Getting rid of 'rain' and 'stars': Mitigating inhibition effects on ddPCR data analysis, the case study of the invasive crayfish Pacifastacus leniusculus in the streams of Luxembourg

Abstract

ddPCR is becoming one of the most widely used tool in the field of eDNA-based aquatic monitoring. Although emulsion PCR used in ddPCR confers a partial mitigation to inhibition due to the high number of reactions for a single sample (between 10K and 20K), it is not impervious to it. Our results showed that inhibition impacts the amplitude of fluorescence in positive droplets with a different intensity among rivers. This signal fluctuation could jeopardize the use of a shared threshold among samples from different origin, and thus the accurate assignment of the positive droplets which is particularly important for low concentration samples such as eDNA ones: amplification events are scarce, thus their objective discrimination as positive is crucial. Another issue, related to target low concentration, is the artifactual generation of high fluorescence droplets ('stars'). Indeed, these could be counted as positive with a single threshold solution, which in turn could produce false positive and incorrect target concentration assessments. Approximating the positive and negative droplets distribution as normal, we proposed here a double threshold method accounting for both high fluorescence droplets ('stars') and PCR inhibition impact in delineating positive droplets clouds. In the context of low concentration template recovered from environmental samples, the application of this method of double threshold establishment could allow for a consistent sorting of the positive and negative droplets throughout ddPCR data generated from samples with varying levels of inhibitor contents. Due to low concentrations template and inhibition effects, Quantasoft software produced an important number of false negatives and positive comparatively to the double threshold method developed here. This case study allowed the detection of the invasive crayfish P. leniusculus in 32 out of 34 sampled sites from two main rivers (Alzette and Sûre) and five of their tributaries (Eisch, Attert, Mamer, Wiltz and Clerve).

Fig 1. Localization of the 34 sampling sites.

The colors of the dots represent the different rivers sampled (Red = Alzette, Blue = Sure, Green = Eisch, Brown = Clerve, Pink = Wiltz, Orange = Attert, Purple = Mamer).

Fig 2. Schematic workflow of the data treatment.

(a) Export of the raw fluorescence data from positive control (genomic extract at 15 ng/μl) spiked with two different amount of river eDNA extract in order to define the part of the signal that can be accounted as ‘rain’ and stars’; (b) from these data, for each rivers (n = 6 for the main rivers Alzette and Sûre and n = 3 for tributaries Eisch, Attert, Mamer, Wiltz, Clerve), the descriptive statistics (Mean pos. = Mean fluorescence value for the positive droplets cloud, ∂ = standard deviation for the positive cloud and mean neg. = Mean fluorescence value for the negative droplets cloud) were calculated and, in turn, used to estimate the two threshold correction factors (Upper Threshold Correction Factor (UTCF) and Lower Threshold Correction Factor (LTCF); (c) River specific threshold correction factors were applied to the analysis of the samples in order to consistently detect and measure target DNA concentrations.

Fig 3. Boxplot representation of the differential fluorescence amplitudes between the mean fluorescence of the positive and the negative droplet clouds for different amounts of eDNA samples (0, 0.5 and 1 μl) spiked into positive controls (P. leniusculus genomic DNA).

Pairwise Wilcoxon test P values with Holm correction are indicated on horizontal bars.

Fig 4

Boxplot representation of the standard deviations measured in (a) negative and (b) positive clouds for different amounts of eDNA samples (0, 0.5 and 1 μl) spiked in positive controls (P. leniusculus genomic DNA). Pairwise Wilcoxon test P values with Holm correction are indicated on horizontal bars (NS = non-significant).

Fig 5. Map of the ddPCR results.

(a) Number of successful amplification out of 10 replicates; (b) Mean concentrations per site in cp/μl.