Classification and specific primer design for accurate detection of SARS-CoV-2 using deep learning

SPM4GAC: SPM based approach for genome analysis and classification of macromolecules

Genome sequence analysis and classification play critical roles in properly understanding an organism's main characteristics, functionalities, and changing (evolving) nature. However, the rapid expansion of genomic data makes genome sequence analysis and classification a challenging task due to the high computational requirements, proper management, and understanding of genomic data. Recently proposed models yielded promising results for the task of genome sequence classification. Nevertheless, these models often ignore the sequential nature of nucleotides, which is crucial for revealing their underlying structure and function. To address this limitation, we present SPM4GAC, a sequential pattern mining (SPM)-based framework to analyze and classify the macromolecule genome sequences of viruses. First, a large dataset containing the genome sequences of various RNA viruses is developed and transformed into a suitable format. On the transformed dataset, algorithms for SPM are used to identify frequent sequential patterns of nucleotide bases. The obtained frequent sequential patterns of bases are then used as features to classify different viruses. Ten classifiers are employed, and their performance is assessed by using several evaluation measures. Finally, a performance comparison of SPM4GAC with state-of-the-art methods for genome sequence classification/detection reveals that SPM4GAC performs better than those methods.

Leveraging Artificial Intelligence to Expedite Antibody Design and Enhance Antibody-Antigen Interactions

This perspective sheds light on the transformative impact of recent computational advancements in the field of protein therapeutics, with a particular focus on the design and development of antibodies. Cutting-edge computational methods have revolutionized our understanding of protein-protein interactions (PPIs), enhancing the efficacy of protein therapeutics in preclinical and clinical settings. Central to these advancements is the application of machine learning and deep learning, which offers unprecedented insights into the intricate mechanisms of PPIs and facilitates precise control over protein functions. Despite these advancements, the complex structural nuances of antibodies pose ongoing challenges in their design and optimization. Our review provides a comprehensive exploration of the latest deep learning approaches, including language models and diffusion techniques, and their role in surmounting these challenges. We also present a critical analysis of these methods, offering insights to drive further progress in this rapidly evolving field. The paper includes practical recommendations for the application of these computational techniques, supplemented with independent benchmark studies. These studies focus on key performance metrics such as accuracy and the ease of program execution, providing a valuable resource for researchers engaged in antibody design and development. Through this detailed perspective, we aim to contribute to the advancement of antibody design, equipping researchers with the tools and knowledge to navigate the complexities of this field.

Machine learning-based approach KEVOLVE efficiently identifies SARS-CoV-2 variant-specific genomic signatures

Machine learning was shown to be effective at identifying distinctive genomic signatures among viral sequences. These signatures are defined as pervasive motifs in the viral genome that allow discrimination between species or variants. In the context of SARS-CoV-2, the identification of these signatures can assist in taxonomic and phylogenetic studies, improve in the recognition and definition of emerging variants, and aid in the characterization of functional properties of polymorphic gene products. In this paper, we assess KEVOLVE, an approach based on a genetic algorithm with a machine-learning kernel, to identify multiple genomic signatures based on minimal sets of k-mers. In a comparative study, in which we analyzed large SARS-CoV-2 genome dataset, KEVOLVE was more effective at identifying variant-discriminative signatures than several gold-standard statistical tools. Subsequently, these signatures were characterized using a new extension of KEVOLVE (KANALYZER) to highlight variations of the discriminative signatures among different classes of variants, their genomic location, and the mutations involved. The majority of identified signatures were associated with known mutations among the different variants, in terms of functional and pathological impact based on available literature. Here we showed that KEVOLVE is a robust machine learning approach to identify discriminative signatures among SARS-CoV-2 variants, which are frequently also biologically relevant, while bypassing multiple sequence alignments. The source code of the method and additional resources are available at: https://github.com/bioinfoUQAM/KEVOLVE.

An Innovative AI-based primer design tool for precise and accurate detection of SARS-CoV-2 variants of concern

As the COVID-19 pandemic winds down, it leaves behind the serious concern that future, even more disruptive pandemics may eventually surface. One of the crucial steps in handling the SARS-CoV-2 pandemic was being able to detect the presence of the virus in an accurate and timely manner, to then develop policies counteracting the spread. Nevertheless, as the pandemic evolved, new variants with potentially dangerous mutations appeared. Faced by these developments, it becomes clear that there is a need for fast and reliable techniques to create highly specific molecular tests, able to uniquely identify VOCs. Using an automated pipeline built around evolutionary algorithms, we designed primer sets for SARS-CoV-2 (main lineage) and for VOC, B.1.1.7 (Alpha) and B.1.1.529 (Omicron). Starting from sequences openly available in the GISAID repository, our pipeline was able to deliver the primer sets for the main lineage and each variant in a matter of hours. Preliminary in-silico validation showed that the sequences in the primer sets featured high accuracy. A pilot test in a laboratory setting confirmed the results: the developed primers were favorably compared against existing commercial versions for the main lineage, and the specific versions for the VOCs B.1.1.7 and B.1.1.529 were clinically tested successfully.

