561-9. (PMID: 23876425)
J Alzheimers Dis. 2018;64(s1):S611-S631. (PMID: 29865055)
Neurol Neurochir Pol. 2018 Aug;52(4):459-464. (PMID: 30025721)
Neuropsychol Rev. 2003 Jun;13(2):79-92. (PMID: 12887040)
Stroke. 2023 Jun;54(6):e251-e271. (PMID: 37009740)
Biol Psychiatry. 2010 Mar 15;67(6):584-7. (PMID: 19833321)
Int J Mol Sci. 2022 Aug 23;23(17):. (PMID: 36076944)
Curr Med Chem. 2008;15(23):2321-8. (PMID: 18855662)
Neuron. 2018 Jan 3;97(1):32-58. (PMID: 29301104)
Imaging Neurosci (Camb). 2024 Feb 05;2:1-19. (PMID: 38947941)
Eur J Nucl Med Mol Imaging. 2022 Jul;49(9):3173-3185. (PMID: 35199225)
Front Aging Neurosci. 2019 Aug 07;11:204. (PMID: 31447664)
Ann Neurol. 2011 Oct;70(4):532-40. (PMID: 22028219)
Signal Transduct Target Ther. 2024 Aug 23;9(1):211. (PMID: 39174535)
Nat Commun. 2020 May 26;11(1):2612. (PMID: 32457389)
Brain. 2014 Aug;137(Pt 8):2382-95. (PMID: 25057133)
J Alzheimers Dis. 2022;88(3):1127-1135. (PMID: 35754276)
Am J Manag Care. 2022 Sep;28(10 Suppl):S188-S196. (PMID: 36197132)

R56 AG056169 United States AG NIA NIH HHS; U01 AG024904 United States AG NIA NIH HHS; R01AG070937 United States NH NIH HHS; 194427 National Science Foundation; R01 AG056169 United States AG NIA NIH HHS; R35GM152245 United States NH NIH HHS; 253558 Chan Zuckerberg Initiative; U19 AG065169 United States AG NIA NIH HHS; R01 AG070937 United States AG NIA NIH HHS; R35 GM152245 United States GM NIGMS NIH HHS; U19AG056169 United States NH NIH HHS

Keywords: Alzheimer’s disease; aging; artificial intelligence; connectome; eigenvalue analysis; machine learning; network decoupling; neurodegeneration; pathology dynamics; temporal diffusion network

0 (Amyloid beta-Peptides)
0 (tau Proteins)

Date Created: 20250213 Date Completed: 20250507 Latest Revision: 20250507

20250508

PMC11817396

10.3390/ijms26031062

39940829