Convolutional neural network analysis of recurrence plots for high resolution melting classification. (August 2021)

• Record Type: Journal Article
• Authors: Ozkok, Fatma Ozge; Celik, Mete
• Is Part Of: Computer methods and programs in biomedicine. Volume 207(2021)
• Publication Date: 2021-08
• Subjects: Convolutional neural network -- Recurrence plot -- Deep learning -- High resolution melting -- HRM analysis -- Classification; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2021.106139
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: High resolution melting (HRM) data analysis methods use melting temperature (Tm) and melting curve representation of HRM data. This study proposes to use recurrence plots to generate image representation of HRM data. Convolutional neural network (CNN) based models that have different number of feature extraction layers are proposed to classify generated HRM images. The performances of CNN models for classifying HRM images are compared with that of CNN and support vector machines (SVM) model for classifying melting curve representation of HRM data. Results show that using black-white recurrence plot (BW-RP) representation of HRM data improves the classification accuracy. Graphical abstract: Abstract: 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.