Evidence for recombination in Mycobacterium tuberculosis

Abstract

Due to its mostly isolated living environment, Mycobacterium tuberculosis is generally believed to be highly clonal, and thus recombination between different strains must be rare and is not critical for the survival of the species. To investigate the roles recombination could have possibly played in the evolution of M. tuberculosis, an analysis was conducted on previously determined genotypes of 36 synonymous single nucleotide polymorphisms (SNPs) in 3,320 M. tuberculosis isolates. The results confirmed the predominant clonal structure of the M. tuberculosis population. However, recombination between different strains was also suggested. To further resolve the issue, 175 intergenic SNPs and 234 synonymous SNPs were genotyped in 37 selected representative strains. A clear mosaic polymorphic pattern ahead of the MT0105 locus encoding a PPE (Pro-Pro-Glu) protein was obtained, which is most likely a result of recombination hot spot. Given that PPE proteins are thought to be critical in host-pathogen interactions, we hypothesize that recombination has been influential in the history of M. tuberculosis and possibly a major contributor to the diversity observed ahead of the MT0105 locus.

FIG. 1.

Mosaic pattern of iSNP in IRMT0105. Deletions are indicated by colons.

FIG. 2.

Recombination detection results of GENECONV and maximum chi-square for strain HN1890 (cluster IV) versus HN2366 (II), TN11607 (III), TN10225 (IV), and TN10757 (V). Dashed lines correspond to local and global significance cuts of the test statistics used (see reference for details). Both the highest red bar in plot A and the interval between the two highest peaks in plot B correspond to the first block of the IRMT0105 iSNPs of HN1890: TTTGGGTTAGTGGATGGCGATAGG. Both algorithms were run with RDP software. GENECONV used the default setting except that each indel site was treated as a polymorphism. Maximum chi-square used the default setting except that gaps were included.

FIG. 3.

Phylogenic trees of strains HN1890 (cluster IV), M. bovis TN10130 (10130MB), HN2366 (II), TN11607 (III), TN10225 (IV) and TN10757 (V) with M. bovis TN10130 as the root. (A) Neighbor-joining tree based on 363 background SNPs. (B) Neighbor-joining tree based on the first 24 iSNPs of IRMT0105. Bootstrap value 35 refers to the cluster of HN1890 and HN2366. (C) Neighbor-joining tree based on the last 22 iSNPs of IRMT0105. Numbers shown on the trees are bootstrap numbers. Assuming no recombination in background SNPs, tree A was supposed to show the true phylogenic relationship of the strains. Tree C was built with the second half of IRMT0105 iSNPs. The relationship shown is similar to that of tree A although with lower differentiating power. However, in tree B, HN1890 jumped from a close cluster with TN1075, TN11607, and TN10225 to the close cluster with HN2366 near the root. This dramatic change of phylogenic relationship suggested a recombination event.

FIG. 4.

Neighbor-joining tree based on background SNPs. Bootstrap numbers are shown on the tree. Arrows show the position of one possible scenario of eight possible recombination events.