Machine Learning Selection of Most Predictive Brain Proteins Suggests Role of Sugar Metabolism in Alzheimer's Disease.

The complex and not yet fully understood etiology of Alzheimer's disease (AD) shows important proteopathic signs which are unlikely to be linked to a single protein. However, protein subsets from deep proteomic datasets can be useful in stratifying patient risk, identifying stage dependent disease markers, and suggesting possible disease mechanisms. The objective was to identify protein subsets that best classify subjects into control, asymptomatic Alzheimer's disease (AsymAD), and AD. Data comprised 6 cohorts; 620 subjects; 3,334 proteins. Brain tissue-derived predictive protein subsets for classifying AD, AsymAD, or control were identified and validated with label-free quantification and machine learning. A 29-protein subset accurately classified AD (AUC = 0.94). However, an 88-protein subset best predicted AsymAD (AUC = 0.85) or Control (AUC = 0.89) from AD (AUC = 0.96). AD versus Control: APP, DHX15, NRXN1, PBXIP1, RABEP1, STOM, and VGF. AD versus AsymAD: ALDH1A1, BDH2, C4A, FABP7, GABBR2, GNAI3, PBXIP1, and PKAR1B. AsymAD versus Control: APP, C4A, DMXL1, EXOC2, PITPNB, REBEP1, and VGF. Additional predictors: DNAJA3, PTBP2, SLC30A9, VAT1L, CROCC, PNP, SNCB, PRKAR1B, ENPP6, HAPLN2, PSMD4, and CMAS. Biomarkers were dynamically separable across disease stages. Predictive proteins were significantly enriched to sugar metabolism.

Citation

Raghav Tandon, Allan I Levey, James J Lah, Nicholas T Seyfried, Cassie S Mitchell. Machine Learning Selection of Most Predictive Brain Proteins Suggests Role of Sugar Metabolism in Alzheimer's Disease. Journal of Alzheimer's disease : JAD. 2023 Mar 21

PMID: 36776048

search → result