摘要：Accurate drug resistance detection is key for guiding effective tuberculosis treatment. While genotypic resistance can be rapidly detected by molecular methods, their application is challenged by mixed mycobacterial populations comprising both susceptible and resistant cells (heteroresistance). For this, next-generation sequencing (NGS) based approaches promise the determination of variants even at low frequencies. However, accurate methods for a valid detection of low-frequency variants in NGS data are currently lacking. To tackle this problem, we developed the variant detection tool binoSNP which allows the determination of low-frequency single nucleotide polymorphisms (SNPs) in NGS datasets from Mycobacterium tuberculosis complex (MTBC) strains. By taking a reference-mapped file as input, binoSNP evaluates each genomic position of interest using a binomial test procedure. binoSNP was validated using in-silico, in-vitro, and serial patient isolates datasets comprising varying genomic coverage depths (100-500×) and SNP allele frequencies (1-30%). Overall, the detection limit for low-frequency SNPs depends on the combination of coverage depth and allele frequency of the resistance-associated mutation. binoSNP allows for valid detection of resistance associated SNPs at a 1% frequency with a coverage ≥400×. In conclusion, binoSNP provides a valid approach to detect low-frequency resistance-mediating SNPs in NGS data from clinical MTBC strains. It can be implemented in automated, end-user friendly analysis tools for NGS data and is a step forward towards individualized TB therapy.
