Classification of SARS-CoV-2 and non-SARS-CoV-2 using machine learning algorithms

Singh, Om Prakash; Vallejo, Marta; El-Badawy, Ismail M.; Aysha, Ali; Madhanagopal, Jagannathan; Faudzi, Ahmad Athif Mohd

doi:10.1016/j.compbiomed.2021.104650

Cited by 24 publications

(18 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Authors in [ 14 ] use a DL model for the classification of SARS-COV-2 viral genome sequence from co-infecting RNA sequences (Coronaviridae, Metapneumovirus, Rhinovirus, Influenza). In [ 15 , 16 ], classical machine learning techniques were used for the classification of SARS-CoV-2 genome sequence.…”

Section: Introductionmentioning

confidence: 99%

Classification of SARS-CoV-2 viral genome sequences using Neurochaos Learning

Harikrishnan

Pranay

Nagaraj

2022

Med Biol Eng Comput

View full text Add to dashboard Cite

The high spread rate of SARS-CoV-2 virus has put the researchers all over the world in a demanding situation. The need of the hour is to develop novel learning algorithms that can effectively learn a general pattern by training with fewer genome sequences of coronavirus. Learning from very few training samples is necessary and important during the beginning of a disease outbreak when sequencing data is limited. This is because a successful detection and isolation of patients can curb the spread of the virus. However, this poses a huge challenge for machine learning and deep learning algorithms as they require huge amounts of training data to learn the pattern and distinguish from other closely related viruses. In this paper, we propose a new paradigm – Neurochaos Learning (NL) for classification of coronavirus genome sequence that addresses this specific problem. NL is inspired from the empirical evidence of chaos and non-linearity at the level of neurons in biological neural networks. The average sensitivity, specificity and accuracy for NL are 0.998, 0.999 and 0.998 respectively for the multiclass classification problem (SARS-CoV-2, Coronaviridae, Metapneumovirus, Rhinovirus and Influenza) using leave one out crossvalidation. With just one training sample per class for 1000 independent random trials of training, we report an average macro F1-score for the classification of SARS-CoV-2 from SARS-CoV-1 genome sequences. We compare the performance of NL with K-nearest neighbours (KNN), logistic regression, random forest, SVM, and naïve Bayes classifiers. We foresee promising future applications in genome classification using NL with novel combinations of chaotic feature engineering and other machine learning algorithms. Graphical abstract Supplementary Information The online version contains supplementary material available at 10.1007/s11517-022-02591-3.

show abstract

Section: Introductionmentioning

confidence: 99%

Classification of SARS-CoV-2 viral genome sequences using Neurochaos Learning

Harikrishnan

Pranay

Nagaraj

2022

Med Biol Eng Comput

View full text Add to dashboard Cite

show abstract

“…Recently, genomic signal processing (GSP) techniques have been used to detect COVID-19 [32][33][34][35] . These techniques transform the genome sequences into genomic signals using various genomic signal mapping approaches.…”

Section: Literature Reviewmentioning

confidence: 99%

“…The SVM with a sigmoid kernel achieved higher performance than the other classifiers, with an accuracy of 99.4%. Singh et al 35 built a GSP system based on the electron-ion interaction pseudopotential mapping technique (EIIP) to detect COVID-19, among other HCoV diseases using partial and whole genome sequences. They extracted several features from the genome signals: singular value decomposition, average and peak-to-signal noise ratio of the magnitude spectrum, average magnitude difference function, and time-domain periodogram.…”

Section: Literature Reviewmentioning

confidence: 99%

A hybrid deep learning approach for COVID-19 detection based on genomic image processing techniques

Hammad

Ghoneim

Mabrouk

et al. 2023

Sci Rep

View full text Add to dashboard Cite

The coronavirus disease 2019 (COVID-19) pandemic has been spreading quickly, threatening the public health system. Consequently, positive COVID-19 cases must be rapidly detected and treated. Automatic detection systems are essential for controlling the COVID-19 pandemic. Molecular techniques and medical imaging scans are among the most effective approaches for detecting COVID-19. Although these approaches are crucial for controlling the COVID-19 pandemic, they have certain limitations. This study proposes an effective hybrid approach based on genomic image processing (GIP) techniques to rapidly detect COVID-19 while avoiding the limitations of traditional detection techniques, using whole and partial genome sequences of human coronavirus (HCoV) diseases. In this work, the GIP techniques convert the genome sequences of HCoVs into genomic grayscale images using a genomic image mapping technique known as the frequency chaos game representation. Then, the pre-trained convolution neural network, AlexNet, is used to extract deep features from these images using the last convolution (conv5) and second fully-connected (fc7) layers. The most significant features were obtained by removing the redundant ones using the ReliefF and least absolute shrinkage and selection operator (LASSO) algorithms. These features are then passed to two classifiers: decision trees and k-nearest neighbors (KNN). Results showed that extracting deep features from the fc7 layer, selecting the most significant features using the LASSO algorithm, and executing the classification process using the KNN classifier is the best hybrid approach. The proposed hybrid deep learning approach detected COVID-19, among other HCoV diseases, with 99.71% accuracy, 99.78% specificity, and 99.62% sensitivity.

show abstract

“…However, as for COVID-19, despite all the achievements, there is still limited research on developing a systematic pattern for the early identification of SARS-CoV-2 because the realistic factor, such as the infectivity and pathogenicity of the virus, could not be solved. Moreover, although the distinguishment between SARS-CoV-2 and non-SARS-CoV-2 was realized with an accuracy of 97.4% using complementary DNA and machine learning algorithms [ 44 ], the significant role of spectroscopy was neglected. Referring to our previous work [ 45 ], the virus-like model based on the nucleocapsid protein of SARS-CoV-2 was synthesized successfully to replace the original virus in some scientific research.…”

Section: Introductionmentioning

confidence: 99%

Identify the Virus-like Models for COVID-19 as Bio-Threats: Combining Phage Display, Spectral Detection and Algorithms Analysis

Wu¹,

Liu²,

Mao

et al. 2023

IJMS

View full text Add to dashboard Cite

The rapid identification and recognition of COVID-19 have been challenging since its outbreak. Multiple methods were developed to realize fast monitoring early to prevent and control the pandemic. In addition, it is difficult and unrealistic to apply the actual virus to study and research because of the highly infectious and pathogenic SARS-CoV-2. In this study, the virus-like models were designed and produced to replace the original virus as bio-threats. Three-dimensional excitation-emission matrix fluorescence and Raman spectroscopy were employed for differentiation and recognition among the produced bio-threats and other viruses, proteins, and bacteria. Combined with PCA and LDA analysis, the identification of the models for SARS-CoV-2 was achieved, reaching a correction of 88.9% and 96.3% after cross-validation, respectively. This idea might provide a possible pattern for detecting and controlling SARS-CoV-2 from the perspective of combining optics and algorithms, which could be applied in the early-warning system against COVID-19 or other bio-threats in the future.

show abstract

Classification of SARS-CoV-2 and non-SARS-CoV-2 using machine learning algorithms

Cited by 24 publications

References 47 publications

Classification of SARS-CoV-2 viral genome sequences using Neurochaos Learning

Classification of SARS-CoV-2 viral genome sequences using Neurochaos Learning

A hybrid deep learning approach for COVID-19 detection based on genomic image processing techniques

Identify the Virus-like Models for COVID-19 as Bio-Threats: Combining Phage Display, Spectral Detection and Algorithms Analysis

Contact Info

Product

Resources

About