Reimagining Healthcare: Unleashing the Power of Artificial Intelligence in Medicine

Artificial intelligence (AI) has opened new medical avenues and revolutionized diagnostic and therapeutic practices, allowing healthcare providers to overcome significant challenges associated with cost, disease management, accessibility, and treatment optimization. Prominent AI technologies such as machine learning (ML) and deep learning (DL) have immensely influenced diagnostics, patient monitoring, novel pharmaceutical discoveries, drug development, and telemedicine. Significant innovations and improvements in disease identification and early intervention have been made using AI-generated algorithms for clinical decision support systems and disease prediction models. AI has remarkably impacted clinical drug trials by amplifying research into drug efficacy, adverse events, and candidate molecular design. AI's precision and analysis regarding patients' genetic, environmental, and lifestyle factors have led to individualized treatment strategies. During the COVID-19 pandemic, AI-assisted telemedicine set a precedent for remote healthcare delivery and patient follow-up. Moreover, AI-generated applications and wearable devices have allowed ambulatory monitoring of vital signs. However, apart from being immensely transformative, AI's contribution to healthcare is subject to ethical and regulatory concerns. AI-backed data protection and algorithm transparency should be strictly adherent to ethical principles. Vigorous governance frameworks should be in place before incorporating AI in mental health interventions through AI-operated chatbots, medical education enhancements, and virtual reality-based training. The role of AI in medical decision-making has certain limitations, necessitating the importance of hands-on experience. Therefore, reaching an optimal balance between AI's capabilities and ethical considerations to ensure impartial and neutral performance in healthcare applications is crucial. This narrative review focuses on AI's impact on healthcare and the importance of ethical and balanced incorporation to make use of its full potential.

Automatic diagnosis of COVID-19 from CT images using CycleGAN and transfer learning

The outbreak of the corona virus disease (COVID-19) has changed the lives of most people on Earth. Given the high prevalence of this disease, its correct diagnosis in order to quarantine patients is of the utmost importance in the steps of fighting this pandemic. Among the various modalities used for diagnosis, medical imaging, especially computed tomography (CT) imaging, has been the focus of many previous studies due to its accuracy and availability. In addition, automation of diagnostic methods can be of great help to physicians. In this paper, a method based on pre-trained deep neural networks is presented, which, by taking advantage of a cyclic generative adversarial net (CycleGAN) model for data augmentation, has reached state-of-the-art performance for the task at hand, i.e., 99.60% accuracy. Also, in order to evaluate the method, a dataset containing 3163 images from 189 patients has been collected and labeled by physicians. Unlike prior datasets, normal data have been collected from people suspected of having COVID-19 disease and not from data from other diseases, and this database is made available publicly. Moreover, the method's reliability is further evaluated by calibration metrics, and its decision is interpreted by Grad-CAM also to find suspicious regions as another output of the method and make its decisions trustworthy and explainable.

Exploring the Intersection of Artificial Intelligence and Clinical Healthcare: A Multidisciplinary Review

Artificial intelligence (AI) plays a more and more important role in our everyday life due to the advantages that it brings when used, such as 24/7 availability, a very low percentage of errors, ability to provide real time insights, or performing a fast analysis. AI is increasingly being used in clinical medical and dental healthcare analyses, with valuable applications, which include disease diagnosis, risk assessment, treatment planning, and drug discovery. This paper presents a narrative literature review of AI use in healthcare from a multi-disciplinary perspective, specifically in the cardiology, allergology, endocrinology, and dental fields. The paper highlights data from recent research and development efforts in AI for healthcare, as well as challenges and limitations associated with AI implementation, such as data privacy and security considerations, along with ethical and legal concerns. The regulation of responsible design, development, and use of AI in healthcare is still in early stages due to the rapid evolution of the field. However, it is our duty to carefully consider the ethical implications of implementing AI and to respond appropriately. With the potential to reshape healthcare delivery and enhance patient outcomes, AI systems continue to reveal their capabilities.

PSAC-PDB: Analysis and classification of protein structures

This paper presents a novel framework, called PSAC-PDB, for analyzing and classifying protein structures from the Protein Data Bank (PDB). PSAC-PDB first finds, analyze and identifies protein structures in PDB that are similar to a protein structure of interest using a protein structure comparison tool. Second, the amino acids (AA) sequences of identified protein structures (obtained from PDB), their aligned amino acids (AAA) and aligned secondary structure elements (ASSE) (obtained by structural alignment), and frequent AA (FAA) patterns (discovered by sequential pattern mining), are used for the reliable detection/classification of protein structures. Eleven classifiers are used and their performance is compared using six evaluation metrics. Results show that three classifiers perform well on overall, and that FAA patterns can be used to efficiently classify protein structures in place of providing the whole AA sequences, AAA or ASSE. Furthermore, better classification results are obtained using AAA of protein structures rather than AA sequences. PSAC-PDB also performed better than state-of-the-art approaches for SARS-CoV-2 genome sequences classification.

New proposal of viral genome representation applied in the classification of SARS-CoV-2 with deep learning

BACKGROUND

In December 2019, the first case of COVID-19 was described in Wuhan, China, and by July 2022, there were already 540 million confirmed cases. Due to the rapid spread of the virus, the scientific community has made efforts to develop techniques for the viral classification of SARS-CoV-2.

RESULTS

In this context, we developed a new proposal for gene sequence representation with Genomic Signal Processing techniques for the work presented in this paper. First, we applied the mapping approach to samples of six viral species of the Coronaviridae family, which belongs SARS-CoV-2 Virus. We then used the sequence downsized obtained by the method proposed in a deep learning architecture for viral classification, achieving an accuracy of 98.35%, 99.08%, and 99.69% for the 64, 128, and 256 sizes of the viral signatures, respectively, and obtaining 99.95% precision for the vectors with size 256.

CONCLUSIONS

The classification results obtained, in comparison to the results produced using other state-of-the-art representation techniques, demonstrate that the proposed mapping can provide a satisfactory performance result with low computational memory and processing time costs.

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

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.

Identification and classification of coronavirus genomic signals based on linear predictive coding and machine learning methods

Corona disease has become one of the problems and challenges of humankind over the past two years. One of the problems that existed from the first days of this epidemic was clinical symptoms similar to other infectious viruses such as colds and influenza. Therefore, diagnosis of this disease and its coping and treatment approaches is also been difficult. In this study, Attempts has been made to investigate the origin of this disease and the genetic structure of the virus leading to it. For this purpose, signal processing and linear predictive coding approaches were used which are widely used in data compression. A pattern recognition model was presented for the detection and separation of covid samples from the influenza virus case studies. This model, which was based on support vector machine classifier, was tested successfully on several datasets collected from different countries. The obtained results performed on all datasets by more than 98% accuracy. The proposed model, in addition to its good performance accuracy, can be a step forward in quantifying and digitizing medical big data information.

