Amplification Curve Analysis: Data-Driven Multiplexing Using Real-Time Digital PCR

Background: The emergence and spread of carbapenemase-producing organisms (CPO) are a significant clinical and public health concern. Rapid and accurate identification of patients colonised with CPO is essential to adopt prompt prevention measures in order to reduce the risk of transmission. Recent proof-of-concept studies have demonstrated the ability to combine machine learning (ML) algorithms with real-time digital PCR (dPCR) instruments to increase classification accuracy of multiplex assays. From this, we sought to determine if this ML based methodology could accurately identify five major carbapenem-resistant genes in clinical CPO-isolates. Methods: We collected 253 clinical isolates (including 221 CPO-positive samples) and developed a novel 5-plex assay for detection of blaVIM, blaOXA-48, blaNDM, blaIMP and blaKPC. Combining the recently reported ML method "Amplification and Melting Curve Analysis" (AMCA) with the abovementioned multiplex assay, we assessed the performance of the methodology in detecting these five carbapenem-resistant genes. The classification accuracy relies on the usage of real-time data from a single fluorescent channel and benefits from the kinetic and thermodynamic information encoded in the thousands of amplification events produced by high throughput dPCR. Results: The 5-plex showed a lower limit of detection of 100 DNA copies per reaction for each primer set and no cross-reactivity with other carbapenemase genes. The AMCA classifier demonstrated excellent predictive performance with 99.6% (CI 97.8-99.9%) accuracy (only one misclassified sample out of the 253, with a total of 163,966 positive amplification events), which represents a 7.9% increase compared to the conventional ML-based melting curve analysis (MCA) method. Conclusion: This work demonstrates the utility of the AMCA method to increase the throughput and performance of state-of-the-art molecular diagnostic platforms, reducing costs without any changes to instrument hardware. Our findings suggest that, pending additional validation directly from clinical samples, advanced data-driven multiplex dPCR could potentially be integrated in routine clinical diagnostic workflows.

Download Full-text

Coupling Machine Learning and High Throughput Multiplex Digital PCR Enables Accurate Detection of Carbapenem-Resistant Genes in Clinical Isolates

Frontiers in Molecular Biosciences ◽

10.3389/fmolb.2021.775299 ◽

2021 ◽

Vol 8 ◽

Author(s):

Luca Miglietta ◽

Ahmad Moniri ◽

Ivana Pennisi ◽

Kenny Malpartida-Cardenas ◽

Hala Abbas ◽

...

Keyword(s):

Machine Learning ◽

Real Time ◽

High Throughput ◽

Classification Accuracy ◽

Melting Curve ◽

Digital Pcr ◽

Curve Analysis ◽

Melting Curve Analysis ◽

Carbapenem Resistant ◽

Resistant Genes

Rapid and accurate identification of patients colonised with carbapenemase-producing organisms (CPOs) is essential to adopt prompt prevention measures to reduce the risk of transmission. Recent studies have demonstrated the ability to combine machine learning (ML) algorithms with real-time digital PCR (dPCR) instruments to increase classification accuracy of multiplex PCR assays when using synthetic DNA templates. We sought to determine if this novel methodology could be applied to improve identification of the five major carbapenem-resistant genes in clinical CPO-isolates, which would represent a leap forward in the use of PCR-based data-driven diagnostics for clinical applications. We collected 253 clinical isolates (including 221 CPO-positive samples) and developed a novel 5-plex PCR assay for detection of blaIMP, blaKPC, blaNDM, blaOXA-48, and blaVIM. Combining the recently reported ML method “Amplification and Melting Curve Analysis” (AMCA) with the abovementioned multiplex assay, we assessed the performance of the AMCA methodology in detecting these genes. The improved classification accuracy of AMCA relies on the usage of real-time data from a single-fluorescent channel and benefits from the kinetic/thermodynamic information encoded in the thousands of amplification events produced by high throughput real-time dPCR. The 5-plex showed a lower limit of detection of 10 DNA copies per reaction for each primer set and no cross-reactivity with other carbapenemase genes. The AMCA classifier demonstrated excellent predictive performance with 99.6% (CI 97.8–99.9%) accuracy (only one misclassified sample out of the 253, with a total of 160,041 positive amplification events), which represents a 7.9% increase (p-value <0.05) compared to conventional melting curve analysis. This work demonstrates the use of the AMCA method to increase the throughput and performance of state-of-the-art molecular diagnostic platforms, without hardware modifications and additional costs, thus potentially providing substantial clinical utility on screening patients for CPO carriage.

