Soluble amyloid-beta isoforms predict downstream Alzheimer’s disease pathology

Cell & Bioscience

Tharick A. Pascoal¹  Wagner S. Brum²  Andrei Bieger²  Marco Antônio De Bastiani²  Bruna Bellaver²  Diogo O. Souza³  Pamela C. L. Ferreira⁴  Eduardo R. Zimmer⁵  Guilherme Povala⁶  Bruno Zatt⁷  Ricardo M. Araujo⁷  Andrea L. Benedet⁸  Pedro Rosa-Neto⁹ 

[1] Department of Neurology and Psychiatry, University of Pittsburgh, Pittsburgh, USA;Graduate Program in Biological Sciences: Biochemistry, Universidade Federal do Rio Grande do Sul (UFRGS), Porto Alegre, Brazil;Graduate Program in Biological Sciences: Biochemistry, Universidade Federal do Rio Grande do Sul (UFRGS), Porto Alegre, Brazil;Department of Biochemistry, Universidade Federal do Rio Grande do Sul (UFRGS), Porto Alegre, Brazil;Graduate Program in Biological Sciences: Biochemistry, Universidade Federal do Rio Grande do Sul (UFRGS), Porto Alegre, Brazil;Department of Neurology and Psychiatry, University of Pittsburgh, Pittsburgh, USA;Graduate Program in Biological Sciences: Biochemistry, Universidade Federal do Rio Grande do Sul (UFRGS), Porto Alegre, Brazil;Department of Pharmacology, Universidade Federal do Rio Grande do Sul (UFRGS), Porto Alegre, Brazil;Graduate Program in Biological Sciences: Pharmacology and Therapeutics, Universidade Federal do Rio Grande do Sul (UFRGS), Porto Alegre, Brazil;Graduate Program in Biological Sciences: Biochemistry, Universidade Federal do Rio Grande do Sul (UFRGS), Porto Alegre, Brazil;Graduate Program in Computing, Universidade Federal de Pelotas (UFPEL), Pelotas, Brazil;Graduate Program in Computing, Universidade Federal de Pelotas (UFPEL), Pelotas, Brazil;Translational Neuroimaging Laboratory, The McGill University Research Centre for Studies in Aging, 6825 LaSalle Boulevard, H4H 1R3, Verdun, QC, Canada;Montreal Neurological Institute, 3801 University Street, H3A 2B4, Montreal, QC, Canada;Translational Neuroimaging Laboratory, The McGill University Research Centre for Studies in Aging, 6825 LaSalle Boulevard, H4H 1R3, Verdun, QC, Canada;Montreal Neurological Institute, 3801 University Street, H3A 2B4, Montreal, QC, Canada;Douglas Hospital, McGill University, 6875 La Salle Blvd-FBC room 3149, H4H 1R3, Montreal, QC, Canada;

关键词: Alzheimer’s disease;    Amyloid-beta;    Tau pathology;    Neurodegeneration;    Machine learning;    Proteomics;   

DOI  :  10.1186/s13578-021-00712-3

来源: Springer

【 摘 要 】

BackgroundChanges in soluble amyloid-beta (Aβ) levels in cerebrospinal fluid (CSF) are detectable at early preclinical stages of Alzheimer’s disease (AD). However, whether Aβ levels can predict downstream AD pathological features in cognitively unimpaired (CU) individuals remains unclear. With this in mind, we aimed at investigating whether a combination of soluble Aβ isoforms can predict tau pathology (T+) and neurodegeneration (N+) positivity.MethodsWe used CSF measurements of three soluble Aβ peptides (Aβ1–38, Aβ1–40 and Aβ1–42) in CU individuals (n = 318) as input features in machine learning (ML) models aiming at predicting T+ and N+. Input data was used for building 2046 tuned predictive ML models with a nested cross-validation technique. Additionally, proteomics data was employed to investigate the functional enrichment of biological processes altered in T+ and N+ individuals.ResultsOur findings indicate that Aβ isoforms can predict T+ and N+ with an area under the curve (AUC) of 0.929 and 0.936, respectively. Additionally, proteomics analysis identified 17 differentially expressed proteins (DEPs) in individuals wrongly classified by our ML model. More specifically, enrichment analysis of gene ontology biological processes revealed an upregulation in myelinization and glucose metabolism-related processes in CU individuals wrongly predicted as T+. A significant enrichment of DEPs in pathways including biosynthesis of amino acids, glycolysis/gluconeogenesis, carbon metabolism, cell adhesion molecules and prion disease was also observed.ConclusionsOur results demonstrate that, by applying a refined ML analysis, a combination of Aβ isoforms can predict T+ and N+ with a high AUC. CSF proteomics analysis highlighted a promising group of proteins that can be further explored for improving T+ and N+ prediction.

【 授权许可】

CC BY