{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T04:25:29Z","timestamp":1793939129043,"version":"4.8.0"},"reference-count":86,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T00:00:00Z","timestamp":1789689600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002322","name":"Coordination for the improvement of Higher Education Personnel","doi-asserted-by":"publisher","award":["Finance Code 001"],"award-info":[{"award-number":["Finance Code 001"]}],"id":[{"id":"10.13039\/501100002322","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004263","name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado do Rio Grande do Sul","doi-asserted-by":"publisher","award":["23\/2551-0001894-2"],"award-info":[{"award-number":["23\/2551-0001894-2"]}],"id":[{"id":"10.13039\/501100004263","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004263","name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado do Rio Grande do Sul","doi-asserted-by":"publisher","award":["24\/2551-0001392-0"],"award-info":[{"award-number":["24\/2551-0001392-0"]}],"id":[{"id":"10.13039\/501100004263","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003593","name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","doi-asserted-by":"publisher","award":["314082\/2021-2"],"award-info":[{"award-number":["314082\/2021-2"]}],"id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003593","name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","doi-asserted-by":"publisher","award":["404319\/2024-6"],"award-info":[{"award-number":["404319\/2024-6"]}],"id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003593","name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","doi-asserted-by":"publisher","award":["440279\/2022-4"],"award-info":[{"award-number":["440279\/2022-4"]}],"id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003593","name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","doi-asserted-by":"publisher","award":["408154\/2022-5"],"award-info":[{"award-number":["408154\/2022-5"]}],"id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computational Biology and Chemistry"],"published-print":{"date-parts":[[2027,2]]},"DOI":"10.1016\/j.compbiolchem.2026.109409","type":"journal-article","created":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T15:30:44Z","timestamp":1789745444000},"page":"109409","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P1","title":["Foundation models and taxonomy inference for metagenomics: A practical review"],"prefix":"10.1016","volume":"126","author":[{"given":"Andrey Felipe","family":"Schoier","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"\u00cdcaro Maia Santos","family":"de Castro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8534-3480","authenticated-orcid":false,"given":"Marcio","family":"Dorn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"4","key":"10.1016\/j.compbiolchem.2026.109409_b1","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1080\/15257770.2019.1645851","article-title":"Bacterial classification with convolutional neural networks based on different data reduction layers","volume":"39","author":"Abd-Alhalem","year":"2020","journal-title":"Nucleosides, Nucleotides Nucleic Acids"},{"key":"10.1016\/j.compbiolchem.2026.109409_b2","series-title":"Fast and accurate taxonomic domain assignment of short metagenomic reads using BBERT","author":"Alekhin","year":"2025"},{"issue":"3","key":"10.1016\/j.compbiolchem.2026.109409_b3","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1016\/S0022-2836(05)80360-2","article-title":"Basic local alignment search tool","volume":"215","author":"Altschul","year":"1990","journal-title":"J. Mol. Biol."},{"key":"10.1016\/j.compbiolchem.2026.109409_b4","series-title":"BarcodeBERT: Transformers for biodiversity analysis","author":"Arias","year":"2023"},{"issue":"18","key":"10.1016\/j.compbiolchem.2026.109409_b5","first-page":"4264","article-title":"Identification of bacteriophage genome sequences with representation learning","volume":"38","author":"Bai","year":"2022","journal-title":"Bioinform. (Oxford, England)"},{"key":"10.1016\/j.compbiolchem.2026.109409_b6","series-title":"Evaluating the Effectiveness of Parameter-Efficient Fine-Tuning in Genomic Classification Tasks","author":"Berman","year":"2025"},{"key":"10.1016\/j.compbiolchem.2026.109409_b7","doi-asserted-by":"crossref","first-page":"1633","DOI":"10.1038\/s41587-023-01688-w","article-title":"Extending and improving metagenomic taxonomic profiling with uncharacterized species using MetaPhlAn 4","volume":"41","author":"Blanco-M\u00edguez","year":"2023","journal-title":"Nature Biotechnol."