Multi-Stage Temporal Convolution Network for COVID-19 Variant Classification

The outbreak of the novel coronavirus disease COVID-19 (SARS-CoV-2) has developed into a global epidemic. Due to the pathogenic virus’s high transmission rate, accurate identification and early prediction are required for subsequent therapy. Moreover, the virus’s polymorphic nature allows it to evolve and adapt to various environments, making prediction difficult. However, other diseases, such as dengue, MERS-CoV, Ebola, SARS-CoV-1, and influenza, necessitate the employment of a predictor based on their genomic information. To alleviate the situation, we propose a deep learning-based mechanism for the classification of various SARS-CoV-2 virus variants, including the most recent, Omicron. Our model uses a neural network with a temporal convolution neural network to accurately identify different variants of COVID-19. The proposed model first encodes the sequences in the numerical descriptor, and then the convolution operation is applied for discriminative feature extraction from the encoded sequences. The sequential relations between the features are collected using a temporal convolution network to classify COVID-19 variants accurately. We collected recent data from the NCBI, on which the proposed method outperforms various baselines with a high margin.

Genomic Analysis of SARS-CoV-2 Alpha, Beta and Delta Variants of Concern Uncovers Signatures of Neutral and Non-Neutral Evolution

Due to the emergence of new variants of the SARS-CoV-2 coronavirus, the question of how the viral genomes evolved, leading to the formation of highly infectious strains, becomes particularly important. Three major emergent strains, Alpha, Beta and Delta, characterized by a significant number of missense mutations, provide a natural test field. We accumulated and aligned 4.7 million SARS-CoV-2 genomes from the GISAID database and carried out a comprehensive set of analyses. This collection covers the period until the end of October 2021, i.e., the beginnings of the Omicron variant. First, we explored combinatorial complexity of the genomic variants emerging and their timing, indicating very strong, albeit hidden, selection forces. Our analyses show that the mutations that define variants of concern did not arise gradually but rather co-evolved rapidly, leading to the emergence of the full variant strain. To explore in more detail the evolutionary forces at work, we developed time trajectories of mutations at all 29,903 sites of the SARS-CoV-2 genome, week by week, and stratified them into trends related to (i) point substitutions, (ii) deletions and (iii) non-sequenceable regions. We focused on classifying the genetic forces active at different ranges of the mutational spectrum. We observed the agreement of the lowest-frequency mutation spectrum with the Griffiths-Tavaré theory, under the Infinite Sites Model and neutrality. If we widen the frequency range, we observe the site frequency spectra much more consistently with the Tung-Durrett model assuming clone competition and selection. The coefficients of the fitting model indicate the possibility of selection acting to promote gradual growth slowdown, as observed in the history of the variants of concern. These results add up to a model of genomic evolution, which partly fits into the classical drift barrier ideas. Certain observations, such as mutation "bands" persistent over the epidemic history, suggest contribution of genetic forces different from mutation, drift and selection, including recombination or other genome transformations. In addition, we show that a "toy" mathematical model can qualitatively reproduce how new variants (clones) stem from rare advantageous driver mutations, and then acquire neutral or disadvantageous passenger mutations which gradually reduce their fitness so they can be then outcompeted by new variants due to other driver mutations.

Omics Data and Data Representations for Deep Learning-Based Predictive Modeling

Medical discoveries mainly depend on the capability to process and analyze biological datasets, which inundate the scientific community and are still expanding as the cost of next-generation sequencing technologies is decreasing. Deep learning (DL) is a viable method to exploit this massive data stream since it has advanced quickly with there being successive innovations. However, an obstacle to scientific progress emerges: the difficulty of applying DL to biology, and this because both fields are evolving at a breakneck pace, thus making it hard for an individual to occupy the front lines of both of them. This paper aims to bridge the gap and help computer scientists bring their valuable expertise into the life sciences. This work provides an overview of the most common types of biological data and data representations that are used to train DL models, with additional information on the models themselves and the various tasks that are being tackled. This is the essential information a DL expert with no background in biology needs in order to participate in DL-based research projects in biomedicine, biotechnology, and drug discovery. Alternatively, this study could be also useful to researchers in biology to understand and utilize the power of DL to gain better insights into and extract important information from the omics data.

Detection of SARS-CoV-2 Using Reverse Transcription Helicase Dependent Amplification and Reverse Transcription Loop-Mediated Amplification Combined with Lateral Flow Assay

Rapid and accurate detection and identification of pathogens in clinical samples is essential for all infection diseases. However, in the case of epidemics, it plays a key role not only in the implementation of effective therapy but also in limiting the spread of the epidemic. In this study, we present the application of two nucleic acid isothermal amplification methods—reverse transcription helicase dependent amplification (RT-HDA) and reverse transcription loop-mediated amplification (RT-LAMP)—combined with lateral flow assay as the tools for the rapid detection of SARS-CoV-2, the etiological agent of COVID-19, which caused the ongoing global pandemic. In order to optimize the RT-had, the LOD was 3 genome copies per reaction for amplification conducted for 10–20 min, whereas for RT-LAMP, the LOD was 30–300 genome copies per reaction for a reaction conducted for 40 min. No false-positive results were detected for RT-HDA conducted for 10 to 90 min, but false-positive results occurred when RT-LAMP was conducted for longer than 40 min. We concluded that RT-HDA combined with LFA is more sensitive than RT-LAMP, and it is a good alternative for the development of point-of-care tests for SARS-CoV-2 detection as this method is simple, inexpensive, practical, and does not require qualified personnel to perform the test and interpret its results.

