Phylogenies as graphs: structured neural networks improve host origin predictions from paramyxovirus sequences
- 1MRC-University of Glasgow Centre for Virus Research
Abstract
Accurately identifying the host of a virus from its genome sequence is a task with important applications in zoonotic disease surveillance and filling data gaps for metagenomic sampling. Machine learning approaches have seen broad application in making host predictions directly from viral genome sequences. However, most host prediction models do not incorporate information on viral phylogeny, which is strongly correlated with both genome composition and host. We apply a novel graph neural network (GNN) approach which explicitly represents viral phylogeny in model architecture to predict hosts of origin within the paramyxoviruses. We conduct rigorous benchmarking against non-structured neural networks and predictions made using phylogeny alone, showing that GNNs carry distinct advantages over other methods when making predictions where training data is sparse. Validation across different phylogenetic scales shows that simple phylogenetic prediction is effective in many applications and that phylogeny contributes a large proportion of the predictive power of host prediction models, with genome compositional features providing additional power only for specific predictions outside the range of the training data. This novel modelling approach and model validation framework are flexible and can be applied to other viral families.
Related
- Deep learning for mass extinction detection on fossilized phylogenies: power, limitations and lessons for simulation-based birth–death inference
- How Phylogenies Inferred from 46 Mitochondrial Genomes Informed the Systematics of the Australasian Genus of Ticks, Bothriocroton, with the Description of Three New Species.
- Described eukaryotic species in published species-level phylogenies: placement by molecular data, dates and date uncertainty
- Gaussian processes on phylogenies: a kernel framework for building, checking and comparing models of trait evolution
- Influenza A virus H5Nx genotypes assigned by genetic similarity are incongruent with global phylogenies
BibTeX
@misc{herzig2026phylogenies,
title = {{Phylogenies as graphs: structured neural networks improve host origin predictions from paramyxovirus sequences}},
author = {J. C. Herzig and H. Stone and L. Brierley},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.18.752634},
url = {https://www.biorxiv.org/content/10.64898/2026.09.18.752634v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Phylogenies as graphs: structured neural networks improve host origin predictions from paramyxovirus sequences
AU - J. C. Herzig
AU - H. Stone
AU - L. Brierley
PY - 2026
DA - 2026/09/18
PB - bioRxiv
DO - 10.64898/2026.09.18.752634
UR - https://www.biorxiv.org/content/10.64898/2026.09.18.752634v1
AB - Accurately identifying the host of a virus from its genome sequence is a task with important applications in zoonotic disease surveillance and filling data gaps for metagenomic sampling. Machine learning approaches have seen broad application in making host predictions directly from viral genome sequences. However, most host prediction models do not incorporate information on viral phylogeny, which is strongly correlated with both genome composition and host. We apply a novel graph neural network (GNN) approach which explicitly represents viral phylogeny in model architecture to predict hosts of origin within the paramyxoviruses. We conduct rigorous benchmarking against non-structured neural networks and predictions made using phylogeny alone, showing that GNNs carry distinct advantages over other methods when making predictions where training data is sparse. Validation across different phylogenetic scales shows that simple phylogenetic prediction is effective in many applications and that phylogeny contributes a large proportion of the predictive power of host prediction models, with genome compositional features providing additional power only for specific predictions outside the range of the training data. This novel modelling approach and model validation framework are flexible and can be applied to other viral families.
ER -