Machine learning estimation of human body time using metabolomic profiling

Tom Woelders, Victoria L. Revell, Benita Middleton, Katrin Ackermann, Manfred Kayser, Florence I. Raynaud, Debra J. Skene, Roelof A. Hut*

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

9 Citations (Scopus)
39 Downloads (Pure)

Abstract

Circadian rhythms influence physiology, metabolism, and molecular processes in the human body. Estimation of individual body time (circadian phase) is therefore highly relevant for individual optimization of behavior (sleep, meals, sports), diagnostic sampling, medical treatment, and for treatment of circadian rhythm disorders. Here, we provide a partial least squares regression (PLSR) machine learning approach that uses plasma-derived metabolomics data in one or more samples to estimate dim light melatonin onset (DLMO) as a proxy for circadian phase of the human body. For this purpose, our protocol was aimed to stay close to real-life conditions. We found that a metabolomics approach optimized for either women or men under entrained conditions performed equally well or better than existing approaches using more labor-intensive RNA sequencing-based methods. Although estimation of circadian body time using blood-targeted metabolomics requires further validation in shift work and other real-world conditions, it currently may offer a robust, feasible technique with relatively high accuracy to aid personalized optimization of behavior and clinical treatment after appropriate validation in patient populations.

Original languageEnglish
Article numbere2212685120
JournalProceedings of the National Academy of Sciences of the United States of America
Volume120
Issue number18
DOIs
Publication statusPublished - 2 May 2023

Bibliographical note

Funding Information:
ACKNOWLEDGMENTS. Datasets used in this study are originally from Honma et al. (2020). We thank the researchers from the original studies (Joo Ern Ang, Sarah K. Davies, Pippa Gunn, Ben Holmes, Aya Honma) and the Faculty Metabolomics facility (Namrata R. Chowdhury, Anuska Mann, Chris Mitchell, Francesca P. Robertson) at the University of Surrey. We also thank Daniel Barrett, Cheryl Isherwood, and the Surrey Clinical Research Centre’s medical, clinical, and research teams for their help with the clinical studies. Melatonin and cortisol measurements were carried out by Stockgrand Ltd. This work was supported in part by the Netherlands Forensic Institute, Netherlands Genomics Initiative/ Netherlands Organization for Scientific Research within the framework of the Forensic Genomics Consortium Netherlands, the 6th Framework project EUCLOCK (018741), and UK Biotechnology and Biological Sciences Research Council Grant BB/I019405/1. Additional funding was received from the Cancer Research UK Cancer Therapeutics Unit award (Ref: C2739/A22897) and a Cancer Therapeutics Centre award (Ref: C309/A25144 to F.I.R.) and the Nederlandse Organisatie voor Wetenschappelijk Onderzoek - Stichting Technische Wetenschappen Perspective Program grant “OnTime” (project 12185 to T.W. and R.A.H.).

Publisher Copyright:
Copyright © 2023 the Author(s).

Fingerprint

Dive into the research topics of 'Machine learning estimation of human body time using metabolomic profiling'. Together they form a unique fingerprint.

Cite this