Machine learning to detect Alzheimer\textquoterights disease from circulating non-coding RNAs

Machine learning to detect Alzheimer\textquoterights disease from circulating non-coding RNAs. Ludwig, N., Fehlmann, T., Gogol, M., Maetzler, W., Deutscher, S., Gurlit, S., Schulte, C., von Thaler, A., Deuschle, C., Metzger, F., Berg, D., Suenkel, U., Keller, V., Backes, C., Lenhof, H., Meese, E., & Keller, A. bioRxiv, Cold Spring Harbor Laboratory, 2019.
$Machine learning to detect Alzheimer\textquoterights disease from circulating non-coding RNAs [link]$ Paper doi abstract bibtex 1 download

Background To develop therapeutics for Alzheimer\textquoterights disease, early detection of patients awakes new hope. Circulating small non-coding RNAs are among the prominent candidates for a blood-based diagnosis, requiring however growing cohort sizes.Methods We determined abundance levels of 21 known circulating microRNAs in 465 individuals encompassing Alzheimer\textquoterights patients and controls recruited in US and Germany. We computed models to assess the relation between microRNA-expression and phenotypes, gender, age and disease severity (Mini-Mental State Examination MMSE).Results 20 of 21 miRNAs were consistently dys-regulated in the US and Germany. 18 were significantly correlated to neurodegeneration (adjusted p<0.05) with highest significance for miR-532-5p (adjusted p=4.8×10-30). Ten miRNAs were significantly correlated with MMSE, in particular miR-26a/26b-5p (adjusted p=0.0002). Machine learning models reached an AUC value of 87.6% in differentiating AD patients from controls.Conclusions Our data provide strong evidence for the relevance of circulating non-coding RNAs to detect Alzheimer\textquoterights from a blood sample.

@article {Ludwig638213,
	author = {Ludwig, Nicole and Fehlmann, Tobias and Gogol, Manfred and Maetzler, Walter and Deutscher, Stephanie and Gurlit, Simone and Schulte, Claudia and von Thaler, Anna-Katharina and Deuschle, Christian and Metzger, Florian and Berg, Daniela and Suenkel, Ulrike and Keller, Verena and Backes, Christina and Lenhof, Hans-Peter and Meese, Eckart and Keller, Andreas},
	title = {Machine learning to detect Alzheimer{\textquoteright}s disease from circulating non-coding RNAs},
	elocation-id = {638213},
	year = {2019},
	doi = {10.1101/638213},
	publisher = {Cold Spring Harbor Laboratory},
	abstract = {Background To develop therapeutics for Alzheimer{\textquoteright}s disease, early detection of patients awakes new hope. Circulating small non-coding RNAs are among the prominent candidates for a blood-based diagnosis, requiring however growing cohort sizes.Methods We determined abundance levels of 21 known circulating microRNAs in 465 individuals encompassing Alzheimer{\textquoteright}s patients and controls recruited in US and Germany. We computed models to assess the relation between microRNA-expression and phenotypes, gender, age and disease severity (Mini-Mental State Examination MMSE).Results 20 of 21 miRNAs were consistently dys-regulated in the US and Germany. 18 were significantly correlated to neurodegeneration (adjusted p\&lt;0.05) with highest significance for miR-532-5p (adjusted p=4.8{\texttimes}10-30). Ten miRNAs were significantly correlated with MMSE, in particular miR-26a/26b-5p (adjusted p=0.0002). Machine learning models reached an AUC value of 87.6\% in differentiating AD patients from controls.Conclusions Our data provide strong evidence for the relevance of circulating non-coding RNAs to detect Alzheimer{\textquoteright}s from a blood sample.},
	URL = {https://www.biorxiv.org/content/early/2019/05/14/638213},
	eprint = {https://www.biorxiv.org/content/early/2019/05/14/638213.full.pdf},
	journal = {bioRxiv}
}

Downloads: 1