Developing Foundation Models for Predicting Viral Animal Host Range in Intelligent Surveillance
Bibliographic record
Abstract
Abstract Emerging human infectious viruses originating from animals continue to pose a persistent threat to global public health. Understanding the host range of animal viruses is crucial for identifying potential spillover pathways and mitigating the risk of future pandemics. Here, we present VirHRanger, a prediction method that integrates foundation models trained on viral genome and protein sequences, alongside genomic and protein compositional traits, viral phylogeny, and protein-protein interactions. To systematically predict the animal host range, VirHRanger incorporates host taxonomy-aware neural networks trained on a comprehensive collection of animal-virus associations spanning mammals, birds, and arthropods. Within a dataset of 4,006 virus species spanning 99 viral families, our model achieved robust performance with a micro-averaged AUROC of 0.938 across all host categories, demonstrating its effectiveness in capturing generalizable host signals from viral genetic data. On a dataset of 315 novel viruses, which are associated with key reservoir animal hosts and insect vectors, VirHRanger notably outperformed the homology-based method, exhibiting a strong generalizability to novel viruses. Furthermore, VirHRanger identified host range variations among closely related viruses within the Coronaviridae family and successfully predicted the ability of SARS-CoV-2 to infect humans and other animal hosts. These findings highlight the potential of VirHRanger to transform sequencing data into timely insights for disease control during the early stages of zoonotic outbreaks.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".