},{"key":"10.1016\/j.compbiolchem.2026.109409_b8","series-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"10.1016\/j.compbiolchem.2026.109409_b9","first-page":"1877","article-title":"Language models are few-shot learners","volume":"vol. 33","author":"Brown","year":"2020"},{"key":"10.1016\/j.compbiolchem.2026.109409_b10","series-title":"Revisiting K-mer Profile for Effective and Scalable Genome Representation Learning","author":"Celikkanat","year":"2024"},{"issue":"6","key":"10.1016\/j.compbiolchem.2026.109409_b11","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1038\/s41576-019-0113-7","article-title":"Clinical metagenomics","volume":"20","author":"Chiu","year":"2019","journal-title":"Nature Rev. Genet."},{"issue":"1","key":"10.1016\/j.compbiolchem.2026.109409_b12","first-page":"45","article-title":"Genomic language models: opportunities, limitations, and future directions","volume":"7","author":"Consens","year":"2025","journal-title":"Nat. Mach. Intell."},{"issue":"1","key":"10.1016\/j.compbiolchem.2026.109409_b13","first-page":"55","article-title":"The nucleotide transformer: Building and evaluating robust foundation models for genomics","volume":"22","author":"Dalla-Torre","year":"2025","journal-title":"Nature Methods"},{"issue":"8","key":"10.1016\/j.compbiolchem.2026.109409_b14","doi-asserted-by":"crossref","first-page":"1426","DOI":"10.1038\/s41559-025-02752-1","article-title":"A composite universal DNA signature for the tree of life","volume":"9","author":"de Medeiros","year":"2025","journal-title":"Nat. Ecol. Evol."},{"issue":"1","key":"10.1016\/j.compbiolchem.2026.109409_b15","doi-asserted-by":"crossref","first-page":"6905","DOI":"10.1038\/s41467-025-61684-3","article-title":"PhyloTune: An efficient method to accelerate phylogenetic updates using a pretrained DNA language model","volume":"16","author":"Deng","year":"2025","journal-title":"Nat. Commun."},{"key":"10.1016\/j.compbiolchem.2026.109409_b16","series-title":"Proceedings of NAACL-HLT","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"issue":"1\u20132","key":"10.1016\/j.compbiolchem.2026.109409_b17","first-page":"109","article-title":"Metagenomics for mining new genetic resources of microbial communities","volume":"16","author":"Ferrer","year":"2009","journal-title":"J. Mol. Microbiol. Biotechnol."},{"issue":"2","key":"10.1016\/j.compbiolchem.2026.109409_b18","doi-asserted-by":"crossref","first-page":"gkae1310","DOI":"10.1093\/nar\/gkae1310","article-title":"GENA-LM: A family of open-source foundational DNA language models for long sequences","volume":"53","author":"Fishman","year":"2025","journal-title":"Nucleic Acids Res."},{"issue":"1","key":"10.1016\/j.compbiolchem.2026.109409_b19","doi-asserted-by":"crossref","first-page":"vbaf257","DOI":"10.1093\/bioadv\/vbaf257","article-title":"ICCTax: a hierarchical taxonomic classifier for metagenomic sequences on a large language model","volume":"5","author":"Gao","year":"2025","journal-title":"Bioinform. Adv."},{"key":"10.1016\/j.compbiolchem.2026.109409_b20","series-title":"BarcodeMamba: State Space Models for Biodiversity Analysis","author":"Gao","year":"2024"},{"key":"10.1016\/j.compbiolchem.2026.109409_b21","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1038\/nrg.2017.88","article-title":"Towards a genomics-informed, real-time, global pathogen surveillance system","volume":"19","author":"Gardy","year":"2018","journal-title":"Nature Rev. Genet."},{"key":"10.1016\/j.compbiolchem.2026.109409_b22","series-title":"META2: Memory-efficient taxonomic classification and abundance estimation for metagenomics with deep learning","author":"Georgiou","year":"2019"},{"issue":"6","key":"10.1016\/j.compbiolchem.2026.109409_b23","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1038\/nrg.2016.49","article-title":"Coming of age: ten years of next-generation sequencing technologies","volume":"17","author":"Goodwin","year":"2016","journal-title":"Nature Rev. Genet."},{"issue":"6","key":"10.1016\/j.compbiolchem.2026.109409_b24","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbad408","article-title":"PhaGenus: genus-level classification of bacteriophages using a Transformer model","volume":"24","author":"Guan","year":"2023","journal-title":"Brief. Bioinform."