{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T01:32:42Z","timestamp":1790904762549,"version":"4.1.0"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T00:00:00Z","timestamp":1788393600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T00:00:00Z","timestamp":1788393600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100018777","name":"Nile University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100018777","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    The rapid growth of genomic sequencing demands fast, accurate, and scalable analysis methods. In viral genomic classification, expanding labeled reference collections can make supervised models costly to update and dependent on fixed label sets, motivating retrieval-based genomic classification as a simpler, more flexible alternative. We present a unified benchmark of supervised and retrieval-based methods for viral genomic sequence classification across three viral classification tasks: hepatitis C virus (HCV) genotyping, COVID-19 discrimination, and human papillomavirus (HPV) genotyping. We compare standard sequence encodings (one-hot,\n                    <jats:italic>k<\/jats:italic>\n                    -mers, FCGR) with dense embeddings (dna2vec, DNABERT). For each representation, we evaluate supervised classifiers (Random Forest, Decision Tree, XGBoost) and retrieval-based classification, where sequence vectors are indexed with FAISS and labels are assigned via similarity-weighted k-NN. Furthermore, we benchmark multiple FAISS index types (Flat, IVF, HNSW, IVFPQ, OPQ) to characterize accuracy-speed\u2013memory trade-offs at scale. The results show that XGBoost and retrieval using Flat or IVF indexes achieve strong classification performance under different computational profiles. Compressed indexes such as IVFPQ and OPQ substantially reduce memory usage, although their accuracy loss depends on the dataset and representation. Overall, supervised XGBoost provides a favorable accuracy\u2013size trade-off, while retrieval-based classification remains competitive and allows labeled reference sequences to be incorporated without retraining a global classifier. This benchmark provides practical guidance for selecting sequence representations, classifiers, and vector-search indexes under different accuracy, memory, and update requirements.\n                  <\/jats:p>","DOI":"10.1038\/s41598-026-67272-9","type":"journal-article","created":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T03:24:42Z","timestamp":1788405882000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A unified benchmark of supervised and retrieval-based methods for viral genomic sequence classification"],"prefix":"10.1038","volume":"16","author":[{"given":"Ahmed M.","family":"Fahmy","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Melissa","family":"Ayad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hassan M.","family":"Ahmed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,3]]},"reference":[{"issue":"1","key":"67272_CR1","doi-asserted-by":"publisher","first-page":"1214","DOI":"10.1186\/s12864-024-11135-y","volume":"25","author":"F Alipour","year":"2024","unstructured":"Alipour, F., Hill, K. A. & Kari, L. Cgrclust: Chaos game representation for twin contrastive clustering of unlabelled DNA sequences. BMC Genomics 25(1), 1214 (2024).","journal-title":"BMC Genomics"},{"key":"67272_CR2","doi-asserted-by":"crossref","unstructured":"Refahi, M. S. et al. Fast and scalable gene embedding search: A comparative study of faiss and scann. arXiv:2507.16978 (2025).","DOI":"10.1145\/3768322.3769097"},{"issue":"3","key":"67272_CR3","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1016\/S0022-2836(05)80360-2","volume":"215","author":"SF Altschul","year":"1990","unstructured":"Altschul, S. F., Gish, W., Miller, W., Myers, E. W. & Lipman, D. J. Basic local alignment search tool. J. Mol. Biol. 215(3), 403\u2013410 (1990).","journal-title":"J. Mol. Biol."},{"issue":"1","key":"67272_CR4","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1038\/s42003-025-07902-6","volume":"8","author":"M Refahi","year":"2025","unstructured":"Refahi, M. et al. Enhancing nucleotide sequence representations in genomic analysis with contrastive optimization. Commun. Biol. 8(1), 517 (2025).","journal-title":"Commun. Biol."},{"key":"67272_CR5","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2022.815714","volume":"13","author":"R Lo","year":"2022","unstructured":"Lo, R. et al. Alignment-free analysis of whole-genome sequences from symbiodiniaceae reveals different phylogenetic signals in distinct regions. Front. Plant Sci. 13, 815714 (2022).","journal-title":"Front. Plant Sci."