Cross-host evolution of severe acute respiratory syndrome coronavirus in palm civet and human

Abstract

The genomic sequences of severe acute respiratory syndrome coronaviruses from human and palm civet of the 2003/2004 outbreak in the city of Guangzhou, China, were nearly identical. Phylogenetic analysis suggested an independent viral invasion from animal to human in this new episode. Combining all existing data but excluding singletons, we identified 202 single-nucleotide variations. Among them, 17 are polymorphic in palm civets only. The ratio of nonsynonymous/synonymous nucleotide substitution in palm civets collected 1 yr apart from different geographic locations is very high, suggesting a rapid evolving process of viral proteins in civet as well, much like their adaptation in the human host in the early 2002-2003 epidemic. Major genetic variations in some critical genes, particularly the Spike gene, seemed essential for the transition from animal-to-human transmission to human-to-human transmission, which eventually caused the first severe acute respiratory syndrome outbreak of 2002/2003.

Fig. 1.

Genotype clustering of SARS-CoV covering the epidemics from 2002 to 2004. It is illustrated by an unrooted phylogenetic tree constructed with complete SNVs and deletions of 91 sequences from the human patient-derived viruses (HP) and five sequences from the palm civet-derived viruses (PC) (A) and a neighbor-joining (N-J) tree for the consensus nucleotide sequences of PC and early individual transmission lineages of HP (B). In A, the division of the clusters and the corresponding nomenclatures was based on both the hosts of the viruses and the phases of the epidemic (7) (Table 2). The map distance between individual sequences represents the extent of genotypic difference. To highlight the variations between two neighboring clusters, the number of SNVs [total (synonymous, nonsynonymous causing drastic amino acid changes)] occurring among the genomic sequences of both groups and the average number of nucleotide difference D between the two sample groups (see Materials and Methods) were shown in the boxes. Besides the SNVs of the whole genome (Total), those occurring in orf1ab (particularly in orf1a, which is part of Orf1ab), S, and sars3a are listed in the same manner as the total SNVs. These SNVs were present in at least two independent samples of all the sequences used for this analysis. In B, consensus nucleotide sequences were derived from each PC and HP data set. For HP03E, consensus nucleotide sequences were individually derived from three primary transmission lineages, based on their direct epidemiological connections and high genomic sequence similarities, and were represented as HP03EGZ (Guangzhou), HP03EHSZ (Shenzhen), and HP03EZS (Zhongshan). These six consensus nucleotide sequences were used to construct the N-J tree (8) in mega2 (23), and the Kimura 2-parameter model was assumed. The branch lengths are the estimates of genetic distances.

Fig. 2.

A plot of the number of synonymous substitutions per synonymous site, Ks, for the concatenated coding sequences vs. the sampling dates. The Ks calculation and samples used are described in Materials and Methods. The sampling dates are measured as the number of days away from Jan. 1, 2003. The slope (β₁) of the fitted line from the linear regression model gives the estimation of the neutral rate, 8.00 × 10^-6 per site per day.

Fig. 3.

A rooted phylogenetic tree for SARS-CoV isolates from palm civet (PC03 and PC04) and early human patients (HP03E and HP04) based on MRCA estimations. All data are described in Materials and Methods except that for HP03E, which was from previous work (7). The branch length is proportional to the time interval.

Fig. 4.

Phylogeny of the most variable genes, S (A), sars3a (B), and nsp3 (C) in the SARS-CoV samples from the early cases of the epidemic 2002–2003 and the new cases of the 2003–2004 outbreak. Samples of the early cases of the 2002–2003 epidemic were selected based on two criteria: the completeness of the sequences and their representativity in each of the epidemiology lineages. The two numbers shown along each branch are the maximum-likelihood estimates of the numbers of synonymous and nonsynonymous substitutions for each entire gene along the branch (Materials and Methods). In each tree, a different dN/dS ratio is assumed for each branch. The branch length is proportional to the total number of estimated synonymous and nonsynonymous substitutions occurring in that branch.