{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T01:57:04Z","timestamp":1793325424382,"version":"4.5.0"},"reference-count":84,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T00:00:00Z","timestamp":1757289600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Rapid and scalable classification of SARS-CoV-2 genomes from spike-gene sequences can support real-time genomic surveillance in contexts where whole-genome data or high-end computing resources are limited.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We curated approximately 35,800 quality-filtered spike sequences spanning multiple clades and lineages and trained a hybrid CNN\u2013BiLSTM model with standard regularization and class-imbalance handling. Model performance was benchmarked against Nextclade assignments and compared with classical machine-learning baselines.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Across 10 experimental runs, the model achieved a mean training accuracy of 99.74% \u00b1 0.11, a validation accuracy of 99.00% \u00b1 0.00, and a test accuracy of 99.91% \u00b1 0.03. In benchmarking against the molecular epidemiology tool Nextclade, our model demonstrated superior performance, correctly identifying 100% of Omicron sequences, compared to 34.95% achieved by Nextclade. Saliency and feature attribution analyses highlighted recurrent spike substitutions consistent with known variant-defining mutations, as well as additional uncharacterized motifs with potential biological relevance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>These findings demonstrate that spike-only deep models can provide rapid and accurate clade or variant classification, while also yielding interpretable feature importance. Such models complement phylogenetic approaches in settings with constrained resources and enable efficient triage of samples for confirmatory whole-genome analysis, supporting more timely genomic surveillance.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2025.1512003","type":"journal-article","created":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T05:31:23Z","timestamp":1757309483000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Enhanced deep Convolutional Neural Network for SARS-CoV-2 variants classification"],"prefix":"10.3389","volume":"8","author":[{"given":"Olaitan I.","family":"Awe","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hesborn","family":"Obura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Charles","family":"Ssemuyiga","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Evans","family":"Mudibo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mike J.","family":"Mwanga","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,9,8]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"41","DOI":"10.21608\/MJEER.2021.146090","article-title":"DNA sequences classification with deep learning: a survey","volume":"30","author":"Abd-Alhalem","year":"2021","journal-title":"Menoufia J. Electron. Eng. Res."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"3773","DOI":"10.21105\/JOSS.03773","article-title":"Nextclade: clade assignment, mutation calling and quality control for viral genomes","volume":"6","author":"Aksamentov","year":"2021","journal-title":"J. Open Source Softw."},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1101\/2024.01.20.576448","article-title":"Multiple sclerosis stages and their differentially expressed genes: a bioinformatics analysis","author":"Alaya","year":"2024","journal-title":"bioRxiv"},{"key":"ref4","volume-title":"PWM2Vec: an efficient embedding approach for viral host specification from coronavirus spike sequences","author":"Ali","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1089\/CMB.2022.0391","article-title":"Characterizing SARS-CoV-2 spike sequences based on geographical location","volume":"30","author":"Ali","year":"2023","journal-title":"J. Comput. Biol."