Assessment of Multi Fragment Melting Analysis System (MFMAS) for the Identification of Food-Borne Yeasts

Convolutional neural network analysis of recurrence plots for high resolution melting classification

BACKGROUND AND OBJECTIVE

High resolution melting (HRM) analysis is a rapid and correct method for identification of species, such as, microorganism, bacteria, yeast, virus, etc. HRM data are produced using real-time polymerase chain reaction (PCR) and unique for each species. Analysis of the HRM data is important for several applications, such as, for detection of diseases (e.g., influenza, zika virus, SARS-Cov-2 and Covid-19 diseases) in health, for identification of spoiled foods in food industry, for analysis of crime scene evidence in forensic investigation, etc. However, the characteristics of the HRM data can change due to the experimental conditions or instrumental settings. In addition, it becomes laborious and time-consuming process as the number of samples increases. Because of these reasons, the analysis and classification of the HRM data become challenging for species which have similar characteristics.

METHODS

To improve the classification accuracy of HRM data, we propose to use image (visual) representation of HRM data, which we call HRM images, that are generated using recurrence plots, and propose convolutional neural network (CNN) based models for classifying HRM images. In this study, two different types of recurrence plots are generated, which are black-white recurrence plots (BW-RP) and gray scale recurrence plots (GS-RP) and four different CNN models are proposed for classifying HRM data.

RESULTS

The classification performance of the proposed methods are evaluated based on average classification accuracy and F1 score, specificity, recall, and precision values for each yeast species. When BW-RP representation of HRM data is used as input to the CNN models, the best classification accuracy of 95.2% is obtained. The classification accuracies of CNN models for melting curve and GS-RP data representations of HRM data are 90.13% and 86.13%, respectively. The classification accuracy of support vector machines (SVM) model that take melting curve representation of HRM data is 86.53%. Moreover, when BW-RP representation of HRM data is used as input to the CNN models, the F1 score, specificity, recall and precision values are the highest for almost all of species.

CONCLUSIONS

Experimental results show that using BW-RP representation of HRM data improved the classification accuracy of HRM data and CNN models that take these images as input outperformed CNN models that take melting curve and GS-RP representations of HRM data as inputs and SVM model that take melting curve representation of HRM data as input.

Update of the list of QPS-recommended biological agents intentionally added to food or feed as notified to EFSA 10: Suitability of taxonomic units notified to EFSA until March 2019

The qualified presumption of safety (QPS) procedure was developed to provide a harmonised generic pre-evaluation to support safety risk assessments of biological agents performed by EFSA's Scientific Panels. The taxonomic identity, body of knowledge, safety concerns and antimicrobial resistance were assessed. Safety concerns identified for a taxonomic unit (TU) are, where possible and reasonable in number, reflected by 'qualifications' which should be assessed at the strain level by the EFSA's Scientific Panels. During the current assessment, no new information was found that would change the previously recommended QPS TUs and their qualifications. The list of microorganisms notified to EFSA from applications for market authorisation was updated with 47 biological agents, received between October 2018 and March 2019. Of these, 19 already had QPS status, 20 were excluded from the QPS exercise by the previous QPS mandate (11 filamentous fungi) or from further evaluations within the current mandate (9 notifications of Escherichia coli). Sphingomonas elodea, Gluconobacter frateurii, Corynebacterium ammoniagenes, Corynebacterium casei, Burkholderia ubonensis, Phaeodactylum tricornutum, Microbacterium foliorum and Euglena gracilis were evaluated for the first time. Sphingomonas elodea cannot be assessed for a possible QPS recommendation because it is not a valid species. Corynebacterium ammoniagenes and Euglena gracilis can be recommended for the QPS list with the qualification 'for production purposes only'. The following TUs cannot be recommended for the QPS list: Burkholderia ubonensis, due to its potential and confirmed ability to generate biologically active compounds and limited of body of knowledge; Corynebacterium casei, Gluconobacter frateurii and Microbacterium foliorum, due to lack of body of knowledge; Phaeodactylum tricornutum, based on the lack of a safe history of use in the food chain and limited knowledge on its potential production of bioactive compounds with possible toxic effects.