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

Abstract

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 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$> 0.99$$\end{document}>0.99 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.

Artificial Intelligence-Based Data-Driven Strategy to Accelerate Research, Development, and Clinical Trials of COVID Vaccine

The global COVID-19 (coronavirus disease 2019) pandemic, which was caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), has resulted in a significant loss of human life around the world. The SARS-CoV-2 has caused significant problems to medical systems and healthcare facilities due to its unexpected global expansion. Despite all of the efforts, developing effective treatments, diagnostic techniques, and vaccinations for this unique virus is a top priority and takes a long time. However, the foremost step in vaccine development is to identify possible antigens for a vaccine. The traditional method was time taking, but after the breakthrough technology of reverse vaccinology (RV) was introduced in 2000, it drastically lowers the time needed to detect antigens ranging from 5-15 years to 1-2 years. The different RV tools work based on machine learning (ML) and artificial intelligence (AI). Models based on AI and ML have shown promising solutions in accelerating the discovery and optimization of new antivirals or effective vaccine candidates. In the present scenario, AI has been extensively used for drug and vaccine research against SARS-COV-2 therapy discovery. This is more useful for the identification of potential existing drugs with inhibitory human coronavirus by using different datasets. The AI tools and computational approaches have led to speedy research and the development of a vaccine to fight against the coronavirus. Therefore, this paper suggests the role of artificial intelligence in the field of clinical trials of vaccines and clinical practices using different tools.

Identification of conserved regions from 230,163 SARS-CoV-2 genomes and their use in diagnostic PCR primer design

BACKGROUND

As the rapidly evolving characteristic of SARS-CoV-2 could result in false negative diagnosis, the use of as much sequence data as possible is key to the identification of conserved viral sequences. However, multiple alignment of massive genome sequences is computationally intensive.

OBJECTIVE

To extract conserved sequences from SARS-CoV-2 genomes for the design of diagnostic PCR primers using a bioinformatics approach that can handle massive genomic sequences efficiently.

METHODS

A total of 230,163 full-length viral genomes were retrieved from the NCBI SARS-CoV-2 Resources and GISAID EpiCoV database. This number was reduced to 14.11% following removal of 5'-/3'-untranslated regions and sequence dereplication. Fast, reference-based, multiple sequence alignments identified conserved sequences and specific primer sets were designed against these regions using a conventional tool. Primer sets chosen among the candidates were evaluated by in silico PCR and RT-qPCR.

RESULTS

Out of 17 conserved sequences (totaling 4.3 kb), two primer sets targeting the nsp2 and ORF3a genes were picked that exhibited > 99.9% in silico amplification coverage against the original dataset (230,163 genomes) when a 5% mismatch between the primers and target was allowed. In addition, the primer sets successfully detected nine SARS-CoV-2 variant RNA samples (Alpha, Beta, Gamma, Delta, Epsilon, Zeta, Eta, Iota, and Kappa) in experimental RT-qPCR validations.

CONCLUSION

In addition to the RdRp, E, N, and S genes that are targeted commonly, our approach can be used to identify novel primer targets in SARS-CoV-2 and should be a priority strategy in the event of novel SARS-CoV-2 variants or other pandemic outbreaks.

Enabling Artificial Intelligence for Genome Sequence Analysis of COVID-19 and Alike Viruses

Recent pandemic of COVID-19 (Coronavirus) caused by severe acute respiratory syndrome Coronavirus 2 (SARS-CoV-2) has been growing lethally with unusual speed. It has infected millions of people and continues a mortifying influence on the global population's health and well-being. In this situation, genome sequence analysis and advanced artificial intelligence techniques may help researchers and medical experts to understand the genetic variants of COVID-19 or SARS-CoV-2. Genome sequence analysis of COVID-19 is crucial to understand the virus's origin, behavior, and structure, which might help produce/develop vaccines, antiviral drugs, and efficient preventive strategies. This paper introduces an artificial intelligence based system to perform genome sequence analysis of COVID-19 and alike viruses, e.g., SARS, middle east respiratory syndrome, and Ebola. The system helps to get important information from the genome sequences of different viruses. We perform comparative data analysis by extracting basic information of COVID-19 and other genome sequences, including information of nucleotides composition and their frequency, tri-nucleotide compositions, count of amino acids, alignment between genome sequences, and their DNA similarity information. We use different visualization methods to analyze these viruses' genome sequences and, finally, apply machine learning based classifier support vector machine to classify different genome sequences. The data set of different virus genome sequences are obtained from an online publicly accessible data center repository. The system achieves good classification results with an accuracy of 97% for COVID-19, 96%, SARS, and 95% for MERS and Ebola genome sequences, respectively.

End-point RT-PCR based on a conservation landscape for SARS-COV-2 detection

End-point RT-PCR is a suitable alternative diagnostic technique since it is cheaper than RT-qPCR tests and can be implemented on a massive scale in low- and middle-income countries. In this work, a bioinformatic approach to guide the design of PCR primers was developed, and an alternative diagnostic test based on end-point PCR was designed. End-point PCR primers were designed through conservation analysis based on kmer frequency in SARS-CoV-2 and human respiratory pathogen genomes. Highly conserved regions were identified for primer design, and the resulting PCR primers were used to amplify 871 nasopharyngeal human samples with a previous RT-qPCR based SARS-CoV-2 diagnosis. The diagnostic test showed high accuracy in identifying SARS-CoV-2-positive samples including B.1.1.7, P.1, B.1.427/B.1.429 and B.1.617.2/ AY samples with a detection limit of 7.2 viral copies/µL. In addition, this test could discern SARS-CoV-2 infection from other viral infections with COVID-19-like symptomatology. The designed end-point PCR diagnostic test to detect SARS-CoV-2 is a suitable alternative to RT-qPCR. Since the proposed bioinformatic approach can be easily applied in thousands of viral genomes and over highly divergent strains, it can be used as a PCR design tool as new SARS-CoV-2 variants emerge. Therefore, this end-point PCR test could be employed in epidemiological surveillance to detect new SARS-CoV-2 variants as they emerge and propagate.

