Automated feature extraction from population wearable device data identified novel loci associated with sleep and circadian rhythms

• Published in: PLoS genetics Vol. 16; no. 10; p. e1009089
• Main Authors: Li, Xinyue, Zhao, Hongyu
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 19.10.2020; Public Library of Science (PLoS)
• Subjects: Accelerometers; Actigraphy - methods; Biobanks; Biology and Life Sciences; Body mass index; Central nervous system; Chromosomes; Circadian rhythm; Circadian Rhythm - genetics; Circadian Rhythm - physiology; Circadian rhythms; Diaries; Electronic data processing; Exercise; Female; Gene loci; Genetic aspects; Genetic factors; Genetic Predisposition to Disease; Genome-wide association studies; Genome-Wide Association Study; Genomes; Humans; Identification and classification; Insomnia; Learning algorithms; Machine learning; Male; Markov Chains; Medicine and Health Sciences; Mental disorders; Metabolism; Middle Aged; Neurological diseases; Phenotypes; Physical activity; Physical sciences; Population; Population genetics; Population studies; Quantitative trait loci; Sleep; Sleep - genetics; Sleep - physiology; Sleep and wakefulness; Sleep disorders; Sleep Wake Disorders - genetics; Sleep Wake Disorders - pathology; Wearable computers; Wearable Electronic Devices; United States; United Kingdom > UK; United States > US
• ISSN: 1553-7404; 1553-7390; 1553-7404
• DOI: 10.1371/journal.pgen.1009089

Wearable devices have been increasingly used in research to provide continuous physical activity monitoring, but how to effectively extract features remains challenging for researchers. To analyze the generated actigraphy data in large-scale population studies, we developed computationally efficient methods to derive sleep and activity features through a Hidden Markov Model-based sleep/wake identification algorithm, and circadian rhythm features through a Penalized Multi-band Learning approach adapted from machine learning. Unsupervised feature extraction is useful when labeled data are unavailable, especially in large-scale population studies. We applied these two methods to the UK Biobank wearable device data and used the derived sleep and circadian features as phenotypes in genome-wide association studies. We identified 53 genetic loci with p<5×10-8 including genes known to be associated with sleep disorders and circadian rhythms as well as novel loci associated with Body Mass Index, mental diseases and neurological disorders, which suggest shared genetic factors of sleep and circadian rhythms with physical and mental health. Further cross-tissue enrichment analysis highlights the important role of the central nervous system and the shared genetic architecture with metabolism-related traits and the metabolic system. Our study demonstrates the effectiveness of our unsupervised methods for wearable device data when additional training data cannot be easily acquired, and our study further expands the application of wearable devices in population studies and genetic studies to provide novel biological insights.