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

Nicholas J. Ashton; Alejo J. Nevado-Holgado; Imelda S. Barber; Steven Lynham; Veer Gupta; Pratishtha Chatterjee; Kathryn Goozee; Eugene Hone; Steve Pedrini; Kaj Blennow; Michael Schöll; Henrik Zetterberg; Kathryn A. Ellis; Ashley I. Bush; Christopher C. Rowe; Victor L. Villemagne; David Ames; Colin L. Masters; Dag Aarsland; John Powell; Simon Lovestone; Ralph Martins; Abdul Hye

doi:10.1126/sciadv.aau7220

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

Nicholas J. Ashton, Alejo J. Nevado-Holgado, Imelda S. Barber, Steven Lynham, Veer Gupta, Pratishtha Chatterjee, Kathryn Goozee, Eugene Hone, Steve Pedrini, Kaj Blennow, Michael Schöll, Henrik Zetterberg, Kathryn A. Ellis, Ashley I. Bush, Christopher C. Rowe, Victor L. Villemagne, David Ames, Colin L. Masters, Dag Aarsland, John PowellSimon Lovestone, Ralph Martins, Abdul Hye^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

57 Citations (Scopus)

50 Downloads (Pure)

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 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.

Original language	English
Article number	eaau7220
Pages (from-to)	1-12
Number of pages	12
Journal	Science Advances
Volume	5
Issue number	2
DOIs	https://doi.org/10.1126/sciadv.aau7220
Publication status	Published - 6 Feb 2019

Bibliographical note

Copyright the Author(s) 2019. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

Access to Document

10.1126/sciadv.aau7220

Publisher version (open access)Final published version, 650 KBLicence: CC BY-NC

Cite this

Ashton, N. J., Nevado-Holgado, A. J., Barber, I. S., Lynham, S., Gupta, V., Chatterjee, P., Goozee, K., Hone, E., Pedrini, S., Blennow, K., Schöll, M., Zetterberg, H., Ellis, K. A., Bush, A. I., Rowe, C. C., Villemagne, V. L., Ames, D., Masters, C. L., Aarsland, D., ... Hye, A. (2019). A plasma protein classifier for predicting amyloid burden for preclinical Alzheimer’s disease. Science Advances, 5(2), 1-12. Article eaau7220. https://doi.org/10.1126/sciadv.aau7220

@article{210ce0acdb314ac0a5eaf75ce4adf8d3,

title = "A plasma protein classifier for predicting amyloid burden for preclinical Alzheimer{\textquoteright}s disease",

abstract = "A blood-based assessment of preclinical disease would have huge potential in the enrichment of participants for Alzheimer{\textquoteright}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.",

author = "Ashton, {Nicholas J.} and Nevado-Holgado, {Alejo J.} and Barber, {Imelda S.} and Steven Lynham and Veer Gupta and Pratishtha Chatterjee and Kathryn Goozee and Eugene Hone and Steve Pedrini and Kaj Blennow and Michael Sch{\"o}ll and Henrik Zetterberg and Ellis, {Kathryn A.} and Bush, {Ashley I.} and Rowe, {Christopher C.} and Villemagne, {Victor L.} and David Ames and Masters, {Colin L.} and Dag Aarsland and John Powell and Simon Lovestone and Ralph Martins and Abdul Hye",

note = "Copyright the Author(s) 2019. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.",

year = "2019",

month = feb,

day = "6",

doi = "10.1126/sciadv.aau7220",

language = "English",

volume = "5",

pages = "1--12",

journal = "Science Advances",

issn = "2375-2548",

publisher = "American Association for the Advancement of Science",

number = "2",

}

Ashton, NJ, Nevado-Holgado, AJ, Barber, IS, Lynham, S, Gupta, V, Chatterjee, P , Goozee, K, Hone, E, Pedrini, S, Blennow, K, Schöll, M, Zetterberg, H, Ellis, KA, Bush, AI, Rowe, CC, Villemagne, VL, Ames, D, Masters, CL, Aarsland, D, Powell, J, Lovestone, S, Martins, R & Hye, A 2019, 'A plasma protein classifier for predicting amyloid burden for preclinical Alzheimer’s disease', Science Advances, vol. 5, no. 2, eaau7220, pp. 1-12. https://doi.org/10.1126/sciadv.aau7220

TY - JOUR

T1 - A plasma protein classifier for predicting amyloid burden for preclinical Alzheimer’s disease

AU - Ashton, Nicholas J.

AU - Nevado-Holgado, Alejo J.

AU - Barber, Imelda S.

AU - Lynham, Steven

AU - Gupta, Veer

AU - Chatterjee, Pratishtha

AU - Goozee, Kathryn

AU - Hone, Eugene

AU - Pedrini, Steve

AU - Blennow, Kaj

AU - Schöll, Michael

AU - Zetterberg, Henrik

AU - Ellis, Kathryn A.

AU - Bush, Ashley I.

AU - Rowe, Christopher C.

AU - Villemagne, Victor L.

AU - Ames, David

AU - Masters, Colin L.

AU - Aarsland, Dag

AU - Powell, John

AU - Lovestone, Simon

AU - Martins, Ralph

AU - Hye, Abdul

N1 - Copyright the Author(s) 2019. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

PY - 2019/2/6

Y1 - 2019/2/6

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85061324358&partnerID=8YFLogxK

U2 - 10.1126/sciadv.aau7220

DO - 10.1126/sciadv.aau7220

M3 - Article

C2 - 30775436

AN - SCOPUS:85061324358

SN - 2375-2548

VL - 5

SP - 1

EP - 12

JO - Science Advances

JF - Science Advances

IS - 2

M1 - eaau7220

ER -

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

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this