{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T17:15:44Z","timestamp":1779297344656,"version":"3.51.4"},"reference-count":49,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T00:00:00Z","timestamp":1779235200000},"content-version":"vor","delay-in-days":19,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Bioinformatics is entering a new phase characterized by the integration of universal biological models and multi-agent systems to enable end-to-end scientific discoveries. This review argues that the next paradigm shift will go beyond traditional predictive models and generative artificial intelligence (AI) toward agentic AI: systems capable of planning, acting through tools, reflecting on results, and iterating until a goal is achieved. We first examine recent foundational models that produce transferable representations across omic modalities, such as scGPT, Nicheformer, and EpiAgent, and discuss their architectural choices, training regimes, and interpretability constraints. We then analyze biomedical agent frameworks through their main components (planning, action, reflection, and memory), highlighting representative systems such as ClinicalAgent and Biomni that operationalize these ideas in controlled environments. Next, we focus on hypothesis validation mechanisms, including retrieval-augmented generation for evidence grounding, sequential statistical testing, and benchmarking methodologies designed to quantify robustness and reproducibility. Finally, we summarize emerging applications in drug discovery and personalized medicine, from molecular literature analysis and protocol automation to drug repurposing for rare diseases and closed-loop synthesis. We conclude by outlining the main challenges ahead, namely hallucinations, interpretability, systemic biases, integration with clinical infrastructures, and regulatory and ethical requirements, and propose a roadmap for the development of scientific agents that are not only high-performing but also reliable, verifiable, and implementable in real biomedical contexts.<\/jats:p>","DOI":"10.1093\/bib\/bbag245","type":"journal-article","created":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T12:14:18Z","timestamp":1777637658000},"source":"Crossref","is-referenced-by-count":0,"title":["The next paradigm in bioinformatics: a review of multi-agent systems and foundational models for end-to-end scientific discovery"],"prefix":"10.1093","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9485-3877","authenticated-orcid":false,"given":"Francesco","family":"Branda","sequence":"first","affiliation":[{"name":"Unit of Medical Statistics and Molecular Epidemiology, Universit\u00e0 Campus Bio-Medico di Roma , Via \u00c1lvaro del Portillo, 21, 00128 Rome ,","place":["Italy"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5991-4052","authenticated-orcid":false,"given":"Mohamed M","family":"Ahmed","sequence":"additional","affiliation":[{"name":"Faculty of Medicine and Health Sciences, SIMAD University , Mogadishu 252 ,","place":["Somalia"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Massimo","family":"Ciccozzi","sequence":"additional","affiliation":[{"name":"Unit of Medical Statistics and Molecular Epidemiology, Universit\u00e0 Campus Bio-Medico di Roma , Via \u00c1lvaro del Portillo, 21, 00128 Rome ,","place":["Italy"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5542-2997","authenticated-orcid":false,"given":"Pietro Hiram","family":"Guzzi","sequence":"additional","affiliation":[{"name":"Department of Surgical and Medical Sciences, Magna Graecia University of Catanzaro , Viale Europa, 88100 Catanzaro ,","place":["Italy"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabio","family":"Scarpa","sequence":"additional","affiliation":[{"name":"Department of Biomedical Sciences, University of Sassari , Viale San Pietro, 07100 Sassari ,","place":["Italy"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2026,5,20]]},"reference":[{"key":"2026052012514690100_ref1","volume":"60","journal-title":"Communications of the ACM"},{"key":"2026052012514690100_ref2","doi-asserted-by":"publisher","first-page":"983","DOI":"10.1038\/nbt.4235","article-title":"A universal SNP and small-indel variant caller using deep neural networks","volume":"36","author":"Poplin","year":"2018","journal-title":"Nat Biotechnol"},{"key":"2026052012514690100_ref3","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":"2026052012514690100_ref4","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1186\/s13059-025-03881-3","article-title":"HAlign-G: rapid and low-memory multiple-genome aligner for large-scale closely related genomes","volume":"26","author":"Zhang","year":"2025","journal-title":"Genome Biol"},{"key":"2026052012514690100_ref5","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkaf533","article-title":"Enhanced RNA secondary structure prediction through integrative deep learning and structural context analysis","volume":"53","author":"Wang","year":"2025","journal-title":"Nucleic Acids Res"},{"key":"2026052012514690100_ref6","author":"Bahdanau","year":"2014"},{"key":"2026052012514690100_ref7","author":"Bommasani","year":"2021"},{"key":"2026052012514690100_ref8","doi-asserted-by":"publisher","first-page":"e2016239118","DOI":"10.1073\/pnas.2016239118","article-title":"Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences","volume":"118","author":"Rives","year":"2021","journal-title":"Proc Natl Acad Sci"},{"key":"2026052012514690100_ref9","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly accurate protein structure prediction with AlphaFold","volume":"596","author":"Jumper","year":"2021","journal-title":"nature."