COVID-19: A systematic review and update on prevention, diagnosis, and treatment

Since the rapid onset of the COVID-19 or SARS-CoV-2 pandemic in the world in 2019, extensive studies have been conducted to unveil the behavior and emission pattern of the virus in order to determine the best ways to diagnosis of virus and thereof formulate effective drugs or vaccines to combat the disease. The emergence of novel diagnostic and therapeutic techniques considering the multiplicity of reports from one side and contradictions in assessments from the other side necessitates instantaneous updates on the progress of clinical investigations. There is also growing public anxiety from time to time mutation of COVID-19, as reflected in considerable mortality and transmission, respectively, from delta and Omicron variants. We comprehensively review and summarize different aspects of prevention, diagnosis, and treatment of COVID-19. First, biological characteristics of COVID-19 were explained from diagnosis standpoint. Thereafter, the preclinical animal models of COVID-19 were discussed to frame the symptoms and clinical effects of COVID-19 from patient to patient with treatment strategies and in-silico/computational biology. Finally, the opportunities and challenges of nanoscience/nanotechnology in identification, diagnosis, and treatment of COVID-19 were discussed. This review covers almost all SARS-CoV-2-related topics extensively to deepen the understanding of the latest achievements (last updated on January 11, 2022).

Covid-19 and Artificial Intelligence: Genome sequencing, drug development and vaccine discovery

OBJECTIVES

To clarify the work done by using AI for identifying the genomic sequences, development of drugs and vaccines for COVID-19 and to recognize the advantages and challenges of using such technology.

METHODS

A non-systematic review was done. All articles published on Pub-Med, Medline, Google, and Google Scholar on AI or digital health regarding genomic sequencing, drug development, and vaccines of COVID-19 were scrutinized and summarized.

RESULTS

The sequence of SARS- CoV-2 was identified with the help of AI. It can help also in the prompt identification of variants of concern (VOC) as delta strains and Omicron. Furthermore, there are many drugs applied with the help of AI. These drugs included Atazanavir, Remdesivir, Efavirenz, Ritonavir, and Dolutegravir, PARP1 inhibitors (Olaparib and CVL218 which is Mefuparib hydrochloride), Abacavir, Roflumilast, Almitrine, and Mesylate. Many vaccines were developed utilizing the new technology of bioinformatics, databases, immune-informatics, machine learning, and reverse vaccinology to the whole SARS-CoV-2 proteomes or the structural proteins. Examples of these vaccines are the messenger RNA and viral vector vaccines. AI provides cost-saving and agility. However, the challenges of its usage are the difficulty of collecting data, the internal and external validation, ethical consideration, therapeutic effect, and the time needed for clinical trials after drug approval. Moreover, there is a common problem in the deep learning (DL) model which is the shortage of interpretability.

CONCLUSION

The growth of AI techniques in health care opened a broad gate for discovering the genomic sequences of the COVID-19 virus and the VOC. AI helps also in the development of vaccines and drugs (including drug repurposing) to obtain potential preventive and therapeutic agents for controlling the COVID-19 pandemic.

Fast Evaluation of Viral Emerging Risks (FEVER): A computational tool for biosurveillance, diagnostics, and mutation typing of emerging viral pathogens

Viral pathogens can rapidly evolve, adapt to novel hosts, and evade human immunity. The early detection of emerging viral pathogens through biosurveillance coupled with rapid and accurate diagnostics are required to mitigate global pandemics. However, RNA viruses can mutate rapidly, hampering biosurveillance and diagnostic efforts. Here, we present a novel computational approach called FEVER (Fast Evaluation of Viral Emerging Risks) to design assays that simultaneously accomplish: 1) broad-coverage biosurveillance of an entire group of viruses, 2) accurate diagnosis of an outbreak strain, and 3) mutation typing to detect variants of public health importance. We demonstrate the application of FEVER to generate assays to simultaneously 1) detect sarbecoviruses for biosurveillance; 2) diagnose infections specifically caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); and 3) perform rapid mutation typing of the D614G SARS-CoV-2 spike variant associated with increased pathogen transmissibility. These FEVER assays had a high in silico recall (predicted positive) up to 99.7% of 525,708 SARS-CoV-2 sequences analyzed and displayed sensitivities and specificities as high as 92.4% and 100% respectively when validated in 100 clinical samples. The D614G SARS-CoV-2 spike mutation PCR test was able to identify the single nucleotide identity at position 23,403 in the viral genome of 96.6% SARS-CoV-2 positive samples without the need for sequencing. This study demonstrates the utility of FEVER to design assays for biosurveillance, diagnostics, and mutation typing to rapidly detect, track, and mitigate future outbreaks and pandemics caused by emerging viruses.

Exploring the Lethality of Human-Adapted Coronavirus Through Alignment-Free Machine Learning Approaches Using Genomic Sequences

Background

A newly emerging novel coronavirus appeared and rapidly spread worldwide and World Health Organization declared a pandemic on March 11, 2020. The roles and characteristics of coronavirus have captured much attention due to its power of causing a wide variety of infectious diseases, from mild to severe, on humans. The detection of the lethality of human coronavirus is key to estimate the viral toxicity and provide perspectives for treatment.

Methods

We developed an alignment-free framework that utilizes machine learning approaches for an ultra-fast and highly accurate prediction of the lethality of human-adapted coronavirus using genomic sequences. We performed extensive experiments through six different feature transformation and machine learning algorithms combining digital signal processing to identify the lethality of possible future novel coronaviruses using existing strains.

