A plasma protein classifier for predicting amyloid burden for preclinical Alzheimer’s disease

Abstract

A blood-based assessment of preclinical disease would have huge potential in the enrichment of participants for Alzheimer’s disease (AD) therapeutic trials. In this study, cognitively unimpaired individuals from the AIBL and KARVIAH cohorts were defined as A negative or A positive by positron emission tomography. Nontargeted proteomic analysis that incorporated peptide fractionation and high-resolution mass spectrometry quantified relative protein abundances in plasma samples from all participants. A protein classifier model was trained to predict A-positive participants using feature selection and machine learning in AIBL and independently assessed in KARVIAH. A 12-feature model for predicting A-positive participants was established and demonstrated high accuracy (testing area under the receiver operator characteristic curve = 0.891, sensitivity = 0.78, and specificity = 0.77). This extensive plasma proteomic study has unbiasedly highlighted putative and novel candidates for AD pathology that should be further validated with automated methodologies. Copyright © 2019 The Authors.

Document Type

Journal Article

PubMed ID

30775436

School

School of Medical and Health Sciences

RAS ID

28901

Copyright

free_to_read

Publisher

American Association for the Advancement of Science

Comments

Ashton, N. J., Nevado-Holgado, A. J., Barber, I. S., Lynham, S., Gupta, V., Chatterjee, P., . . . Hye, A. (2019). A plasma protein classifier for predicting amyloid burden for preclinical Alzheimer’s disease. Science Advances, 5(2). Available here

Share

 
COinS
 

Link to publisher version (DOI)

10.1126/sciadv.aau7220