},{"key":"2026052012514690100_ref10","doi-asserted-by":"publisher","first-page":"616","DOI":"10.1038\/s41586-023-06139-9","article-title":"Transfer learning enables predictions in network biology","volume":"618","author":"Theodoris","year":"2023","journal-title":"Nature."},{"key":"2026052012514690100_ref11","first-page":"528","volume-title":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics","author":"Zhang","year":"2025"},{"key":"2026052012514690100_ref12","doi-asserted-by":"publisher","DOI":"10.1186\/s12915-026-02557-z","article-title":"HiGLDP: a hierarchical graph neural network for predicting lncRNA-disease associations through multi-omic integration","volume":"24","author":"Wang","year":"2026","journal-title":"BMC Biol"},{"key":"2026052012514690100_ref13","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1007\/s43657-022-00089-4","article-title":"Phenomic studies on diseases: potential and challenges","volume":"3","author":"Ying","year":"2023","journal-title":"Phenomics"},{"key":"2026052012514690100_ref14","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1186\/s41038-018-0137-9","article-title":"Burn image segmentation based on mask regions with convolutional neural network deep learning framework: more accurate and more convenient","volume":"7","author":"Jiao","year":"2019","journal-title":"Burns Trauma"},{"key":"2026052012514690100_ref15","doi-asserted-by":"publisher","first-page":"7932","DOI":"10.1109\/JBHI.2024.3457271","article-title":"Integrative graph-based framework for predicting circRNA drug resistance using disease contextualization and deep learning","volume":"29","author":"Wang","year":"2024","journal-title":"IEEE J Biomed Health Inform"},{"key":"2026052012514690100_ref16","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1007\/s12539-024-00603-4","article-title":"A review of the application of spatial transcriptomics in neuroscience","volume":"16","author":"Zhang","year":"2024","journal-title":"Interdiscip Sci: Comput Life Sci"},{"key":"2026052012514690100_ref17","volume-title":"The Eleventh International Conference on Learning Representations","author":"Yao","year":"2022"},{"key":"2026052012514690100_ref18","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Adv Neural Inf Proces Syst"},{"key":"2026052012514690100_ref19","author":"Baker"},{"key":"2026052012514690100_ref20","doi-asserted-by":"publisher","first-page":"1470","DOI":"10.1038\/s41592-024-02201-0","article-title":"scGPT: toward building a foundation model for single-cell multi-omics using generative AI","volume":"21","author":"Cui","year":"2024","journal-title":"Nat Methods"},{"key":"2026052012514690100_ref21","doi-asserted-by":"publisher","first-page":"2525","DOI":"10.1038\/s41592-025-02814-z","article-title":"Nicheformer: a foundation model for single-cell and spatial omics","volume":"22","author":"Tejada-Lapuerta","year":"2025","journal-title":"Nat Methods"},{"key":"2026052012514690100_ref23","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1186\/s13059-025-03574-x","article-title":"Zero-shot evaluation reveals limitations of single-cell foundation models","volume":"26","author":"Kedzierska","year":"2025","journal-title":"Genome Biol"},{"key":"2026052012514690100_ref24","doi-asserted-by":"publisher","first-page":"593","DOI":"10.1038\/s41580-024-00756-6","article-title":"Harnessing the deep learning power of foundation models in single-cell omics","volume":"25","author":"Ma","year":"2024","journal-title":"Nat Rev Mol Cell Biol"},{"key":"2026052012514690100_ref29","doi-asserted-by":"publisher","first-page":"730","DOI":"10.1038\/s41467-025-67481-2","article-title":"scDrugMap: benchmarking large foundation models for drug response prediction","volume":"17","author":"Wang","year":"2025","journal-title":"Nat Commun"},{"key":"2026052012514690100_ref49","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1038\/s41592-021-01336-8","article-title":"Benchmarking atlas-level data integration in single-cell genomics","volume":"19","author":"Luecken","year":"2022","journal-title":"Nat Methods"},{"key":"2026052012514690100_ref26","doi-asserted-by":"publisher","first-page":"102374","DOI":"10.1016\/j.xcrm.2025.102374","article-title":"A foundational architecture for AI agents in healthcare","volume":"6","author":"Liu","year":"2025","journal-title":"Cell Rep Med"},{"key":"2026052012514690100_ref35","volume-title":"First Conference on Language Modeling","author":"Wu","year":"2024"},{"key":"2026052012514690100_ref37","volume-title":"The Twelfth International Conference on Learning Representations","author":"Hong","year":"2024"},{"key":"2026052012514690100_ref32","author":"ElSayed","year":"2025"},{"key":"2026052012514690100_ref38","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1038\/s42256-024-00832-8","article-title":"Augmenting large language models with chemistry tools","volume":"6","author":"Bran","year":"2024","journal-title":"Nat Mach Intell"},{"key":"2026052012514690100_ref39","doi-asserted-by":"publisher","first-page":"570","DOI":"10.1038\/s41586-023-06792-0","article-title":"Autonomous chemical research with large language models","volume":"624","author":"Boiko","year":"2023","journal-title":"Nature"},{"key":"2026052012514690100_ref34","doi-asserted-by":"publisher","first-page":"160018","DOI":"10.1038\/sdata.2016.18","article-title":"The