Predicting viral host range for reverse zoonosis surveillance
- 1ETH Zurich
Abstract
Zoonotic transmission of viruses has triggered major outbreaks throughout history. However, human-to-animal transmission, or reverse zoonotic transmission, also represents an underappreciated public health threat. Reverse zoonoses can establish novel animal reservoirs that fuel viral evolution and enable eventual spillback into humans, underscoring the importance of defining viral host range. Current approaches for host range prediction are limited. Experimental methods are retrospective and rely on brute-force testing in a small number of models, whereas computational approaches often lack experimental grounding. Here, we present a platform that integrates high-throughput experimental screening with deep learning to predict viral host range from sequence. We screened a yeast-displayed SARS-CoV-2 receptor-binding domain library against 15 ACE2 orthologs from diverse species, and deep sequenced the ACE2-binding and non-binding populations to generate an atlas of 8.8 million unique RBD:ACE2 interaction measurements. These data were used to train a transformer-based deep learning model that predicts RBD:ACE2 compatibility across animal species from sequence alone, and generalizes in a zero-shot manner to ACE2 orthologs not observed during training. Critically, the model pairs each prediction with a distance-based uncertainty estimate, allowing hundreds of candidate species to be triaged by both predicted host compatibility and confidence. This framework enables the rapid prioritization of animal species for SARS-CoV-2 surveillance and provides a general strategy for anticipating viral host range.
Related
- RevPert: predicting candidate drivers of transcriptomic state transitions via gallery-native reverse perturbation
- Sensitive reverse transcription-digital droplet PCR-based discrimination of hepatitis delta virus RNAs reveals differential effects of interferon-α on viral RNA species
- High-Throughput Virome Surveillance Reveals Emerging Viral Threats to Cucumber Production in Taiwan.
- Viral pathogens in effluent samples collected from a swine slaughterhouse in Central Italy: a 1-year molecular surveillance
- Species distribution modelling of three Aacia species in the Negev Desert: predicting future range shifts and identifying climatic drivers
BibTeX
@misc{irvine2026predicting,
title = {{Predicting viral host range for reverse zoonosis surveillance}},
author = {E. B. Irvine and T. Bikias and T. Schifferli and L. Plath and J. Han and N. Chen and B. Sahin and L. Frei and J. M. Taft and S. T. Reddy},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.30.755793},
url = {https://www.biorxiv.org/content/10.64898/2026.09.30.755793v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Predicting viral host range for reverse zoonosis surveillance
AU - E. B. Irvine
AU - T. Bikias
AU - T. Schifferli
AU - L. Plath
AU - J. Han
AU - N. Chen
AU - B. Sahin
AU - L. Frei
AU - J. M. Taft
AU - S. T. Reddy
PY - 2026
DA - 2026/09/30
PB - bioRxiv
DO - 10.64898/2026.09.30.755793
UR - https://www.biorxiv.org/content/10.64898/2026.09.30.755793v1
AB - Zoonotic transmission of viruses has triggered major outbreaks throughout history. However, human-to-animal transmission, or reverse zoonotic transmission, also represents an underappreciated public health threat. Reverse zoonoses can establish novel animal reservoirs that fuel viral evolution and enable eventual spillback into humans, underscoring the importance of defining viral host range. Current approaches for host range prediction are limited. Experimental methods are retrospective and rely on brute-force testing in a small number of models, whereas computational approaches often lack experimental grounding. Here, we present a platform that integrates high-throughput experimental screening with deep learning to predict viral host range from sequence. We screened a yeast-displayed SARS-CoV-2 receptor-binding domain library against 15 ACE2 orthologs from diverse species, and deep sequenced the ACE2-binding and non-binding populations to generate an atlas of 8.8 million unique RBD:ACE2 interaction measurements. These data were used to train a transformer-based deep learning model that predicts RBD:ACE2 compatibility across animal species from sequence alone, and generalizes in a zero-shot manner to ACE2 orthologs not observed during training. Critically, the model pairs each prediction with a distance-based uncertainty estimate, allowing hundreds of candidate species to be triaged by both predicted host compatibility and confidence. This framework enables the rapid prioritization of animal species for SARS-CoV-2 surveillance and provides a general strategy for anticipating viral host range.
ER -