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

2019-02

Ashton, Nicholas J

Nevado-Holgado, Alejo J

Barber, Imelda S

Lynham, Steven

Gupta, Veer

Chatterjee, Pratishtha

Goozee, Kathryn

Hone, Eugene

Pedrini, Steve

Blennow, Kaj

Schöll, Michael

Zetterberg, Henrik

Ellis, Kathryn A

Bush, Ashley I

Rowe, Christopher C

Villemagne, Victor L

Ames, David

Masters, Colin L

Aarsland, Dag

Powell, John

Lovestone, Simon

Martins, Ralph

Hye, Abdul

Journal Article

0000-0001-9276-2720

0000-0003-3756-6430

0000-0002-3573-1554

0000-0001-6708-3718

0000-0002-6409-8022

0000-0002-1890-4193

0000-0001-7800-1781

0000-0001-8259-9069

0000-0002-5832-9875

0000-0003-3072-7940

0000-0001-6314-216X

0000-0001-6124-439X

0000-0002-4828-9363

0000-0003-2237-4823

0000-0003-3910-2453

10.1126/sciadv.aau7220

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 Aβ negative or Aβ 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 Aβ-positive participants using feature selection and machine learning in AIBL and independently assessed in KARVIAH. A 12-feature model for predicting Aβ-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.

link

Science advances 2019; 5(2): eaau7220

Science advances