Role of Seasonal Importation and Random Genetic Drift on Selection for Drug-Resistant Genotypes of Plasmodium falciparum in High Transmission Settings

Abstract

Historically Plasmodium falciparum has followed a pattern of drug resistance first appearing in low transmission settings before spreading to high transmission settings. Several features of low-transmission regions are hypothesized as explanations: higher chance of symptoms and treatment seeking, better treatment access, less within-host competition among clones, and lower rates of recombination. Here, we test whether importation of drug-resistant parasites is more likely to lead to successful emergence and establishment in low-transmission or high-transmission periods of the same epidemiological setting, using a spatial, individual-based stochastic model of malaria and drug-resistance evolution calibrated for Burkina Faso. Upon controlling for the timing of importation of drug-resistant genotypes and examination of key model variables, we found that drug-resistant genotypes imported during the low transmission season were, (1) more susceptible to stochastic extinction due to the action of random genetic drift, and (2) more likely to lead to establishment of drug resistance when parasites are able to survive early stochastic loss due to drift. This implies that rare importation events are more likely to lead to establishment if they occur during a high-transmission season, but that constant importation (e.g., neighboring countries with high levels of resistance) may produce a greater risk during low-transmission periods.

Keywords: Anti-Malaria Drug Resistance; Burkina Faso; Genetic Drift; Importation; Malaria.

Figure 1.. 580Y frequency at model completion (after 20 years) based upon month of importation.

Circles show median allele frequency, bars show interquartile ranges, and violin plots show full range. As expected, the final frequency of 580Y increases as the number of importations increases (top to bottom) and when cases are symptomatic as opposed to asymptomatic (left to right). In most scenarios, importations that occur during periods of low seasonal transmission are more likely to result in establishment than cases imported during periods of high seasonal transmission (shaded region).

Figure 2.. Visualization of 580Y trajectories that reached extinction.

Plots show 580Y allele frequency trajectories under a scenario of one asymptomatic importation per month and are broken up into twelve panels by month of introduction. Only trajectories that reached extinction, out of fifty model runs, are shown. Title on each panel shows the month of introduction and the number (n) of trajectories that reached extinction in the first 20 years. The likelihood of extinction was higher in the low transmission season (78% to 92% during Jan-May) than in the high-transmission season (34% to 64% during Jun-Dec).

Figure 3.. Probability of successful emergence following importation.

Probabilities shown (circles) are maximum likelihood estimates from fifty simulations and bars show 95% confidence intervals (exact binomial method). Probabilities of emergence are stratified by month of importation (x-axis), by number of importation events per month (columns), and by whether the imported parasite occurred in an asymptomatic (top row) or symptomatic (bottom row) individual. Successful emergence is generally more likely for parasites imported during low transmission season (non-shaded).

Figure 4.. Visualization of 580Y trajectories that successfully emerged (frequency > 0.001).

Plots show 580Y allele frequency trajectories under a scenario of nine asymptomatic importations per month and are broken up into twelve panels by month of introduction. Only trajectories that reached an allele frequency >0.001, out of 50 simulations, are shown. Title on each panel shows the month of introduction and the number (n) of trajectories that successfully emerged. Successful emergence was higher in the low transmission season (12% to 18% during Jan-May) than in the high-transmission season (2% to 8% during Jun-Dec).

Figure 5.. Change in treatment seeking when controlling for seasonality and treatment seeking by age group.

Lines in each panel show median percentage of symptomatic malaria infections seeking treatment with shaded areas showing interquartile ranges from one hundred simulations. Panel titles show whether the epidemiological setting represents seasonal (right) or non-seasonal transmission (left), and whether treatment seeking is the same across age groups (“50–50”) with 50% of individuals seeking treatment (left) or uneven with 87% of children under-5 and 23.4% of individuals over-5 seeking treatment (right). In the presence of both seasonality and uneven treatment seeking across age groups, treatment coverage and thus selection pressure change through time (bottom right).

Figure 6.. Treatment coverage and fraction symptomatic (φ) from Jan 1, 2033, to Jan 1, 2036.

When examining a 36-month window, we clearly see that the population treatment coverage is slowly increasing (consistent with a gradual increase in treatment seeking over time) and that treatment coverage (right-axis) fluctuates moderately with the transmission season. The fraction of all infections that are symptomatic (φ) remains relatively constant (between 0.073 and 0.117) but fluctuates out-of-phase with treatment coverage. The product of φ and coverage (black line) fluctuates between 0.058 and 0.092. Medians and IQRs (shaded areas) shown from fifty simulations.

Figure 7.. Multiplicity of infection and fraction of multi-clonal infections harboring resistant alleles, from Jan 1, 2033, to Jan 1, 2036.

Mean multiplicity of infection (MOI) across individuals ranges from 1.55 to 2.75, peaking at the end of the low-transmission season. Fraction of multiclonal infections that harbor resistant alleles also fluctuates and peaks at the end of the high-transmission season (out of phase with MOI). There does not appear to be a particular period when 580Y alleles are experiencing maximum within-host competition from wild-type parasites. Medians and IQRs (shaded areas) shown from fifty simulations.