},{"key":"ref6","volume-title":"Spike2Vec:","author":"Ali","year":"2021"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-91415-8_14","volume-title":"A k-mer based approach for SARS-CoV-2 variant identification","author":"Ali","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"628","DOI":"10.12688\/f1000research.14880.4","article-title":"SeqAcademy: an educational pipeline for RNA-Seq and ChIP-Seq analysis","volume":"7","author":"Ather","year":"2018","journal-title":"F1000Res"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"101143","DOI":"10.1016\/j.imu.2022.101143","article-title":"Comparative study between molecular and genetic evolutionary analysis tools using African SARS-CoV-2 variants","volume":"36","author":"Awe","year":"2023","journal-title":"Inform. Med. Unlocked"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"gigabyte143-0","DOI":"10.46471\/gigabyte.143","article-title":"Neurovar: an open-source tool for the visualization of gene expression and variation data for biomarkers of neurological diseases","volume":"2024","author":"Ben Aribi","year":"2024","journal-title":"Gigabyte"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-93067-5","article-title":"Efficient and easy gene expression and genetic variation data analysis and visualization using exvar","author":"Ben Aribi","year":"2025","journal-title":"Sci. Rep."},{"key":"ref12","article-title":"Accounting for variance in machine learning benchmarks","author":"Bouthillier","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1186\/1471-2105-10-421","article-title":"BLAST+: architecture and applications","volume":"10","author":"Camacho","year":"2009","journal-title":"BMC Bioinform."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1038\/s41586-021-04385-3","article-title":"Omicron escapes the majority of existing SARS-CoV-2 neutralizing antibodies","volume":"602","author":"Cao","year":"2021","journal-title":"Nature"},{"key":"ref15","volume-title":"Geometric deep learning","author":"Charles","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"15286","DOI":"10.1080\/07391102.2023.2188419","article-title":"Artificial intelligence based virtual screening study for competitive and allosteric inhibitors of the SARS-CoV-2 main protease","volume":"41","author":"Charles","year":"2023","journal-title":"J. Biomol. Struct. Dyn."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1080\/07391102.2023.2279700","article-title":"Artificial intelligence based de-novo design for novel Plasmodium falciparum plasmepsin (PM) X inhibitors","volume":"43","author":"Charles","year":"2023","journal-title":"J. Biomol. Struct. Dyn."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"24442","DOI":"10.1038\/s41598-025-09744-y","article-title":"RareInsight simplifies the communication of genetic results for rare disease patients","volume":"15","author":"Coetzer","year":"2025","journal-title":"Sci. Rep."},{"key":"ref19","article-title":"Tensorflow lite micro: embedded machine learning for tinyml systems","author":"David","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1186\/s12864-019-5952-2","article-title":"geneHummus: an R package to define gene families and their expression in legumes and beyond","volume":"20","author":"Die","year":"2019","journal-title":"BMC Genomics"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"516","DOI":"10.1016\/j.chom.2021.03.009","article-title":"Infection- and vaccine-induced antibody binding and neutralization of the B.1.351 SARS-CoV-2 variant","volume":"29","author":"Edara","year":"2021","journal-title":"Cell Host Microbe"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1101\/2023.09.11.557132","article-title":"Differential expression analysis of miRNAs and mRNAs in epilepsy uncovers potential biomarkers","author":"El Abed","year":"2023","journal-title":"bioRxiv"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1038\/s41467-023-36336-z","article-title":"A deep learning approach reveals unexplored landscape of viral expression in cancer","volume":"14","author":"Elbasir","year":"2023","journal-title":"Nat. Commun."},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3389\/fchem.2024.1503593","article-title":"Machine learning and molecular dynamics simulations predict potential TGR5 agonists for type 2 diabetes treatment","author":"Enejoh","year":"2025","journal-title":"Front. Chem."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1016\/J.PATREC.2005.10.010","article-title":"An introduction to ROC analysis","volume":"27","author":"Fawcett","year":"2006","journal-title":"Pattern Recogn. Lett."},{"key":"ref26","article-title":"Exploring the limits of out-of-distribution detection","author":"Fort","year":"2021"},{"key":"ref27","volume-title":"Deep learning using rectified linear units (ReLU)","author":"Fred Agarap","year":"2018"},{"key":"ref28","volume-title":"Pooling methods in deep neural networks, a review","author":"Gholamalinezhad","year":"2020"},{"key":"ref29","volume-title":"Deep learning","author":"Goodfellow","year":"2016"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1007\/978-3-642-24797-2_4","article-title":"Long short-term memory","volume-title":"Supervised sequence labelling with recurrent neural networks","author":"Graves","year":"2012"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"4196","DOI":"10.1038\/s41467-021-24435-8","article-title":"Mapping mutations to the SARS-CoV-2 RBD that escape binding by different classes of antibodies","volume":"12","author":"Greaney","year":"2021","journal-title":"Nat. Commun."