},{"issue":"13","key":"67272_CR6","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1093\/bioinformatics\/bty275","volume":"34","author":"S Seo","year":"2018","unstructured":"Seo, S., Oh, M., Park, Y. & Kim, S. Deepfam: Deep learning based alignment-free method for protein family modeling and prediction. Bioinformatics 34(13), 254\u2013262 (2018).","journal-title":"Bioinformatics"},{"issue":"1","key":"67272_CR7","doi-asserted-by":"publisher","first-page":"15463","DOI":"10.1038\/s41598-024-64209-y","volume":"14","author":"AM Fahmy","year":"2024","unstructured":"Fahmy, A. M., Hammad, M. S., Mabrouk, M. S. & Al-Atabany, W. I. On leveraging self-supervised learning for accurate hcv genotyping. Sci. Rep. 14(1), 15463 (2024).","journal-title":"Sci. Rep."},{"issue":"1","key":"67272_CR8","first-page":"1835056","volume":"2021","author":"H Gunasekaran","year":"2021","unstructured":"Gunasekaran, H. et al. Analysis of DNA sequence classification using cnn and hybrid models. Comput. Math. Methods Med. 2021(1), 1835056 (2021).","journal-title":"Comput. Math. Methods Med."},{"key":"67272_CR9","doi-asserted-by":"publisher","first-page":"6263","DOI":"10.1016\/j.csbj.2021.11.008","volume":"19","author":"HF L\u00f6chel","year":"2021","unstructured":"L\u00f6chel, H. F. & Heider, D. Chaos game representation and its applications in bioinformatics. Comput. Struct. Biotechnol. J. 19, 6263\u20136271 (2021).","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"67272_CR10","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1093\/gigascience\/giac119","volume":"12","author":"J Avila Cartes","year":"2023","unstructured":"Avila Cartes, J., Anand, S., Ciccolella, S., Bonizzoni, P. & Della Vedova, G. Accurate and fast clade assignment via deep learning and frequency chaos game representation. GigaScience 12, 119 (2023).","journal-title":"GigaScience"},{"issue":"3","key":"67272_CR11","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1007\/s00607-019-00768-7","volume":"102","author":"S Wang","year":"2020","unstructured":"Wang, S., Zhou, W. & Jiang, C. A survey of word embeddings based on deep learning. Computing 102(3), 717\u2013740 (2020).","journal-title":"Computing"},{"issue":"5","key":"67272_CR12","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1002\/cpz1.113","volume":"1","author":"C Dallago","year":"2021","unstructured":"Dallago, C. et al. Learned embeddings from deep learning to visualize and predict protein sets. Curr. Protoc. 1(5), 113 (2021).","journal-title":"Curr. Protoc."},{"key":"67272_CR13","unstructured":"Ng, P. dna2vec: Consistent vector representations of variable-length k-mers. arXiv:1701.06279 (2017)."},{"issue":"15","key":"67272_CR14","doi-asserted-by":"publisher","first-page":"2112","DOI":"10.1093\/bioinformatics\/btab083","volume":"37","author":"Y Ji","year":"2021","unstructured":"Ji, Y., Zhou, Z., Liu, H. & Davuluri, R. V. Dnabert: Pre-trained bidirectional encoder representations from transformers model for dna-language in genome. Bioinformatics 37(15), 2112\u20132120 (2021).","journal-title":"Bioinformatics"},{"key":"67272_CR15","unstructured":"Zhou, Z., Ji, Y., Li, W., Dutta, P., Davuluri, R., Liu, H.: Dnabert-2: Efficient foundation model and benchmark for multi-species genome. arXiv:2306.15006 (2023)."},{"key":"67272_CR16","doi-asserted-by":"publisher","first-page":"43177","DOI":"10.52202\/075280-1872","volume":"36","author":"E Nguyen","year":"2023","unstructured":"Nguyen, E. et al. Hyenadna: Long-range genomic sequence modeling at single nucleotide resolution. Adv. Neural Inf. Process. Syst. 36, 43177\u201343201 (2023).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"67272_CR17","first-page":"43632","volume":"235","author":"Y Schiff","year":"2024","unstructured":"Schiff, Y. et al. Caduceus: Bi-directional equivariant long-range DNA sequence modeling. Proc. Mach. Learn. Res. 235, 43632 (2024).","journal-title":"Proc. Mach. Learn. Res."