Results

The results tested on SARS-CoV, MERS-CoV and SARS-CoV-2 datasets show an average 96.7% prediction accuracy. We also provide preliminary analysis validating the effectiveness of our models through other human coronaviruses. Our framework achieves high levels of prediction performance that is alignment-free and based on RNA sequences alone without genome annotations and specialized biological knowledge.

Conclusion

The results demonstrate that, for any novel human coronavirus strains, this study can offer a reliable real-time estimation for its viral lethality.

Recent omics-based computational methods for COVID-19 drug discovery and repurposing

The coronavirus disease 2019 (COVID-19) pandemic, caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), is the main reason for the increasing number of deaths worldwide. Although strict quarantine measures were followed in many countries, the disease situation is still intractable. Thus, it is needed to utilize all possible means to confront this pandemic. Therefore, researchers are in a race against the time to produce potential treatments to cure or reduce the increasing infections of COVID-19. Computational methods are widely proving rapid successes in biological related problems, including diagnosis and treatment of diseases. Many efforts in recent months utilized Artificial Intelligence (AI) techniques in the context of fighting the spread of COVID-19. Providing periodic reviews and discussions of recent efforts saves the time of researchers and helps to link their endeavors for a faster and efficient confrontation of the pandemic. In this review, we discuss the recent promising studies that used Omics-based data and utilized AI algorithms and other computational tools to achieve this goal. We review the established datasets and the developed methods that were basically directed to new or repurposed drugs, vaccinations and diagnosis. The tools and methods varied depending on the level of details in the available information such as structures, sequences or metabolic data.

COVID-19 prediction based on genome similarity of human SARS-CoV-2 and bat SARS-CoV-like coronavirus

This paper proposes an efficient and accurate method to predict coronavirus disease 19 (COVID-19) based on the genome similarity of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and a bat SARS-CoV-like coronavirus. We introduce similarity features to distinguish COVID-19 from other human coronaviruses by comparing human coronaviruses with a bat SARS-CoV-like coronavirus. In the proposed method each human coronavirus sequence is assigned to three similarity scores considering nucleotide similarities and mutations that lead to the strong absence of cytosine and guanine nucleotides. Next the proposed features are integrated with CpG island features of the genome sequences to improve COVID-19 prediction. Thus, each genome sequence is represented by five real numbers. We exhibit the effectiveness of the proposed features using six machine learning classifiers on a dataset including the genome sequences of human coronaviruses similar to SARS-CoV-2. The performances of the machine learning classifiers are close to each other and k-nearest neighbor classifier with similarity features achieves the best results with an accuracy of 99.2%. Moreover, k-nearest neighbor classifier with the integration of CpG based and similarity features has an admirable performance and achieves an accuracy of 99.8%. Experimental results demonstrate that similarity features remarkably decrease the number of false negatives and significantly improve the overall performance. The superiority of the proposed method is also highlighted by comparing with the state-of-the-art studies detecting COVID-19 from genome sequences.

Multiplex Biosensing for Simultaneous Detection of Mutations in SARS-CoV-2

COVID-19 pandemic caused by the severe acute respiratory syndrome coronavirus type 2 (SARS-CoV-2) has become the world's largest public health emergency of the past few decades. Thousands of mutations were identified in the SARS-CoV-2 genome. Some mutants are more infectious and may replace the original strains. Recently, B.1.1.7(Alpha), B1.351(Beta), and B.1.617.2(Delta) strains, which appear to have increased transmissibility, were detected. These strains accounting for the high proportion of newly diagnosed cases spread rapidly over the world. Particularly, the Delta variant has been reported to account for a vast majority of the infections in several countries over the last few weeks. The application of biosensors in the detection of SARS-CoV-2 is important for the control of the COVID-19 pandemic. Due to high demand for SARS-CoV-2 genotyping, it is urgent to develop reliable and efficient systems based on integrated multiple biosensor technology for rapid detection of multiple SARS-CoV-2 mutations simultaneously. This is important not only for the detection and analysis of the current but also for future mutations. Novel biosensors combined with other technologies can be used for the reliable and effective detection of SARS-CoV-2 mutants.

CoVrimer: A tool for aligning SARS-CoV-2 primer sequences and selection of conserved/degenerate primers

As mutations in SARS-CoV-2 virus accumulate rapidly, novel primers that amplify this virus sensitively and specifically are in demand. We have developed a webserver named CoVrimer by which users can search for and align existing or newly designed conserved/degenerate primer pair sequences against the viral genome and assess the mutation load of both primers and amplicons. CoVrimer uses mutation data obtained from an online platform established by NGDC-CNCB (12 May 2021) to identify genomic regions, either conserved or with low levels of mutations, from which potential primer pairs are designed and provided to the user for filtering based on generalized and SARS-CoV-2 specific parameters. Alignments of primers and probes can be visualized with respect to the reference genome, indicating variant details and the level of conservation. Consequently, CoVrimer is likely to help researchers with the challenges posed by viral evolution and is freely available at http://konulabapps.bilkent.edu.tr:3838/CoVrimer/.

SARS-CoV-2 Tests: Bridging the Gap between Laboratory Sensors and Clinical Applications

This review covers emerging biosensors for SARS-CoV-2 detection together with a review of the biochemical and clinical assays that are in use in hospitals and clinical laboratories. We discuss the gap in bridging the current practice of testing laboratories with nucleic acid amplification methods, and the robustness of assays the laboratories seek, and what emerging SARS-CoV-2 sensors have currently addressed in the literature. Together with the established nucleic acid and biochemical tests, we review emerging technology and antibody tests to determine the effectiveness of vaccines on individuals.

