High-Level Multiplexing in Digital PCR with Intercalating Dyes by Coupling Real-Time Kinetics and Melting Curve Analysis

Abstract

Digital polymerase chain reaction (dPCR) is a mature technique that has enabled scientific breakthroughs in several fields. However, this technology is primarily used in research environments with high-level multiplexing representing a major challenge. Here, we propose a novel method for multiplexing, referred to as amplification and melting curve analysis (AMCA), which leverages the kinetic information in real-time amplification data and the thermodynamic melting profile using an affordable intercalating dye (EvaGreen). The method trains a system comprised of supervised machine learning models for accurate classification, by virtue of the large volume of data from dPCR platforms. As a case study, we develop a new 9-plex assay to detect mobilized colistin resistant (mcr ) genes as clinically relevant targets for antimicrobial resistance. Over 100,000 amplification events have been analyzed, and for the positive reactions, the AMCA approach reports a classification accuracy of 99.33 ± 0.13%, an increase of 10.0% over using melting curve analysis. This work provides an affordable method of high-level multiplexing without fluo-rescent probes, extending the benefits of dPCR in research and clinical settings.

Coupling machine learning and high throughput multiplex digital PCR enables accurate detection of carbapenem-resistant genes in clinical isolates

“…As previously reported (1), the AMCA method is capable of enhancing high-level multiplexing capabilities in real-time dPCR platforms, increasing the classification accuracy by utilising kinetic and thermodynamic information of the amplification event. The methodology is extremely advantageous to identify multiple targets in a single reaction in a time and cost-effective manner.…”

“…The proposed method, referred to as AMCA, trains a supervised machine learning model to combine the predictions of ACA and MCA as reported in previous studies from Moniri et al (1,14). In this study, the MCA method consists of applying a logistic regression model to melting T m values extracted from each melting curve.…”

“…The proposed method, AMCA, trains a supervised machine learning model in which the best fit linear line and the optimal value of intercept and coefficient are calculated to minimize error when combining the predictions of amplification curve analysis (ACA) and MCA, as previously reported in Moniri et al (Moniri et al, 2020a, 2020b). In this study, the ACA consists of applying a k-nearest neighbors (KNN) model (with parameter k=10) to the entire real-time curve from each amplification event, whereas the MCA method consists of applying a logistic regression model to T m values extracted from each melting curve (Cunningham and Delany, 2020).…”

“…This paper shows that machine learning (ML) approaches coupled with high throughput real-time digital PCR (dPCR) can be used to increase detection accuracy of multiplex assays. We used a recently reported ML method called Amplification and Melting Curve Analysis (AMCA), which leverages the target-specific information encoded in each amplification event (via real-time data), to identify the nature of nucleic acid molecules (1). Validation of this methodology using clinical isolates has never been reported before.…”

“…Recently, our group has demonstrated that the large volume of data obtained from real-time digital PCR (dPCR) instruments can be exploited to perform data-driven multiplexing in a single fluorescent channel, reporting a 99.28% accuracy of target identification when using synthetic DNA in a 9-plex format (1). The ML method used, called AMCA, leverage kinetic and thermodynamic information encoded in the amplification and melting curves, to perform target identification in multiplexed environments (14,15,16).…”