Proof-of-principle demonstration of endogenous circadian system and circadian misalignment effects on human oral microbiota

Abstract

Circadian misalignment-the misalignment between the central circadian "clock" and behavioral and environmental cycles (including sleep/wake, fasting/eating, dark/light)-results in adverse cardiovascular and metabolic effects. Potential underlying mechanisms for these adverse effects include alterations in the orogastrointestinal microbiota. However, it remains unknown whether human oral microbiota has endogenous circadian rhythms (i.e., independent of sleep/wake, fasting/eating, and dark/light cycles) and whether circadian misalignment influences oral microbiota community composition. Healthy young individuals [27.3 ± 2.3 years (18-35 years), 4 men and 2 women, body-mass index range: 18-28 kg/m² ] were enrolled in a stringently controlled 14-day circadian laboratory protocol. This included a 32-h constant routine (CR) protocol (endogenous circadian baseline assessment), a forced desynchrony protocol with four 28-h "days" under ~3 lx to induce circadian misalignment, and a post-misalignment 40-h CR protocol. Microbiota assessments were performed on saliva samples collected every 4 h throughout both CR protocols. Total DNA was extracted and processed using high-throughput 16S ribosomal RNA gene amplicon sequencing. The relative abundance of specific oral microbiota populations, i.e., one of the five dominant phyla, and three of the fourteen dominant genera, exhibited significant endogenous circadian rhythms. Importantly, circadian misalignment dramatically altered the oral microbiota landscape, such that four of the five dominant phyla and eight of the fourteen dominant genera exhibited significant circadian misalignment effects. Moreover, circadian misalignment significantly affected the metagenome functional content of oral microbiota (inferred gene content analysis), as indicated by changes in specific functional pathways associated with metabolic control and immunity. Collectively, our proof-of-concept study provides evidence for endogenous circadian rhythms in human oral microbiota and show that even relatively short-term experimental circadian misalignment can dramatically affect microbiota community composition and functional pathways involved in metabolism and immune function. These proof-of-principle findings have translational relevance to individuals typically exposed to circadian misalignment, including night shift workers and frequent flyers.

Trial registration: ClinicalTrials.gov NCT02291952.

Keywords: circadian misalignment; circadian rhythms; functional pathways; microbiota; shift work.

Figure 1.. Study design.

The 14-day in-laboratory study design is presented with relative clock time (for an example research participant with a habitual wake-up time of 7:00AM) along the X-axis and study day along the Y-axis. Data presented in the manuscript are derived from the two constant routine protocols, Baseline CR (CR1; days 3–4) and Post-misalignment CR (CR2, days 11–13). During CR protocols, participants were kept awake, under constant posture (semi-recumbent, upper body at 45° angle), constant dim light (light levels <3lx), constant room temperature and humidity, and received isocaloric snacks every hour. Oral microbial community composition was assessed through saliva sampling every 4-h during CR conditions.

Figure 2.. Endogenous circadian rhythms in human oral microbiota.

Cosinor mixed-models of circadian rhythms were applied to the oral microbiota community composition. Phylum Proteobacteria (A) and the genus Neisseria (B) had significant endogenous circadian rhythms (Baseline CR). Genus Fusobacterium (C) and the genus Streptococcus (D) showed significant endogenous circadian rhythms (Baseline CR). The cosinor models use precise circadian phase data. To show that these models adequately fit the actual data, we also plot average data grouped into 60-circadian degree windows (~4-hour resolution) with standard error of the mean (SEM) error bars. Bottom x-axes corresponds to circadian phase with 0° indicating the timing of the fitted circadian core body temperature minimum (average ∼3:30AM during baseline CR in these participants). Top x-axes indicate the corresponding average clock time in these participants; left y-axes correspond to the percentage of each individual’s mean during Baseline CR; right y-axes indicate the relative abundance (% of total abundance); P values: significance of “circadian effect” derived from the cosinor mixed-model analyses.

Figure 3.. Circadian misalignment affects human oral microbiota.

Bubble plots graphically illustrate the circadian misalignment effects on oral microbiota composition at the phyla (A) and genera (B) taxonomical levels. Data correspond to the five dominant phyla (>1% threshold of relative abundance) and to the 14 dominant genera (>1% threshold of relative abundance). Each bubble plot corresponds to the difference from the baseline CR to the post-misalignment CR (CR2-CR1). X-axes: data was i. normalized as 100% of each participant’s mean during Baseline CR1, ii. detrended to remove the linear component, iii. averaged across all time points for each CR condition, iv. derived the difference from the baseline CR to post-misalignment CR at the individual level, and v. averaged across all participants, per phylum and genus. Y-axes: 5 dominant phyla (A) and 14 dominant genera (B), ordered by prevalence. The area of each bubble plot corresponds to the prevalence for each given phylum and genus averaged across all participants in both CR protocols. Data correspond to mean and standard error of the mean (SEM); P-values: significance of “circadian alignment condition” (aligned vs. misaligned) is derived from the cosinor mixed-model analyses (see “Statistical analyses“ for details).