The catalogue of Mycobacterium tuberculosis mutations associated with drug resistance to 12 drugs in China from a nationwide survey: a genomic analysis

Abstract

Background: WHO issued the first edition catalogue of Mycobacterium tuberculosis complex (MTBC) mutations associated with drug resistance in 2021. However, country-specific issues might lead to arising complex and additional drug-resistant mutations. We aimed to fully reflect the characteristics of drug resistance mutations in China.

Methods: We analysed MTBC isolates from the nationwide drug-resistant tuberculosis surveillance with 70 counties in 31 provinces, municipalities, and autonomous regions in China. Three types of MYCOTB plates were used to perform drug susceptibility testing for 12 antibiotics (rifampicin, isoniazid, ethambutol, levofloxacin, moxifloxacin, amikacin, kanamycin, ethionamide, clofazimine, linezolid, delamanid, and bedaquiline). Mutations were divided into five groups according to their odds ratios, positive predictive values, false discovery rate-corrected p values, and 95% CIs: (1) associated with resistance; (2) associated with resistance-interim; (3) uncertain significance; (4) not associated with resistance-interim; and (5) not associated with resistance. The Wilcoxon rank-sum and Kruskal-Wallis tests were used to quantify the association between mutations and minimum inhibitory concentrations (MICs). Our dataset was compared with the first edition of the WHO catalogue.

Findings: We analysed 10 146 MTBC isolates, of which 9071 (89·4%) isolates were included in the final analysis. 744 (8·2%) isolates were resistant to rifampicin and 1339 (14·8%) to isoniazid. 208 (1·9%) of 11 065 mutations were classified as associated with resistance or associated with resistance-interim. 33 (97·1%) of 34 mutations in group 1 and 92 (52·9%) of 174 in group 2 also appeared in groups 1 or 2 of the WHO catalogue. Of 81 indel mutations in group 2, 15 (18·5%) were in the WHO catalogue. The newly discovered mutation gyrA_Ala288Asp was associated with levofloxacin resistance. MIC values for rifampicin, isoniazid, moxifloxacin, and levofloxacin corresponding to resistance mutations in group 1 were significantly different (p<0·0001), and 12 high-level resistance mutations were detected. 61 mutations in group 3 occurred as solo in at least five phenotypically susceptible isolates, but with MIC values moderately higher than other susceptible isolates. Among 945 phenotypically resistant but genotypically susceptible isolates, 433 (45·8%) were mutated for at least one efflux pump gene.

Interpretation: Our analysis reflects the complexity of drug resistance mutations in China and suggests that indel mutations, efflux pump genes, protein structure, and MICs should be fully considered in the WHO catalogue, especially in countries with a high tuberculosis burden.

Funding: National Key Research and Development Program of China and the Science and Technology Major Project of Tibetan Autonomous Region of China.

Figure 1

Distribution of Mycobacterium tuberculosis complex isolates in China used in this catalogue of genotype–phenotype associations Pie charts show the proportion of isolates among different lineages for each location. The size of pie charts corresponds with the number of isolates.

Figure 2

Drug resistance classification and correlation to 12 anti-tuberculosis drugs (A) The frequency of resistance to each of the 12 drugs. (B) Pie chart showing the distribution of MDR or rifampicin-resistant, pre-XDR, and XDR isolates. (C) Spearman’s correlation of resistance to 12 drugs. FDR=false discovery rate. MDR=multidrug resistant. pre-XDR=pre-extensively drug resistant.

Figure 3

Comparison of the WHO catalogue and our dataset (A) The number of associations between the catalogues for each drug. (B) Venn diagram of the differences between our dataset and the first edition of the WHO catalogue for groups 1 and 2 mutations. (C) Boxplots of the proportion of solo mutations as the number of times the mutation was observed in groups 1 and 2 for our dataset and WHO data. The cross indicates the median, boxes indicate IQRs, bars indicate minimum and maximum values, and dots show outliers.