Viral Sentry AI: Automated Zoonotic Surveillance and Drug Repurposing Agent
| UDC.coleccion | Investigación | |
| UDC.departamento | Ciencias da Computación e Tecnoloxías da Información | |
| UDC.grupoInv | Redes de Neuronas Artificiais e Sistemas Adaptativos -Informática Médica e Diagnóstico Radiolóxico (RNASA - IMEDIR) | |
| UDC.institutoCentro | CITIC - Centro de Investigación de Tecnoloxías da Información e da Comunicación | |
| UDC.issue | 1 | |
| UDC.journalTitle | Biology Methods and Protocols | |
| UDC.volume | 11 | |
| dc.contributor.author | Munteanu, Cristian-Robert | |
| dc.contributor.author | Vázquez-Naya, José | |
| dc.contributor.author | Tejera, Eduardo | |
| dc.date.accessioned | 2026-06-25T07:42:45Z | |
| dc.date.available | 2026-06-25T07:42:45Z | |
| dc.date.issued | 2026 | |
| dc.description | Financiado 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.sponsorship | The 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.sponsorship | Xunta de Galicia; ED431C 2022/46 | |
| dc.identifier.citation | Cristian 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.doi | 10.1093/biomethods/bpag026 | |
| dc.identifier.issn | 2396-8923 | |
| dc.identifier.uri | https://hdl.handle.net/2183/48649 | |
| dc.language.iso | eng | |
| dc.publisher | Oxford University Press | |
| dc.relation.isbasedon | https://github.com/muntisa/virsentai | |
| dc.relation.isbasedon | https://doi.org/10.5281/zenodo.17445222 | |
| dc.relation.isbasedon | https://doi.org/10.5281/zenodo.20314175 | |
| dc.relation.uri | https://doi.org/10.1093/biomethods/bpag026 | |
| dc.rights | Attribution-NonCommercial 4.0 International | en |
| dc.rights.accessRights | open access | |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc/4.0/ | |
| dc.subject | Virus host prediction | |
| dc.subject | Bioinformatics | |
| dc.subject | Web server | |
| dc.subject | Artificial intelligence | |
| dc.subject | Zoonotic infection | |
| dc.title | Viral Sentry AI: Automated Zoonotic Surveillance and Drug Repurposing Agent | |
| dc.type | journal article | |
| dc.type.hasVersion | VoR | |
| dspace.entity.type | Publication | |
| relation.isAuthorOfPublication | fac98c9d-7cc7-4b09-bbb1-1068637fc73f | |
| relation.isAuthorOfPublication | aeeb3bbf-9f99-467b-aa36-de0b911b5a94 | |
| relation.isAuthorOfPublication.latestForDiscovery | fac98c9d-7cc7-4b09-bbb1-1068637fc73f |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Munteanu_CristianR_2026_ViralSentryAI.pdf
- Size:
- 818.76 KB
- Format:
- Adobe Portable Document Format