},{"key":"10.1016\/j.compbiolchem.2026.109409_b25","series-title":"2022 IEEE International Conference on Big Data and Smart Computing (IEEE BIGCOMP 2022)","first-page":"374","article-title":"Transformer-based embedding applied to classify bacterial species using sequencing reads","author":"Gwak","year":"2022"},{"issue":"4","key":"10.1016\/j.compbiolchem.2026.109409_b26","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbac204","article-title":"ViBE: a hierarchical BERT model to identify eukaryotic viruses using metagenome sequencing data","volume":"23","author":"Gwak","year":"2022","journal-title":"Brief. Bioinform."},{"issue":"1","key":"10.1016\/j.compbiolchem.2026.109409_b27","doi-asserted-by":"crossref","DOI":"10.1186\/s13059-025-03861-7","article-title":"DeepCOI: a large language model-driven framework for fast and accurate taxonomic assignment in animal metabarcoding","volume":"26","author":"Gwak","year":"2025","journal-title":"Genome Biol."},{"issue":"4","key":"10.1016\/j.compbiolchem.2026.109409_b28","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1128\/MMBR.68.4.669-685.2004","article-title":"Metagenomics: application of genomics to uncultured microorganisms","volume":"68","author":"Handelsman","year":"2004","journal-title":"Microbiol. Mol. Biol. Rev."},{"issue":"1","key":"10.1016\/j.compbiolchem.2026.109409_b29","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbaf041","article-title":"ViTax: adaptive hierarchical viral taxonomy classification with a taxonomy belief tree on a foundation model","volume":"26","author":"He","year":"2025","journal-title":"Briefings Bioinform."},{"issue":"1512","key":"10.1016\/j.compbiolchem.2026.109409_b30","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1098\/rspb.2002.2218","article-title":"Biological identifications through DNA barcodes","volume":"270","author":"Hebert","year":"2003","journal-title":"Proc. R. Soc. B: Biol. Sci."},{"key":"10.1016\/j.compbiolchem.2026.109409_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.117972","article-title":"BERT contextual embeddings for taxonomic classification of bacterial DNA sequences","volume":"208","author":"Helaly","year":"2022","journal-title":"Expert Syst. Appl."},{"issue":"24","key":"10.1016\/j.compbiolchem.2026.109409_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.cell.2024.09.027","article-title":"Using artificial intelligence to document the hidden RNA virosphere","volume":"187","author":"Hou","year":"2024","journal-title":"Cell"},{"key":"10.1016\/j.compbiolchem.2026.109409_b33","series-title":"Parameter-efficient transfer learning for NLP","author":"Houlsby","year":"2019"},{"key":"10.1016\/j.compbiolchem.2026.109409_b34","series-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"issue":"6","key":"10.1016\/j.compbiolchem.2026.109409_b35","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1004957","article-title":"MEGAN community edition - interactive exploration and analysis of large-scale microbiome sequencing data","volume":"12","author":"Huson","year":"2016","journal-title":"PLoS Comput. Biol."},{"key":"10.1016\/j.compbiolchem.2026.109409_b36","first-page":"164","article-title":"Sim2Real for Metagenomes: Accelerating Animal Diagnostics with Adversarial Co-training","volume":"vol. 12712 LNAI","author":"Indla","year":"2021"},{"key":"10.1016\/j.compbiolchem.2026.109409_b37","series-title":"CoViT: Real-time phylogenetics for the SARS-CoV-2 pandemic using Vision Transformers","author":"Jahshan","year":"2022"},{"issue":"15","key":"10.1016\/j.compbiolchem.2026.109409_b38","doi-asserted-by":"crossref","first-page":"2112","DOI":"10.1093\/bioinformatics\/btab083","article-title":"DNABERT: Pre-trained bidirectional encoder representations from transformers model for DNA-language in genome","volume":"37","author":"Ji","year":"2021","journal-title":"Bioinformatics"},{"key":"10.1016\/j.compbiolchem.2026.109409_b39","series-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"issue":"12","key":"10.1016\/j.compbiolchem.2026.109409_b40","doi-asserted-by":"crossref","first-page":"1721","DOI":"10.1101\/gr.210641.116","article-title":"Centrifuge: Rapid and sensitive classification of metagenomic sequences","volume":"26","author":"Kim","year":"2016","journal-title":"Genome Res."