},{"key":"ref32","volume-title":"Deep learning with Keras","author":"Gulli","year":"2017"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"1835056","DOI":"10.1155\/2021\/1835056","article-title":"Analysis of DNA sequence classification using CNN and hybrid models","volume":"2021","author":"Gunasekaran","year":"2021","journal-title":"Comput. Math. Methods Med."},{"key":"ref34","article-title":"On calibration of modern neural networks","author":"Guo","year":"2017"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1007\/978-3-031-43725-0_5","article-title":"Introduction to pandas","volume-title":"Essentials of python for artificial intelligence and machine learning","author":"Gupta","year":"2024"},{"key":"ref36","article-title":"Nextstrain: real-time tracking of pathogen evolution","volume-title":"Bioinformatics","author":"Hadfield","year":"2018"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"1510029","DOI":"10.3389\/fchem.2024.1510029","article-title":"Machine learning and molecular docking prediction of potential inhibitors against dengue virus","volume":"12","author":"Hanson","year":"2024","journal-title":"Front. Chem."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1038\/s41579-021-00573-0","article-title":"SARS-CoV-2 variants, spike mutations and immune escape","volume":"19","author":"Harvey","year":"2021","journal-title":"Nat. Rev. Microbiol."},{"key":"ref39","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/NECO.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2018.00286","article-title":"Quantization and training of neural networks for efficient integer-arithmetic-only inference","author":"Jacob","year":"2018"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"3387","DOI":"10.1093\/bioinformatics\/btx431","article-title":"Deeploc: prediction of protein subcellular localization using deep learning","volume":"33","author":"Juan","year":"2017","journal-title":"Bioinformatics"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"2126","DOI":"10.1016\/S0140-6736(21)02758-6","article-title":"Omicron SARS-CoV-2 variant: a new chapter in the COVID-19 pandemic","volume":"398","author":"Karim","year":"2021","journal-title":"Lancet"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"1160","DOI":"10.1093\/BIB\/BBX108","article-title":"MAFFT online service: multiple sequence alignment, interactive sequence choice and visualization","volume":"20","author":"Katoh","year":"2019","journal-title":"Brief. Bioinform."},{"key":"ref44","article-title":"Adam: A method for stochastic optimization","volume-title":"Proceedings of the 3rd International Conference on Learning Representations (ICLR 2015)","author":"Kingma","year":"2014"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"812","DOI":"10.1016\/j.cell.2020.06.043","article-title":"Tracking changes in SARS-CoV-2 spike: evidence that D614G increases infectivity of the COVID-19 virus","volume":"182","author":"Korber","year":"2020","journal-title":"Cell"},{"key":"ref46","first-page":"45","article-title":"Scikit-learn","volume-title":"Machine learning for evolution strategies","author":"Kramer","year":"2016"},{"key":"ref47","article-title":"Beyond temperature scaling: Obtaining well-calibrated multi-class probabilities with dirichlet calibration","volume-title":"Advances in neural information processing systems","author":"Kull","year":"2019"},{"key":"ref48","doi-asserted-by":"publisher","first-page":"553","DOI":"10.1016\/j.bbrc.2020.09.010","article-title":"Machine learning methods accurately predict host specificity of coronaviruses based on spike sequences alone","volume":"533","author":"Kuzmin","year":"2020","journal-title":"Biochem. Biophys. Res. Commun."