Serial image analysis of Mycobacterium tuberculosis colony growth reveals a persistent subpopulation in sputum during treatment of pulmonary TB

Abstract

Faster elimination of drug tolerant 'persister' bacteria may shorten treatment of tuberculosis (TB) but no method exists to quantify persisters in clinical samples. We used automated image analysis to assess whether studying growth characteristics of individual Mycobacterium tuberculosis colonies from sputum on solid media during early TB treatment facilitates 'persister' phenotyping. As Time to Detection (TTD) in liquid culture inversely correlates with total bacterial load we also evaluated the relationship between individual colony growth parameters and TTD. Sputum from TB patients in Malawi was prepared for solid and liquid culture after 0, 2 and 4 weeks of treatment. Serial photography of agar plates was used to measure time to appearance (lag time) and radial growth rate for each colony. Mixed-effects modelling was used to analyse changing growth characteristics from serial samples. 20 patients had colony measurements recorded at ≥1 time-point. Overall lag time increased by 6.5 days between baseline and two weeks (p = 0.0001). Total colony count/ml showed typical biphasic elimination, but long lag time colonies (>20days) had slower, monophasic decline. TTD was associated with minimum lag time (time to appearance of first colony1). Slower elimination of long lag time colonies suggests that these may represent a persister subpopulation of bacilli.

Keywords: Biomarkers; Drug tolerance; Persisters; Pharmacodynamics.

Figure 1

Observed distributions of colonies' lag times and growth rates change over time on treatment. A. Box plots showing lag times (top) and radial growth rates (bottom) of observed H37Rv plate colonies (n = 269), and observed colonies recovered from clinical isolates (n = 1352) at three time points into treatment (0, 2, and 4 weeks). Box shows median and interquartile range. B. Scatterplots of lag time and growth rate for colonies recovered from clinical isolates at the 3 treatment time points. Partitioning the colonies above and below the overall median lag time of 20 days, indicated by red circle and green triangle markers, shows that bacilli forming colonies with shorter lag time are the dominant sub-population at baseline, but are a minority after 2 or 4 weeks of treatment.

Figure 2

CFU elimination from sputum over first 4 weeks treatment shows different dynamics for short and long lag time colonies. Each data point represents a colony count for an individual patient sputum sample, averaged across usable plate replicates; each patient therefore contributes one colony count at each timepoint, less data points at later timepoints results from higher rates of culture negativity, contamination, and loss to follow up (n = 19 at 0 weeks, n = 10 at 2 weeks, n = 6 at 4 weeks). A. CFU count per ml sputum for patients at baseline, 2 weeks, and 4 weeks into treatment were multiplied by the proportion of observed colonies which had lag time ≤20 days in the sample, giving a ‘short lag CFU’ count per ml. A segmented line of best fit – allowed to bend at one point as shown – reduces residual sum of squares (RSS) compared to a single gradient line of best fit with a trend towards statistical significance for the improved fit (segmented linear regression RSS = 18.1, unsegmented linear regression RSS = 20.2; comparison by ANOVA, p = 0.09). B. CFU count per ml sputum multiplied by proportion of observed colonies with lag time >20 days in sample, giving elimination kinetics of ‘prolonged lag CFU’. Fitting a segmented line of best fit does not improve residual sum of squares compared with single gradient line of best fit (segmented linear regression RSS = 21.5, unsegmented linear regression RSS = 21.5; comparison by ANOVA, p = 0.93). Samples with zero short lag CFU (below limit of detection) were excluded to allow plotting on the log scale (n = 4 samples). Shaded areas show 95% confidence intervals around line of best fit.