An update on novel approaches for diagnosis and treatment of SARS-CoV-2 infection

The ongoing pandemic of coronavirus disease 2019 (COVID-19) has made a serious public health and economic crisis worldwide which united global efforts to develop rapid, precise, and cost-efficient diagnostics, vaccines, and therapeutics. Numerous multi-disciplinary studies and techniques have been designed to investigate and develop various approaches to help frontline health workers, policymakers, and populations to overcome the disease. While these techniques have been reviewed within individual disciplines, it is now timely to provide a cross-disciplinary overview of novel diagnostic and therapeutic approaches summarizing complementary efforts across multiple fields of research and technology. Accordingly, we reviewed and summarized various advanced novel approaches used for diagnosis and treatment of COVID-19 to help researchers across diverse disciplines on their prioritization of resources for research and development and to give them better a picture of the latest techniques. These include artificial intelligence, nano-based, CRISPR-based, and mass spectrometry technologies as well as neutralizing factors and traditional medicines. We also reviewed new approaches for vaccine development and developed a dashboard to provide frequent updates on the current and future approved vaccines.

Simple Classification of RNA Sequences of Respiratory-Related Coronaviruses

A very simple, fast, and efficient approach to analyze and identify respiratory-related virus sequences based on machine learning is proposed. Such schemes are very important in identifying viruses, especially in view of spreading pandemics. The method is based on genetic code rules and the open reading frame (ORF). Data from the respiratory-related coronaviruses are collected and features are extracted based on reoccurring nucleobase 3-tuples in the RNA. Our methodology is simply based on counting nucleobase triplets, normalizing the count to the length of the sequence, and applying principal component analysis (PCA) techniques. The triplet counting can be further used for classification purposes. DNA sequences from the herpes virus family can be considered as the first step towards a complete and accurate classification including more complex factors, such as mutations. The proposed classification scheme is simply based on "counting" biological information. It can serve as the first fast detection method, widely accessible and portable to a variety of distinct architectures for fast and on-the-fly detection. We provide an approach that can be further optimized and combined with supervised techniques to allow for more accurate detection and read out of the exact virus type or sequence. We discuss the relevance of this scheme in identifying differences in similar viruses and their impact on biochemical analysis.

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

Due to the continued evolution of the SARS-CoV-2 pandemic, researchers worldwide are working to mitigate, suppress its spread, and better understand it by deploying digital signal processing (DSP) and machine learning approaches. This study presents an alignment-free approach to classify the SARS-CoV-2 using complementary DNA, which is DNA synthesized from the single-stranded RNA virus. Herein, a total of 1582 samples, with different lengths of genome sequences from different regions, were collected from various data sources and divided into a SARS-CoV-2 and a non-SARS-CoV-2 group. We extracted eight biomarkers based on three-base periodicity, using DSP techniques, and ranked those based on a filter-based feature selection. The ranked biomarkers were fed into k-nearest neighbor, support vector machines, decision trees, and random forest classifiers for the classification of SARS-CoV-2 from other coronaviruses. The training dataset was used to test the performance of the classifiers based on accuracy and F-measure via 10-fold cross-validation. Kappa-scores were estimated to check the influence of unbalanced data. Further, 10 × 10 cross-validation paired t-test was utilized to test the best model with unseen data. Random forest was elected as the best model, differentiating the SARS-CoV-2 coronavirus from other coronaviruses and a control a group with an accuracy of 97.4 %, sensitivity of 96.2 %, and specificity of 98.2 %, when tested with unseen samples. Moreover, the proposed algorithm was computationally efficient, taking only 0.31 s to compute the genome biomarkers, outperforming previous studies.

A Simple RT-PCR Melting temperature Assay to Rapidly Screen for Widely Circulating SARS-CoV-2 Variants

The increased transmission of SARS-CoV-2 variants of concern (VOC), which originated in the United Kingdom (B.1.1.7/alpha), South Africa (B1.351/beta), Brazil (P.1/gamma), the United States (B.1.427/429 or epsilon), and India (B.1.617.2/delta), requires a vigorous public health response, including real-time strain surveillance on a global scale. Although genome sequencing is the gold standard for identifying these VOCs, it is time-consuming and expensive. Here, we describe a simple, rapid, and high-throughput reverse transcriptase PCR (RT-PCR) melting-temperature (T_m) screening assay that identifies the first three major VOCs. RT-PCR primers and four sloppy molecular beacon (SMB) probes were designed to amplify and detect the SARS-CoV-2 N501Y (A23063T) and E484K (G23012A) mutations and their corresponding wild-type sequences. After RT-PCR, the VOCs were identified by a characteristic T_m of each SMB. Assay optimization and testing was performed with RNA from SARS-CoV-2 USA WA1/2020 (wild type [WT]), B.1.1.7, and B.1.351 variant strains. The assay was then validated using clinical samples. The limit of detection for both the WT and variants was 4 and 10 genomic copies/reaction for the 501- and 484-codon assays, respectively. The assay was 100% sensitive and 100% specific for identifying the N501Y and E484K mutations in cultured virus and in clinical samples, as confirmed by Sanger sequencing. We have developed an RT-PCR melt screening test for the major VOCs that can be used to rapidly screen large numbers of patient samples, providing an early warning for the emergence of these variants and a simple way to track their spread.

Analysis of DNA Sequence Classification Using CNN and Hybrid Models

In a general computational context for biomedical data analysis, DNA sequence classification is a crucial challenge. Several machine learning techniques have used to complete this task in recent years successfully. Identification and classification of viruses are essential to avoid an outbreak like COVID-19. Regardless, the feature selection process remains the most challenging aspect of the issue. The most commonly used representations worsen the case of high dimensionality, and sequences lack explicit features. It also helps in detecting the effect of viruses and drug design. In recent days, deep learning (DL) models can automatically extract the features from the input. In this work, we employed CNN, CNN-LSTM, and CNN-Bidirectional LSTM architectures using Label and K-mer encoding for DNA sequence classification. The models are evaluated on different classification metrics. From the experimental results, the CNN and CNN-Bidirectional LSTM with K-mer encoding offers high accuracy with 93.16% and 93.13%, respectively, on testing data.