},{"key":"ref49","doi-asserted-by":"publisher","first-page":"e0296627","DOI":"10.1371\/JOURNAL.PONE.0296627","article-title":"Machine learning-based approach KEVOLVE efficiently identifies SARS-CoV-2 variant-specific genomic signatures","volume":"19","author":"Lebatteux","year":"2024","journal-title":"PLoS One"},{"key":"ref50","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/NATURE14539","article-title":"Deep learning","volume":"521","author":"Lecun","year":"2015","journal-title":"Nature"},{"key":"ref51","article-title":"Python libraries matplotlib, seaborn and pandas for visualization geospatial datasets generated by QGIS","volume-title":"Analele stiintifice ale Universitatii\" Alexandru Ioan Cuza\" din Iasi-seria Geografie","author":"Lemenkova","year":"2020"},{"key":"ref52","doi-asserted-by":"publisher","first-page":"2000792","DOI":"10.1002\/SMTD.202000792","article-title":"High-throughput metagenomics for identification of pathogens in the clinical settings","volume":"5","author":"Li","year":"2021","journal-title":"Small Methods"},{"key":"ref53","doi-asserted-by":"publisher","first-page":"bbac036","DOI":"10.1093\/bib\/bbac036","article-title":"Deep learning based on biologically interpretable genome representation predicts two types of human adaptation of SARS-CoV-2 variants","volume":"23","author":"Li","year":"2022","journal-title":"Brief. Bioinform."},{"key":"ref54","doi-asserted-by":"publisher","first-page":"lqaa009","DOI":"10.1093\/NARGAB\/LQAA009","article-title":"DeepMicrobes: taxonomic classification for metagenomics with deep learning","volume":"2","author":"Liang","year":"2020","journal-title":"NAR Genom. Bioinform."},{"key":"ref55","doi-asserted-by":"publisher","first-page":"1139","DOI":"10.1126\/science.abf6950","article-title":"Recurrent deletions in the SARS-CoV-2 spike glycoprotein drive antibody escape","volume":"371","author":"McCarthy","year":"2021","journal-title":"Science"},{"key":"ref56","doi-asserted-by":"publisher","first-page":"706","DOI":"10.1038\/s41586-022-04474-x","article-title":"Altered TMPRSS2 usage by SARS-CoV-2 omicron impacts infectivity and fusogenicity","volume":"603","author":"Meng","year":"2022","journal-title":"Nature"},{"key":"ref57","doi-asserted-by":"publisher","first-page":"11257","DOI":"10.1038\/NCOMMS11257","article-title":"Fast and sensitive taxonomic classification for metagenomics with kaiju","volume":"7","author":"Menzel","year":"2016","journal-title":"Nat. Commun."},{"key":"ref58","doi-asserted-by":"publisher","first-page":"1072","DOI":"10.3390\/v14051072","article-title":"Convolutional neural networks based on sequential spike predict the high human adaptation of SARS-CoV-2 omicron variants","volume":"14","author":"Nan","year":"2022","journal-title":"Viruses"},{"key":"ref59","article-title":"Exploring Generalization in Deep Learning","volume-title":"Proceedings of the 31st Annual Conference on Neural Information Processing Systems (NeurIPS 2017)","author":"Neyshabur","year":"2017"},{"key":"ref60","doi-asserted-by":"publisher","first-page":"e100643","DOI":"10.1136\/bmjhci-2022-100643","article-title":"Predicting emerging SARS-CoV-2 variants of concern through a one class dynamic anomaly detection algorithm","volume":"29","author":"Nicora","year":"2022","journal-title":"BMJ Health Care Inform."},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1101\/2023.09.11.557129","article-title":"Expression level analysis of ACE2 receptor gene in African-American and non-African-American COVID-19 patients","author":"Nyamari","year":"2023","journal-title":"bioRxiv"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1101\/2022.06.30.498338","article-title":"Transcriptional profiles analysis of COVID-19 and malaria patients reveals potential biomarkers in children","author":"Nzungize","year":"2022","journal-title":"bioRxiv"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1101\/2022.05.18.492401","article-title":"Molecular phylogenetics of HIV-1 subtypes in African populations: a case study of sub-Saharan African countries","author":"Obura","year":"2022","journal-title":"bioRxiv"},{"key":"ref64","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1016\/j.imu.2018.07.004","article-title":"A comparative computational genomics of Ebola virus disease strains: in-silico insight for Ebola control","volume":"12","author":"Oluwagbemi","year":"2018","journal-title":"Inform. Med. Unlocked"},{"key":"ref65","doi-asserted-by":"publisher","first-page":"e17181","DOI":"10.7717\/PEERJ.17181\/SUPP-9","article-title":"Investigating antimicrobial resistance genes in Kenya, Uganda and Tanzania cattle using metagenomics","volume":"12","author":"Omar","year":"2024","journal-title":"PeerJ"},{"key":"ref66","doi-asserted-by":"publisher","first-page":"1509407","DOI":"10.3389\/fchem.2024.1509407","article-title":"Prostruc: an open-source tool for 3D structure prediction using homology modeling","volume":"12","author":"Pawar","year":"2024","journal-title":"Front. Chem."