Accurate prediction of brain age using hippocampal microarray data
-
1
Wellcome Trust/University of Cambridge, United Kingdom
We have trained a classifier to predict age of mice, such that 90% of samples aged between 2--18 months of age are predicted within two months of their actual age. The classifier is trained and tested using data from 189 Illumina Mouse WG2 microarrays, which were probed with hippocampal mRNA. Accurate predictions can be made using only 20 microarray probes, though 100 probes is optimal. This shows that a minimal set of genes can explain ageing of the hippocampus. The time course profiles of the genes involved reveal several stages of cognitive ageing. Wheel running has been shown in various behavioural/electrophysiological paragraphs to slow the rate of ageing, and we show that the classifier is able to detect the reduced rate of ageing in aged mice which have had lifelong access to a running wheel.
Keywords:
age,
Ageing,
Aging,
Microarray,
machine learning,
Support vector machine,
prediction,
SVM,
Transcriptomics
Conference:
Neuroinformatics 2014, Leiden, Netherlands, 25 Aug - 27 Aug, 2014.
Presentation Type:
Demo, to be considered for oral presentation
Topic:
Genomics and genetics
Citation:
Skene
N
(2014). Accurate prediction of brain age using hippocampal microarray data.
Front. Neuroinform.
Conference Abstract:
Neuroinformatics 2014.
doi: 10.3389/conf.fninf.2014.18.00013
Copyright:
The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers.
They are made available through the Frontiers publishing platform as a service to conference organizers and presenters.
The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated.
Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed.
For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions.
Received:
27 Mar 2014;
Published Online:
04 Jun 2014.
*
Correspondence:
Mr. Nathan Skene, Wellcome Trust/University of Cambridge, Cambridge, United Kingdom, nskene@exseed.ed.ac.uk