Dating the Emergence of Human Endemic Coronaviruses

Abstract

Four endemic coronaviruses infect humans and cause mild symptoms. Because previous analyses were based on a limited number of sequences and did not control for effects that affect molecular dating, we re-assessed the timing of endemic coronavirus emergence. After controlling for recombination, selective pressure, and molecular clock model, we obtained similar tMRCA (time to the most recent common ancestor) estimates for the four coronaviruses, ranging from 72 (HCoV-229E) to 54 (HCoV-NL63) years ago. The split times of HCoV-229E and HCoV-OC43 from camel alphacoronavirus and bovine coronavirus were dated ~268 and ~99 years ago. The split times of HCoV-HKU1 and HCoV-NL63 could not be calculated, as their zoonoticic sources are unknown. To compare the timing of coronavirus emergence to that of another respiratory virus, we recorded the occurrence of influenza pandemics since 1500. Although there is no clear relationship between pandemic occurrence and human population size, the frequency of influenza pandemics seems to intensify starting around 1700, which corresponds with the initial phase of exponential increase of human population and to the emergence of HCoV-229E. The frequency of flu pandemics in the 19th century also suggests that the concurrence of HCoV-OC43 emergence and the Russian flu pandemic may be due to chance.

Keywords: coronavirus; emerging infectious diseases; molecular dating; viral disease; virus evolution.

Figure 1

Recombination events and temporal signal. Unique recombination events in endemic coronaviruses (left panels). Each event is shown as a line with dots representing the start and the end. The non-recombinant regions used in the analyses are indicated with gray shadows. Schematic representations of coronavirus genomes are also reported. Plots of the root-to-tip distance as a function of sampling years are shown in the central panels. Each point corresponds to a viral sequence and the dotted line is the linear regression calculated using a method that minimizes the residual mean squares. The r coefficient and the corresponding p value are also shown. (right panels) report comparisons of branch lengths obtained using the aBSREL and the GTR models. Each dot represents an internal branch of a phylogenetic tree calculated using the longest non-recombinant regions of each endemic coronavirus.

Figure 2

HCoV-229E and HCoV-OC43 timescaled phylogenetic trees. Maximum likelihood trees estimated for the non-recombinant region of HCoV-229E (a) and HCoV-OC43 (b). Branch lengths represent the evolutionary time measured by the grids corresponding to the timescale shown at the tree base (in years). For internal nodes, 95% HPD bars are shown, and black dots indicate a posterior probability > 0.80 for that node.

Figure 3

Timeline of endemic coronavirus emergence. Colored horizontal bars represent the time span between the divergence of each coronavirus from the closest known animal virus and the tMRCA (time to the most recent common ancestor) of circulating strains. In the case of HCoV-HKU1 and HCoV-NL63 tMRCA are shown as colored dots. Gray bars indicate 95% HPD. Vertical lines represent influenza pandemic events and the scaled colors (from blue to red, see legend on the plot) indicate the proportion of articles reporting that event as pandemic [33,34,35,36,37,38,39,40,41,42]. The three recent coronavirus zoonoses are shown as black vertical lines. The world human population count from 1400 C.E. is reported as a dotted gray line.