},{"issue":"2","key":"67272_CR18","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1038\/s41592-024-02523-z","volume":"22","author":"H Dalla-Torre","year":"2025","unstructured":"Dalla-Torre, H. et al. Nucleotide transformer: Building and evaluating robust foundation models for human genomics. Nat. Methods 22(2), 287\u2013297 (2025).","journal-title":"Nat. Methods"},{"key":"67272_CR19","doi-asserted-by":"crossref","unstructured":"Refahi, M., Sokhansanj, B. & Rosen, G. Leveraging large language models for metagenomic analysis. In 2023 IEEE Signal Processing in Medicine and Biology Symposium (SPMB) 1\u20136 (IEEE, 2023).","DOI":"10.1109\/SPMB59478.2023.10372773"},{"issue":"3","key":"67272_CR20","doi-asserted-by":"publisher","first-page":"2177","DOI":"10.1109\/TCBB.2023.3237769","volume":"20","author":"NN Soylu","year":"2023","unstructured":"Soylu, N. N. & Sefer, E. Bert2ome: Prediction of $$2^{\\prime }$$-o-methylation modifications from rna sequence by transformer architecture based on bert. IEEE\/ACM Trans. Comput. Biol. Bioinform. 20(3), 2177\u20132189. https:\/\/doi.org\/10.1109\/TCBB.2023.3237769 (2023).","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform."},{"key":"67272_CR21","doi-asserted-by":"crossref","unstructured":"Sefer, E. & Kingsford, C. Metric labeling and semi-metric embedding for protein annotation prediction. In International Conference on Research in Computational Molecular Biology 392\u2013407 (Springer, 2011).","DOI":"10.1007\/978-3-642-20036-6_37"},{"issue":"2","key":"67272_CR22","doi-asserted-by":"publisher","first-page":"064","DOI":"10.1093\/ve\/veab064","volume":"7","author":"\u00c1 O\u2019Toole","year":"2021","unstructured":"O\u2019Toole, \u00c1. et al. Assignment of epidemiological lineages in an emerging pandemic using the pangolin tool. Virus evolution 7(2), 064 (2021).","journal-title":"Virus evolution"},{"key":"67272_CR23","unstructured":"Douze, M. et al. The faiss library. arXiv:2401.08281 (2024)."},{"issue":"suppl\u20131","key":"67272_CR24","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1093\/nar\/gkm962","volume":"36","author":"C Kuiken","year":"2007","unstructured":"Kuiken, C., Hraber, P., Thurmond, J. & Yusim, K. The hepatitis c sequence database in Los Alamos. Nucleic Acids Res. 36(suppl\u20131), 512\u2013516 (2007).","journal-title":"Nucleic Acids Res."},{"issue":"3","key":"67272_CR25","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1093\/bioinformatics\/bth485","volume":"21","author":"C Kuiken","year":"2005","unstructured":"Kuiken, C., Yusim, K., Boykin, L. & Richardson, R. The Los Alamos hepatitis c sequence database. Bioinformatics 21(3), 379\u2013384 (2005).","journal-title":"Bioinformatics"},{"issue":"1","key":"67272_CR26","doi-asserted-by":"publisher","first-page":"4003","DOI":"10.1038\/s41598-023-30941-0","volume":"13","author":"MS Hammad","year":"2023","unstructured":"Hammad, M. S., Ghoneim, V. F., Mabrouk, M. S. & Al-Atabany, W. I. A hybrid deep learning approach for covid-19 detection based on genomic image processing techniques. Sci. Rep. 13(1), 4003 (2023).","journal-title":"Sci. Rep."},{"issue":"8","key":"67272_CR27","doi-asserted-by":"publisher","first-page":"1475","DOI":"10.1109\/TKDE.2019.2909204","volume":"32","author":"W Li","year":"2019","unstructured":"Li, W. et al. Approximate nearest neighbor search on high dimensional data\u2013experiments, analyses, and improvement. IEEE Trans. Knowl. Data Eng. 32(8), 1475\u20131488 (2019).","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"67272_CR28","doi-asserted-by":"publisher","first-page":"2289","DOI":"10.1016\/j.csbj.2024.05.025","volume":"23","author":"C Moeckel","year":"2024","unstructured":"Moeckel, C. et al. A survey of k-mer methods and applications in bioinformatics. Comput. Struct. Biotechnol. J. 23, 2289\u20132303 (2024).","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"67272_CR29","doi-asserted-by":"publisher","unstructured":"Bisong, E.: Google colaboratory. In Building Machine Learning and Deep Learning Models on Google Cloud Platform: A Comprehensive Guide for Beginners 59\u201364 Apress, Berkeley, CA (2019). https:\/\/doi.org\/10.1007\/978-1-4842-4470-8_7","DOI":"10.1007\/978-1-4842-4470-8_7"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-67272-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-67272-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-67272-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T03:37:38Z","timestamp":1788406658000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-67272-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,3]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["67272"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-67272-9","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,3]]},"assertion":[{"value":"23 May 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 August 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 September 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"27647"}}