The Role of Artificial Intelligence in Fighting the COVID-19 Pandemic

The first few months of 2020 have profoundly changed the way we live our lives and carry out our daily activities. Although the widespread use of futuristic robotaxis and self-driving commercial vehicles has not yet become a reality, the COVID-19 pandemic has dramatically accelerated the adoption of Artificial Intelligence (AI) in different fields. We have witnessed the equivalent of two years of digital transformation compressed into just a few months. Whether it is in tracing epidemiological peaks or in transacting contactless payments, the impact of these developments has been almost immediate, and a window has opened up on what is to come. Here we analyze and discuss how AI can support us in facing the ongoing pandemic. Despite the numerous and undeniable contributions of AI, clinical trials and human skills are still required. Even if different strategies have been developed in different states worldwide, the fight against the pandemic seems to have found everywhere a valuable ally in AI, a global and open-source tool capable of providing assistance in this health emergency. A careful AI application would enable us to operate within this complex scenario involving healthcare, society and research.

A Simple RT-PCR Melting temperature Assay to Rapidly Screen for Widely Circulating SARS-CoV-2 Variants

Background.

The increased transmission of SARS-CoV-2 variants of concern (VOC) which originated in the United Kingdom (B.1.1.7), South Africa (B1.351), Brazil (P.1) and in United States (B.1.427/429) requires a vigorous public health response, including real time strain surveillance on a global scale. Although genome sequencing is the gold standard for identifying these VOCs, it is time consuming and expensive. Here, we describe a simple, rapid and high-throughput reverse-transcriptase PCR (RT-PCR) melting temperature (Tm) screening assay that identifies these three major VOCs.

Methods.

RT-PCR primers and four sloppy molecular beacon (SMB) probes were designed to amplify and detect the SARS-CoV-2 N501Y (A23063T) and E484K (G23012A) mutations and their corresponding wild type sequences. After RT-PCR, the VOCs were identified by a characteristic Tm of each SMB. Assay optimization and testing was performed with RNA from SARS-CoV-2 USA WA1/2020 (WT), a B.1.17 and a B.1.351 variant strains. The assay was then validated using clinical samples.

Results.

The limit of detection (LOD) for both the WT and variants was 4 and 10 genomic copies/reaction for the 501 and 484 codon assays, respectively. The assay was 100% sensitive and 100% specific for identifying the N501Y and E484K mutations in cultured virus and in clinical samples as confirmed by Sanger sequencing.

Conclusion.

We have developed an RT-PCR melt screening test for the three major VOCs which can be used to rapidly screen large numbers of patient samples providing an early warning for the emergence of these variants and a simple way to track their spread.

Deep Learning for SARS COV-2 Genome Sequences

The SARS-CoV-2 virus which originated in Wuhan, China has since spread throughout the world and is affecting millions of people. When there is a novel virus outbreak, it is crucial to quickly determine if the epidemic is a result of the novel virus or a well-known virus. We propose a deep learning algorithm that uses a convolutional neural network (CNN) as well as a bi-directional long short-term memory (Bi-LSTM) neural network, for the classification of the severe acute respiratory syndrome coronavirus 2 (SARS CoV-2) amongst Coronaviruses. Besides, we classify whether a genome sequence contains candidate regulatory motifs or otherwise. Regulatory motifs bind to transcription factors. Transcription factors are responsible for the expression of genes. The experimental results show that at peak performance, the proposed convolutional neural network bi-directional long short-term memory (CNN-Bi-LSTM) model achieves a classification accuracy of 99.95%, area under curve receiver operating characteristic (AUC ROC) of 100.00%, a specificity of 99.97%, the sensitivity of 99.97%, Cohen's Kappa equal to 0.9978, Mathews Correlation Coefficient (MCC) equal to 0.9978 for the classification of SARS CoV-2 amongst Coronaviruses. Also, the CNN-Bi-LSTM correctly detects whether a sequence has candidate regulatory motifs or binding-sites with a classification accuracy of 99.76%, AUC ROC of 100.00%, a specificity of 99.76%, a sensitivity of 99.76%, MCC equal to 0.9980, and Cohen's Kappa of 0.9970 at peak performance. These results are encouraging enough to recognise deep learning algorithms as alternative avenues for detecting SARS CoV-2 as well as detecting regulatory motifs in the SARS CoV-2 genes.

Essential interpretations of bioinformatics in COVID-19 pandemic

The currently emerging pathogen SARS-CoV-2 has produced the global pandemic crisis by causing COVID-19. The unique and novel genetic makeup of SARS-CoV-2 has created hurdles in biological research, due to which the potential drug/vaccine candidates have not yet been discovered by the scientific community. Meanwhile, the advantages of bioinformatics in viral research had created a milestone since last few decades. The exploitation of bioinformatics tools and techniques has successfully interpreted this viral genomics architecture. Some major in silico studies involving next-generation sequencing, genome-wide association studies, computer-aided drug design etc. have been effectively applied in COVID-19 research methodologies and discovered novel information on SARS-CoV-2 in several ways. Nowadays the implementation of in silico studies in COVID-19 research has not only sequenced the SARS-CoV-2 genome but also properly analyzed the sequencing errors, evolutionary relationship, genetic variations, putative drug candidates against SARS-CoV-2 viral genes etc. within a very short time period. These would be very needful towards further research on COVID-19 pandemic and essential for vaccine development against SARS-CoV-2 which will save public health.