Whole-genome comparison of Mycobacterium tuberculosis clinical and laboratory strains

Abstract

Virulence and immunity are poorly understood in Mycobacterium tuberculosis. We sequenced the complete genome of the M. tuberculosis clinical strain CDC1551 and performed a whole-genome comparison with the laboratory strain H37Rv in order to identify polymorphic sequences with potential relevance to disease pathogenesis, immunity, and evolution. We found large-sequence and single-nucleotide polymorphisms in numerous genes. Polymorphic loci included a phospholipase C, a membrane lipoprotein, members of an adenylate cyclase gene family, and members of the PE/PPE gene family, some of which have been implicated in virulence or the host immune response. Several gene families, including the PE/PPE gene family, also had significantly higher synonymous and nonsynonymous substitution frequencies compared to the genome as a whole. We tested a large sample of M. tuberculosis clinical isolates for a subset of the large-sequence and single-nucleotide polymorphisms and found widespread genetic variability at many of these loci. We performed phylogenetic and epidemiological analysis to investigate the evolutionary relationships among isolates and the origins of specific polymorphic loci. A number of these polymorphisms appear to have occurred multiple times as independent events, suggesting that these changes may be under selective pressure. Together, these results demonstrate that polymorphisms among M. tuberculosis strains are more extensive than initially anticipated, and genetic variation may have an important role in disease pathogenesis and immunity.

FIG.1.

Circular representation of the M. tuberculosis chromosome illustrating the location of each predicted protein-coding region as well as selected features differing between the CDC1551 and H37Rv strains. The outer concentric circle shows predicted protein-coding regions on both strands, color coded according to role category. The second concentric circle shows the location of nonsynonymous substitutions (black). The third concentric circle shows the location of synonymous substitutions (blue). The fourth concentric circle shows the location of substitutions in noncoding regions (red). The fifth concentric circle shows the location of insertions in strain CDC1551, including coding (black) and noncoding (blue) regions, and the location of phage phiRv1 (red). The sixth concentric circle shows the location of insertions in strain H37Rv, including coding (black) and noncoding (blue) regions, and the location of phage phiRv1 (red). The seventh concentric circle shows the location of IS6110 insertion elements in strains CDC1551 (blue) and H37Rv (red). The eighth (innermost) concentric circle shows the location of tRNAs (blue) and rRNA (red).

FIG. 2.

(a) Schematic diagram of homologous genome region in strains H37Rv and CDC1551 encoding several membrane lipoproteins. The region in strain H37Rv contains two genes in tandem (Rv2543 and Rv2544) that are 87% identical to each other at the protein level. The homologous region in strain CDC1551 contains three genes (MT2618, MT2619, and MT2620), with the middle gene, MT2619, being unique to strain CDC1551 and 88 and 84% identical to MT2619 and MT2620, respectively. Homology between strain CDC1551 and M. bovis and equivalent evolutionary distances between paralogs suggest that the three paralogs arose in a common ancestor of the M. tuberculosis complex and subsequent loss of MT2619 occurred in the H37Rv lineage. (b) Schematic diagram of the tandem adenylate cyclase region. Two paralogous cyclases flank the region (MT1359/Rv1318c and MT1362/Rv1320c). Analysis revealed two cyclases (MT1360 and MT1361) between the two flanking genes in strain CDC1551 and only one cyclase (Rv1319c) in strain H37Rv. Rv1319c appears to be a chimera of the 5′ half of MT1361 and the 3′ half of MT1360. The 3′ halves of all orthologs share >80% nucleotide identity, while the 5′ halves appear diverse. Phylogenetic analysis indicates that the duplication events share a similar evolutionary distance. Inspection of the M. bovis sequence data reveals that this region is organized in an identical way to the H37Rv genome.

FIG. 3.

The distribution of CDC1551/H37Rv LSPs in clinical M. tuberculosis strains using a slot blot cross hybridization method. Strains include unique isolates and clustered strains with and without epidemiological links. Clusters are grouped by letter (and number if subtyped by a secondary fingerprinting method). Strains with epidemiological links are designated by links. Probes to LSPs are described in Table 3.

FIG. 4.

M. tuberculosis strain phylogeny based on a combination of LSPs, SNPs, and selected phenotypic traits. The tree shown is a consensus of the most parsimonious trees found using the heuristic search algorithm. Character state boxes are shown at the top (for LSPs, a blue box indicates presence and a yellow box indicates absence; for SNPs and other characters, colors correspond to different character states). Characters 1 to 12 are SNPs, characters 13 to 28 are LSPs, character 29 belongs to the Musser group, character 30 is Smear positive or negative, and character 31 is Site (pulmonary or extrapulmonary). Unresolved branching patterns are collapsed.

FIG. 5.

Consistency index for characters in the phylogenetic tree based on the LSPs and SNPs. Each column corresponds to the consistency index for a particular character (SNPs and LSPs). Each bar shows the minimum (black), average (striped), and maximum (grey) value of the consistency index over a large number of different trees (including multiple equally parsimonious trees and multiple distance trees). The percent variability indicates the variability of each marker in the 28 isolates tested. Calculations of the consistency indices were made using the MacClade program.