Download Full-text

Cognitive Automation, Big Data-driven Manufacturing, and Sustainable Industrial Value Creation in Internet of Things-based Real-Time Production Logistics

Economics Management and Financial Markets ◽

10.22381/emfm15420204 ◽

2020 ◽

Vol 15 (4) ◽

pp. 39

Keyword(s):

Big Data ◽

Internet Of Things ◽

Real Time ◽

Value Creation ◽

Data Driven ◽

Production Logistics ◽

Time Production ◽

Cognitive Automation

Download Full-text

Development and validation of a method for quantification of common wheat, durum wheat, rye and barley by droplet digital PCR

European Food Research and Technology ◽

10.1007/s00217-021-03786-y ◽

2021 ◽

Author(s):

Christian Schulze ◽

Anne-Catrin Geuthner ◽

Dietrich Mäde

Keyword(s):

Durum Wheat ◽

Real Time ◽

Bread Wheat ◽

Common Wheat ◽

Real Time Pcr ◽

Digital Pcr ◽

Droplet Digital Pcr ◽

Food Fraud ◽

Single Genome ◽

Cereal Species

AbstractFood fraud is becoming a prominent topic in the food industry. Thus, valid methods for detecting potential adulterations are necessary to identify instances of food fraud in cereal products, a significant component of human diet. In this work, primer–probe systems for real-time PCR and droplet digital PCR (ddPCR) for the detection of these cereal species: bread wheat (together with spelt), durum wheat, rye and barley for real-time PCR and ddPCR were established, optimized and validated. In addition, it was projected to validate a molecular system for differentiation of bread wheat and spelt; however, attempts for molecular differentiation between common wheat and spelt based on the gene GAG56D failed because of the genetic variability of the molecular target. Primer–probe systems were further developed and optimized on the basis of alignments of DNA sequences, as well as already developed PCR systems. The specificity of each system was demonstrated on 10 (spelt), 11 (durum wheat and rye) and 12 (bread wheat) reference samples. Specificity of the barley system was already proved in previous work. The calculated limits of detection (LOD95%) were between 2.43 and 4.07 single genome copies in real-time PCR. Based on the “three droplet rule”, the LOD95% in ddPCR was calculated to be 9.07–13.26 single genome copies. The systems were tested in mixtures of flours (rye and common wheat) and of semolina (durum and common wheat). The methods proved to be robust with regard to the tested conditions in the ddPCR. The developed primer–probe systems for ddPCR proved to be effective in quantitatively detecting the investigated cereal species rye and common wheat in mixtures by taking into account the haploid genome weight and the degree of milling of a flour. This method can correctly detect proportions of 50%, 60% and 90% wholemeal rye flour in a mixture of wholemeal common wheat flour. Quantitative results depend on the DNA content, on ploidy of cereal species and are also influenced by comminution. Hence, the proportion of less processed rye is overestimated in higher processed bread wheat and adulteration of durum wheat by common wheat by 1–5% resulted in underestimation of common wheat.

Download Full-text

Data-Driven Dispatching Rules Mining and Real-Time Decision-Making Methodology in Intelligent Manufacturing Shop Floor with Uncertainty

Sensors ◽

10.3390/s21144836 ◽

2021 ◽

Vol 21 (14) ◽

pp. 4836

Author(s):

Liping Zhang ◽

Yifan Hu ◽

Qiuhua Tang ◽

Jie Li ◽

Zhixiong Li

Keyword(s):

Decision Making ◽

Data Base ◽

Real Time ◽

Manufacturing Industry ◽

Job Shop ◽

Data Driven ◽

Dispatching Rules ◽

Shop Floor ◽

Production Data ◽

Online Decision Making

In modern manufacturing industry, the methods supporting real-time decision-making are the urgent requirement to response the uncertainty and complexity in intelligent production process. In this paper, a novel closed-loop scheduling framework is proposed to achieve real-time decision making by calling the appropriate data-driven dispatching rules at each rescheduling point. This framework contains four parts: offline training, online decision-making, data base and rules base. In the offline training part, the potential and appropriate dispatching rules with managers’ expectations are explored successfully by an improved gene expression program (IGEP) from the historical production data, not just the available or predictable information of the shop floor. In the online decision-making part, the intelligent shop floor will implement the scheduling scheme which is scheduled by the appropriate dispatching rules from rules base and store the production data into the data base. This approach is evaluated in a scenario of the intelligent job shop with random jobs arrival. Numerical experiments demonstrate that the proposed method outperformed the existing well-known single and combination dispatching rules or the discovered dispatching rules via metaheuristic algorithm in term of makespan, total flow time and tardiness.

Download Full-text