},{"key":"10.1016\/j.compbiolchem.2026.109409_b41","series-title":"Binning meets taxonomy: TaxVAMB improves metagenome binning using bi-modal variational autoencoder","author":"Kutuzova","year":"2024"},{"issue":"4","key":"10.1016\/j.compbiolchem.2026.109409_b42","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1038\/nmeth.1923","article-title":"Fast gapped-read alignment with bowtie 2","volume":"9","author":"Langmead","year":"2012","journal-title":"Nature Methods"},{"key":"10.1016\/j.compbiolchem.2026.109409_b43","series-title":"Machine learning-based approach KEVOLVE efficiently identifies SARS-CoV-2 variant-specific genomic signatures","author":"Lebatteux","year":"2022"},{"issue":"14","key":"10.1016\/j.compbiolchem.2026.109409_b44","doi-asserted-by":"crossref","first-page":"1754","DOI":"10.1093\/bioinformatics\/btp324","article-title":"Fast and accurate short read alignment with burrows\u2013wheeler transform","volume":"25","author":"Li","year":"2009","journal-title":"Bioinformatics"},{"key":"10.1016\/j.compbiolchem.2026.109409_b45","series-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics","first-page":"4582","article-title":"Prefix-tuning: Optimizing continuous prompts for generation","author":"Li","year":"2021"},{"key":"10.1016\/j.compbiolchem.2026.109409_b46","series-title":"METAGENE-1: Metagenomic Foundation Model for Pandemic Monitoring","author":"Liu","year":"2025"},{"key":"10.1016\/j.compbiolchem.2026.109409_b47","doi-asserted-by":"crossref","DOI":"10.7717\/peerj-cs.104","article-title":"Bracken: Estimating species abundance in metagenomics data","volume":"3","author":"Lu","year":"2017","journal-title":"PeerJ Comput. Sci."},{"key":"10.1016\/j.compbiolchem.2026.109409_b48","article-title":"Euktect: Enhanced eukaryotic sequence detection and classification in metagenomes via the DNA language model","author":"Lu","year":"2025","journal-title":"Res. Sq."},{"key":"10.1016\/j.compbiolchem.2026.109409_b49","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1146\/annurev.genom.9.081307.164359","article-title":"Next-generation DNA sequencing methods","volume":"9","author":"Mardis","year":"2008","journal-title":"Annu. Rev. Genom. Hum. Genet."},{"key":"10.1016\/j.compbiolchem.2026.109409_b50","doi-asserted-by":"crossref","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."},{"issue":"4","key":"10.1016\/j.compbiolchem.2026.109409_b51","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1038\/s41592-022-01431-4","article-title":"Critical assessment of metagenome interpretation: the second round of challenges","volume":"19","author":"Meyer","year":"2022","journal-title":"Nature Methods"},{"key":"10.1016\/j.compbiolchem.2026.109409_b52","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1038\/s41586-023-05881-4","article-title":"Foundation models for generalist medical AI","volume":"616","author":"Moor","year":"2023","journal-title":"Nature"},{"key":"10.1016\/j.compbiolchem.2026.109409_b53","series-title":"Scalable Pathogen Detection from Next Generation DNA Sequencing with Deep Learning","author":"Narayanan","year":"2022"},{"key":"10.1016\/j.compbiolchem.2026.109409_b54","series-title":"Genome Sequence Classification for Animal Diagnostics with Graph Representations and Deep Neural Networks","author":"Narayanan","year":"2020"},{"key":"10.1016\/j.compbiolchem.2026.109409_b55","series-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems (NeurIPS)","first-page":"1872:1","article-title":"HyenaDNA: Long-range genomic sequence modeling at single nucleotide resolution","author":"Nguyen","year":"2023"},{"key":"10.1016\/j.compbiolchem.2026.109409_b56","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1186\/s13059-016-0997-x","article-title":"Mash: fast genome and metagenome distance estimation using MinHash","volume":"17","author":"Ondov","year":"2016","journal-title":"Genome Biol."},{"key":"10.1016\/j.compbiolchem.2026.109409_b57","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1186\/s12864-015-1419-2","article-title":"CLARK: fast and accurate classification of metagenomic and genomic sequences using discriminative k-mers","volume":"16","author":"Ounit","year":"2015","journal-title":"BMC Genomics"},{"key":"10.1016\/j.compbiolchem.2026.109409_b58","doi-asserted-by":"crossref","first-page":"n71","DOI":"10.1136\/bmj.n71","article-title":"The PRISMA 2020 statement: an updated guideline for reporting systematic reviews","volume":"372","author":"Page","year":"2021","journal-title":"BMJ"},{"issue":"S, SI","key":"10.1016\/j.compbiolchem.2026.109409_b59","doi-asserted-by":"crossref","first-page":"i21","DOI":"10.1093\/bioinformatics\/btad209","article-title":"SemiBin2: self-supervised contrastive learning leads to better MAGs for short- and long-read sequencing","volume":"39","author":"Pan","year":"2023","journal-title":"Bioinformatics"},{"issue":"12","key":"10.1016\/j.compbiolchem.2026.109409_b60","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btae704","article-title":"ViraLM: empowering virus discovery through the genome foundation model","volume":"40","author":"Peng","year":"2024","journal-title":"Bioinformatics"},{"issue":"4","key":"10.1016\/j.compbiolchem.2026.109409_b61","doi-asserted-by":"crossref","DOI":"10.1016\/j.slast.2024.100147","article-title":"Assessment and classification of COVID-19 DNA sequence using pairwise features concatenation from multi-transformer and deep features with machine learning models","volume":"29","author":"Qayyum","year":"2024","journal-title":"SLAS Technol."},{"key":"10.1016\/j.compbiolchem.2026.109409_b62","series-title":"Context-Aware Regularization with Markovian Integration for Attention-Based Nucleotide Analysis","author":"Refahi","year":"2025"},{"issue":"1","key":"10.1016\/j.compbiolchem.2026.109409_b63","doi-asserted-by":"crossref","first-page":"517","DOI":"10.1038\/s42003-025-07902-6","article-title":"Enhancing nucleotide sequence representations in genomic analysis with contrastive optimization","volume":"8","author":"Refahi","year":"2025","journal-title":"Commun. Biol."},{"key":"10.1016\/j.compbiolchem.2026.109409_b64","series-title":"2023 IEEE Signal Processing in Medicine and Biology Symposium","first-page":"1","article-title":"Leveraging Large Language Models for Metagenomic Analysis","author":"Refahi","year":"2023"},{"key":"10.1016\/j.compbiolchem.2026.109409_b65","series-title":"Identifying viruses from metagenomic data by deep learning","author":"Ren","year":"2018"},{"issue":"1","key":"10.1016\/j.compbiolchem.2026.109409_b66","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1186\/s13643-020-01542-z","article-title":"PRISMA-S: an extension to the PRISMA statement for reporting literature searches in systematic reviews","volume":"10","author":"Rethlefsen","year":"2021","journal-title":"Syst. Rev."},{"issue":"8","key":"10.1016\/j.compbiolchem.2026.109409_b67","doi-asserted-by":"crossref","DOI":"10.1111\/1755-0998.14006","article-title":"MycoAI: Fast and accurate taxonomic classification for fungal ITS sequences","volume":"24","author":"Romeijn","year":"2024","journal-title":"Mol. Ecol. Resour."},{"issue":"4","key":"10.1016\/j.compbiolchem.2026.109409_b68","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1109\/TNB.2010.2081375","article-title":"Comparison of Statistical Methods to Classify Environmental Genomic Fragments","volume":"9","author":"Rosen","year":"2010","journal-title":"IEEE Trans. Nanobioscience"},{"key":"10.1016\/j.compbiolchem.2026.109409_b69","series-title":"MetagenBERT: a transformer architecture using foundational DNA read embedding models to enhance disease classification","author":"Roy","year":"2025"},{"issue":"11","key":"10.1016\/j.compbiolchem.2026.109409_b70","doi-asserted-by":"crossref","first-page":"1063","DOI":"10.1038\/nmeth.4458","article-title":"Critical assessment of metagenome interpretation\u2014a benchmark of metagenomics software","volume":"14","author":"Sczyrba","year":"2017","journal-title":"Nature Methods"},{"key":"10.1016\/j.compbiolchem.2026.109409_b71","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1016\/j.ymeth.2020.05.018","article-title":"CHEER: HierarCHical taxonomic classification for viral mEtagEnomic data via deep leaRning","volume":"189","author":"Shang","year":"2021","journal-title":"Methods (San Diego, Calif.)"},{"issue":"4","key":"10.1016\/j.compbiolchem.2026.109409_b72","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbac258","article-title":"Accurate identification of bacteriophages from metagenomic data using Transformer","volume":"23","author":"Shang","year":"2022","journal-title":"Briefings Bioinform."},{"issue":"7676","key":"10.1016\/j.compbiolchem.2026.109409_b73","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1038\/nature24286","article-title":"DNA sequencing at 40: past, present and future","volume":"550","author":"Shendure","year":"2017","journal-title":"Nature"},{"key":"10.1016\/j.compbiolchem.2026.109409_b74","series-title":"Improved metagenomic binning with transformers","author":"Shenker-Tauris","year":"2022"},{"issue":"7","key":"10.1016\/j.compbiolchem.2026.109409_b75","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pbio.1002195","article-title":"Big data: astronomical or genomical?","volume":"13","author":"Stephens","year":"2015","journal-title":"PLoS Biol."