Viral Sentry AI: Automated Zoonotic Surveillance and Drug Repurposing Agent

UDC.coleccionInvestigación
UDC.departamentoCiencias da Computación e Tecnoloxías da Información
UDC.grupoInvRedes de Neuronas Artificiais e Sistemas Adaptativos -Informática Médica e Diagnóstico Radiolóxico (RNASA - IMEDIR)
UDC.institutoCentroCITIC - Centro de Investigación de Tecnoloxías da Información e da Comunicación
UDC.issue1
UDC.journalTitleBiology Methods and Protocols
UDC.volume11
dc.contributor.authorMunteanu, Cristian-Robert
dc.contributor.authorVázquez-Naya, José
dc.contributor.authorTejera, Eduardo
dc.date.accessioned2026-06-25T07:42:45Z
dc.date.available2026-06-25T07:42:45Z
dc.date.issued2026
dc.descriptionFinanciado para publicación en acceso aberto: Universidade da Coruña/CISUG Data: Web server: https://muntisa.github.io/virsentai Source code: https://github.com/muntisa/virsentai Code release v1.1.0: https://doi.org/10.5281/zenodo.17445222 Dataset: https://doi.org/10.5281/zenodo.20314175 Virsentai model (ver. 3): https://doi.org/10.5281/zenodo.20314458
dc.description.abstract[Abstract]: Zoonotic viruses capable of jumping from animal reservoirs into human populations represent a persistent and unpredictable menace to global health. To confront this challenge, we developed Viral Sentry AI, an autonomous agent designed to close the gap between viral emergence and therapeutic response. Unlike static analysis tools, Viral Sentry AI operates as a continuous sentinel, automatically scanning the National Center for Biotechnology Information public databases for new viral genomes and executing a three-stage agentic surveillance workflow, with distinct, specialized artificial intelligence architectures for generated text, macromolecule sequences, and drug chemical data. First, the system is using a Large Language Model (Gemma4) to parse unstructured submission records and extract the host information if it is not available in the dedicated field. In the second stage, the system employs a novel deep-learning topology, virsentai-v3-hyena-dna-16k, a fine-tuned HyenaDNA model capable of processing complete viral genomes up to 160 000 bases. This architecture captures subtle, long-range genomic dependencies to predict human infectivity with high precision. Upon predicting the possible human infection of the scanned viruses, the agent autonomously triggers a downstream therapeutic module as the stage three. It extracts National Center for Biotechnology Information RefSeq viral protein sequences and utilizes a pretrained Protein-Ligand Affinity Prediction Transformer model to calculate affinity interactions against 2092 ChEMBL-approved drugs, instantly identifying candidates for drug repurposing. In rigorous cross-validation on a curated dataset of 33 426 complete viral genomes, the surveillance module demonstrated robust discriminatory power, achieving an Area Under the Receiver Operating Characteristic Curve of 0.88 in classifying human host potential. By integrating state-of-the-art genomic modeling with automated lead compound screening, Viral Sentry AI offers a proactive, end-to-end research prototype for pandemic preparedness. The platform is freely accessible at https://muntisa.github.io/virsentai (source code: https://github.com/muntisa/virsentai).
dc.description.sponsorshipThe CITIC is funded by the Xunta de Galicia through the collaboration agreement between the Consellería de Cultura, Educación, Formación Profesional e Universidades, and the Galician universities for the strengthening of research centers in the Galician University System (CIGUS). This work was supported by the Consolidation and Structuring of Competitive Research Units (ED431C 2022/46), GRC funded by Xunta de Galicia endowed with EU FEDER funds. Funding for open access charge: Universidade da Coruña/CISUG.
dc.description.sponsorshipXunta de Galicia; ED431C 2022/46
dc.identifier.citationCristian R Munteanu, Jose Vázquez-Naya, Eduardo Tejera, Viral Sentry AI—Automated zoonotic surveillance and drug repurposing agent, Biology Methods and Protocols, Volume 11, Issue 1, 2026, bpag026, https://doi.org/10.1093/biomethods/bpag026
dc.identifier.doi10.1093/biomethods/bpag026
dc.identifier.issn2396-8923
dc.identifier.urihttps://hdl.handle.net/2183/48649
dc.language.isoeng
dc.publisherOxford University Press
dc.relation.isbasedonhttps://github.com/muntisa/virsentai
dc.relation.isbasedonhttps://doi.org/10.5281/zenodo.17445222
dc.relation.isbasedonhttps://doi.org/10.5281/zenodo.20314175
dc.relation.urihttps://doi.org/10.1093/biomethods/bpag026
dc.rightsAttribution-NonCommercial 4.0 Internationalen
dc.rights.accessRightsopen access
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/
dc.subjectVirus host prediction
dc.subjectBioinformatics
dc.subjectWeb server
dc.subjectArtificial intelligence
dc.subjectZoonotic infection
dc.titleViral Sentry AI: Automated Zoonotic Surveillance and Drug Repurposing Agent
dc.typejournal article
dc.type.hasVersionVoR
dspace.entity.typePublication
relation.isAuthorOfPublicationfac98c9d-7cc7-4b09-bbb1-1068637fc73f
relation.isAuthorOfPublicationaeeb3bbf-9f99-467b-aa36-de0b911b5a94
relation.isAuthorOfPublication.latestForDiscoveryfac98c9d-7cc7-4b09-bbb1-1068637fc73f

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Munteanu_CristianR_2026_ViralSentryAI.pdf
Size:
818.76 KB
Format:
Adobe Portable Document Format