FAIR guiding principles for scientific data management and stewardship: comment","volume":"3","author":"Wilkinson","year":"2016","journal-title":"Sci Data"},{"key":"2026052012514690100_ref44","author":"Seal","year":"2025"},{"key":"2026052012514690100_ref46","volume-title":"An Auditable Agent Platform for Automated Molecular Optimisation","author":"\u00dcnl\u00fc","year":"2025"},{"key":"2026052012514690100_ref33","doi-asserted-by":"publisher","first-page":"899","DOI":"10.1093\/jamia\/ocv189","article-title":"SMART on FHIR: a standards-based, interoperable apps platform for electronic health records","volume":"23","author":"Mandel","year":"2016","journal-title":"J Am Med Inform Assoc"},{"key":"2026052012514690100_ref22","doi-asserted-by":"publisher","first-page":"2169","DOI":"10.1038\/s12276-025-01547-5","article-title":"Single-cell foundation models: bringing artificial intelligence into cell biology","volume":"57","author":"Baek","year":"2025","journal-title":"Exp Mol Med"},{"key":"2026052012514690100_ref25","doi-asserted-by":"publisher","first-page":"170101","DOI":"10.1007\/s11432-024-4466-3","article-title":"Large language models transform biological research: from architecture to utilization","volume":"68","author":"Wang","year":"2025","journal-title":"SCIENCE CHINA Inf Sci"},{"key":"2026052012514690100_ref27","doi-asserted-by":"publisher","first-page":"e0342182","DOI":"10.1371\/journal.pone.0342182","article-title":"Artificial intelligence agents in healthcare research: A scoping review","volume":"21","author":"Njei","year":"2026","journal-title":"PLoS One"},{"key":"2026052012514690100_ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-025-11471-9","article-title":"From language to action: a review of large language models as autonomous agents and tool users","volume":"59","author":"Chowa","year":"2026","journal-title":"Artif Intell Rev"},{"key":"2026052012514690100_ref30","doi-asserted-by":"publisher","first-page":"1176","DOI":"10.1186\/s12967-025-07091-0","article-title":"Transformative advances in single-cell omics: a comprehensive review of foundation models, multimodal integration and computational ecosystems","volume":"23","author":"Yiu","year":"2025","journal-title":"J Transl Med"},{"key":"2026052012514690100_ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-025-11458-6","article-title":"Agentic AI systems in the age of generative models: architectures, cloud scalability, and real-world applications","volume":"59","author":"Alva","year":"2026","journal-title":"Artif Intell Rev"},{"key":"2026052012514690100_ref36","first-page":"51991","article-title":"Camel: communicative agents for\" mind\" exploration of large language model society","volume":"36","author":"Li","year":"2023","journal-title":"Adv Neural Inf Proces Syst"},{"key":"2026052012514690100_ref40","doi-asserted-by":"publisher","first-page":"1053","DOI":"10.1038\/s41592-018-0229-2","article-title":"Deep generative modeling for single-cell transcriptomics","volume":"15","author":"Lopez","year":"2018","journal-title":"Nat Methods"},{"key":"2026052012514690100_ref41","doi-asserted-by":"publisher","first-page":"1289","DOI":"10.1038\/s41592-019-0619-0","article-title":"Fast, sensitive and accurate integration of single-cell data with harmony","volume":"16","author":"Korsunsky","year":"2019","journal-title":"Nat Methods"},{"key":"2026052012514690100_ref42","doi-asserted-by":"publisher","first-page":"1271","DOI":"10.3390\/ph18091271","article-title":"Artificial intelligence in small-molecule drug discovery: a critical review of methods, applications, and real-world outcomes","volume":"18","author":"Niazi","year":"2025","journal-title":"Pharmaceuticals"},{"key":"2026052012514690100_ref43","doi-asserted-by":"publisher","first-page":"23889","DOI":"10.1021\/acsomega.5c00549","article-title":"AI-driven drug discovery: a comprehensive review","volume":"10","author":"Ferreira","year":"2025","journal-title":"ACS Omega"},{"key":"2026052012514690100_ref45","doi-asserted-by":"publisher","first-page":"104605","DOI":"10.1016\/j.drudis.2026.104605","article-title":"Democratising real-world drug discovery through agentic AI","volume":"31","author":"He","year":"2026","journal-title":"Drug Discov Today"},{"key":"2026052012514690100_ref47","first-page":"6956","article-title":"MADD: multi-agent drug discovery orchestra","volume":"2025","author":"Solovev","year":"2025","journal-title":"In Findings of the Association for Computational Linguistics: EMNLP"},{"key":"2026052012514690100_ref48","doi-asserted-by":"publisher","first-page":"894","DOI":"10.3390\/info16100894","article-title":"Large language model agents for biomedicine: a comprehensive review of methods, evaluations, challenges, and future directions","volume":"16","author":"Xu","year":"2025","journal-title":"Information"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/3\/bbag245\/68346789\/bbag245.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/3\/bbag245\/68346789\/bbag245.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T16:51:54Z","timestamp":1779295914000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbag245\/8688274"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":49,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,5,4]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbag245","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,5]]},"published":{"date-parts":[[2026,5]]},"article-number":"bbag245"}}