Data treatment methods for real-time colorimetric loop-mediated isothermal amplification reactions.

With the SARS-CoV-2 pandemic and the need for affordable and rapid mass testing, colorimetric isothermal amplification reactions such as Loop-Mediated Isothermal Amplification (LAMP) are quickly rising in importance. The technique generates data that is similar to quantitative Polymerase Chain Reaction (qPCR), but instead of an endpoint color visualization, it is possible to construct a signal over a time curve. As the number of works using time-course analysis of isothermal reactions increases, there is a need to analyze data and standardize their related treatments quantitatively. Here, we take a step forward toward this goal by evaluating different available data treatments (curve models) for amplification curves, which allows for a cycle threshold-like parameter extraction. In this study, we uncover evidence of a double sigmoid equation as the most adequate model to describe amplification data from our remote diagnostics system and discuss possibilities for similar setups. We also demonstrate the use of multimodal Gompertz regression models. Thus, this work provides advances toward standardized and unbiased data reporting of Reverse Transcription (RT) LAMP reactions, which may facilitate and quicken assay interpretation, potentially enabling the application of machine learning techniques for further optimization and classification.

A novel dynamic multi-criteria ensemble selection mechanism applied to drinking water quality anomaly detection.

The provision of clean and safe drinking water is a crucial task for water supply companies from all over the world. To this end, automatic anomaly detection plays a critical role in drinking water quality monitoring. Recent anomaly detection studies use techniques that focus on a single global objective. Yet, companies need solutions that better balance the trade-off between false positives (FPs), which lead to financial losses to water companies, and false negatives (FNs), which severely impact public health and damage the environment. This work proposes a novel dynamic multi-criteria ensemble selection mechanism to cope with both problems simultaneously: the non-dominated local class-specific accuracy (NLCA). Moreover, experiments rely on recent time series related classification metrics to assess the predictive performance. Results on data from a real-world water distribution system show that NLCA outperforms other ensemble learning and dynamic ensemble selection techniques by more than 15% in terms of time series related F1 scores. As a conclusion, NLCA enables the development of stronger anomaly detection systems for drinking water quality monitoring. The proposed technique also offers a new perspective on dynamic ensemble selection, which can be applied to different classification tasks to balance conflicting criteria.