Viral Sentry AI (VirSentAI) - Automated Zoonotic Surveillance & Drug Repurposing Agent

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 (VirSentAI), an autonomous agent designed to close the gap between viral emergence and therapeutic response. Unlike static analysis tools, VirSentAI operates as a continuous sentinel, automatically scanning the NCBI public databases for new viral genomes and executing a three-stage agentic surveillance workflow, with distinct, specialized AI 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 NCBI RefSeq viral protein sequences and utilizes a pre-trained PLAPT (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 AUROC of 0.88 in classifying human host potential. By integrating state-of-the-art genomic modeling with automated lead compound screening, VirSentAI 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).