},{"issue":"8","key":"10.1016\/j.compbiolchem.2026.109409_b76","doi-asserted-by":"crossref","first-page":"1789","DOI":"10.1111\/j.1365-294X.2012.05542.x","article-title":"Environmental DNA","volume":"21","author":"Taberlet","year":"2012","journal-title":"Mol. Ecol."},{"issue":"7681","key":"10.1016\/j.compbiolchem.2026.109409_b77","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1038\/nature24621","article-title":"A communal catalogue reveals earth\u2019s multiscale microbial diversity","volume":"551","author":"Thompson","year":"2017","journal-title":"Nature"},{"issue":"6","key":"10.1016\/j.compbiolchem.2026.109409_b78","doi-asserted-by":"crossref","first-page":"616","DOI":"10.1016\/j.copbio.2009.09.010","article-title":"Functional metagenomics for enzyme discovery: challenges to efficient screening","volume":"20","author":"Uchiyama","year":"2009","journal-title":"Curr. Opin. Biotechnol."},{"key":"10.1016\/j.compbiolchem.2026.109409_b79","series-title":"Advances in Neural Information Processing Systems (NeurIPS)","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.compbiolchem.2026.109409_b80","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1016\/j.future.2024.07.025","article-title":"TransGINmer: Identifying viral sequences from metagenomes with self-attention and Graph Isomorphism Network","volume":"161","author":"Wang","year":"2024","journal-title":"Future Gener. Comput. Syst.- Int. J. Escience"},{"issue":"4","key":"10.1016\/j.compbiolchem.2026.109409_b81","doi-asserted-by":"crossref","first-page":"548","DOI":"10.7326\/ANNALS-25-02104","article-title":"QUADAS-3: A revised tool for the quality assessment of diagnostic test accuracy studies","volume":"179","author":"Whiting","year":"2026","journal-title":"Ann. Intern. Med."},{"issue":"3","key":"10.1016\/j.compbiolchem.2026.109409_b82","doi-asserted-by":"crossref","first-page":"lqad082","DOI":"10.1093\/nargab\/lqad082","article-title":"MetaTransformer: deep metagenomic sequencing read classification using self-attention models","volume":"5","author":"Wichmann","year":"2023","journal-title":"NAR Genom. Bioinform."},{"issue":"1","key":"10.1016\/j.compbiolchem.2026.109409_b83","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1186\/s13059-019-1891-0","article-title":"Improved metagenomic analysis with kraken 2","volume":"20","author":"Wood","year":"2019","journal-title":"Genome Biol."},{"key":"10.1016\/j.compbiolchem.2026.109409_b84","series-title":"Proceedings - 2025 IEEE International Conference on Bioinformatics and Biomedicine","first-page":"7237","article-title":"Evo2-Virus: Ultra-Short Viral Sequence Identification with EVO2","author":"Xu","year":"2025"},{"key":"10.1016\/j.compbiolchem.2026.109409_b85","series-title":"Converting transformers into DGNNs form","author":"Zhang","year":"2025"},{"key":"10.1016\/j.compbiolchem.2026.109409_b86","unstructured":"Zhou, Z., Ping, W., Li, P., Peng, Y., Bian, J., Lu, Y., Yu, D., Chen, W., Wang, S., Liu, C., Li, Z., Liu, Q., Wang, Z., Li, X., Zhang, Y., Liu, X., Liu, Y., Duan, N., Chen, W., 2024. DNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species DNA Language. In: International Conference on Learning Representations. ICLR."}],"container-title":["Computational Biology and Chemistry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1476927126005360?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1476927126005360?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T03:36:31Z","timestamp":1793936191000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1476927126005360"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,2]]},"references-count":86,"alternative-id":["S1476927126005360"],"URL":"https:\/\/doi.org\/10.1016\/j.compbiolchem.2026.109409","relation":{},"ISSN":["1476-9271"],"issn-type":[{"value":"1476-9271","type":"print"}],"subject":[],"published":{"date-parts":[[2027,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Foundation models and taxonomy inference for metagenomics: A practical review","name":"articletitle","label":"Article Title"},{"value":"Computational Biology and Chemistry","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.compbiolchem.2026.109409","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"109409"}}