},{"key":"ref67","article-title":"Hyper-opinion evidential deep learning for out-of-distribution detection","author":"Qu","year":"2024"},{"key":"ref68","doi-asserted-by":"crossref","first-page":"667","DOI":"10.1007\/978-1-4842-4215-5_11","article-title":"Deep learning using keras and tensorflow","volume-title":"Machine Learning Using R: With Time Series and Industry-Based Use Cases in R","author":"Ramasubramanian","year":"2019"},{"key":"ref69","doi-asserted-by":"publisher","first-page":"e0232391","DOI":"10.1371\/JOURNAL.PONE.0232391","article-title":"Machine learning using intrinsic genomic signatures for rapid classification of novel pathogens: COVID-19 case study","volume":"15","author":"Randhawa","year":"2020","journal-title":"PLoS One"},{"key":"ref70","first-page":"338","article-title":"Reporting score distributions makes a difference: performance study of LSTM-networks for sequence tagging","author":"Reimers","year":"2017"},{"key":"ref71","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1186\/s40168-017-0283-5","article-title":"Virfinder: a novel k-mer based tool for identifying viral sequences from assembled metagenomic data","volume":"5","author":"Ren","year":"2017","journal-title":"Microbiome"},{"key":"ref72","doi-asserted-by":"publisher","first-page":"e985","DOI":"10.7717\/PEERJ.985\/SUPP-2","article-title":"VirSorter: mining viral signal from microbial genomic data","volume":"2015","author":"Roux","year":"2015","journal-title":"PeerJ"},{"key":"ref73","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1038\/S41586-021-04266-9","article-title":"Enhanced fusogenicity and pathogenicity of SARS-CoV-2 delta P681R mutation","volume":"602","author":"Saito","year":"2022","journal-title":"Nature"},{"key":"ref74","doi-asserted-by":"crossref","DOI":"10.1109\/JPROC.2021.3060483","article-title":"Explaining deep neural networks and beyond: A review of methods and applications","author":"Samek","year":"2021"},{"key":"ref75","volume-title":"Horovod: fast and easy distributed deep learning in TensorFlow","author":"Sergeev","year":"2018"},{"key":"ref76","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref77","doi-asserted-by":"publisher","first-page":"867111","DOI":"10.3389\/fbinf.2022.867111","article-title":"VirHunter: a deep learning-based method for detection of novel RNA viruses in plant sequencing data","volume":"2","author":"Sukhorukov","year":"2022","journal-title":"Front. Bioinform."},{"key":"ref78","doi-asserted-by":"publisher","first-page":"e0222271","DOI":"10.1371\/JOURNAL.PONE.0222271","article-title":"ViraMiner: deep learning on raw DNA sequences for identifying viral genomes in human samples","volume":"14","author":"Tampuu","year":"2019","journal-title":"PLoS One"},{"key":"ref79","article-title":"Evaluating model calibration in classification","author":"Vaicenavicius","year":"2019"},{"key":"ref80","doi-asserted-by":"crossref","DOI":"10.1109\/APCCAS.2018.8605654","article-title":"A high-speed and low-complexity architecture for softmax function in deep learning","author":"Wang","year":"2018"},{"key":"ref81","doi-asserted-by":"publisher","first-page":"59597","DOI":"10.1109\/ACCESS.2021.3073728","article-title":"Deep learning for SARS COV-2 genome sequences","volume":"9","author":"Whata","year":"2021","journal-title":"IEEE Access"},{"key":"ref82","doi-asserted-by":"publisher","first-page":"i121","DOI":"10.1093\/BIOINFORMATICS\/BTW255","article-title":"Convolutional neural network architectures for predicting DNA\u2013protein binding","volume":"32","author":"Zeng","year":"2016","journal-title":"Bioinformatics"},{"key":"ref83","article-title":"Bidirectional long short-term memory networks for relation classification","author":"Zhang","year":"2015"},{"key":"ref84","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1038\/S41586-020-2012-7","article-title":"A pneumonia outbreak associated with a new coronavirus of probable bat origin","volume":"579","author":"Zhou","year":"2020","journal-title":"Nature"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1512003\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T05:31:27Z","timestamp":1757309487000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1512003\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,8]]},"references-count":84,"alternative-id":["10.3389\/frai.2025.1512003"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1512003","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,8]]},"article-number":"1512003"}}