Advanced search
1 file | 4.77 MB Add to list

Optimising predictive models to prioritise viral discovery in zoonotic reservoirs

(2022) LANCET MICROBE. 3(8). p.e625-e637
Author
Organization
Project
Abstract
Despite the global investment in One Health disease surveillance, it remains difficult and costly to identify and monitor the wildlife reservoirs of novel zoonotic viruses. Statistical models can guide sampling target prioritisation, but the predictions from any given model might be highly uncertain; moreover, systematic model validation is rare, and the drivers of model performance are consequently under-documented. Here, we use the bat hosts of betacoronaviruses as a case study for the data-driven process of comparing and validating predictive models of probable reservoir hosts. In early 2020, we generated an ensemble of eight statistical models that predicted host-virus associations and developed priority sampling recommendations for potential bat reservoirs of betacoronaviruses and bridge hosts for SARS-CoV-2. During a time frame of more than a year, we tracked the discovery of 47 new bat hosts of betacoronaviruses, validated the initial predictions, and dynamically updated our analytical pipeline. We found that ecological trait-based models performed well at predicting these novel hosts, whereas network methods consistently performed approximately as well or worse than expected at random. These findings illustrate the importance of ensemble modelling as a buffer against mixed-model quality and highlight the value of including host ecology in predictive models. Our revised models showed an improved performance compared with the initial ensemble, and predicted more than 400 bat species globally that could be undetected betacoronavirus hosts. We show, through systematic validation, that machine learning models can help to optimise wildlife sampling for undiscovered viruses and illustrates how such approaches are best implemented through a dynamic process of prediction, data collection, validation, and updating. © 2022 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license.
Keywords
RESPIRATORY SYNDROME CORONAVIRUS, BAT CORONAVIRUS, INFECTION, HOST, TRANSMISSION, PERSISTENCE, EVOLUTION, ROUSETTUS, COVID-19, GENOMES

Downloads

  • Optimising predictive models.pdf
    • full text (Published version)
    • |
    • open access
    • |
    • PDF
    • |
    • 4.77 MB

Citation

Please use this url to cite or link to this publication:

MLA
Becker, Daniel J., et al. “Optimising Predictive Models to Prioritise Viral Discovery in Zoonotic Reservoirs.” LANCET MICROBE, vol. 3, no. 8, 2022, pp. e625–37, doi:10.1016/S2666-5247(21)00245-7.
APA
Becker, D. J., Albery, G. F., Sjodin, A. R., Poisot, T., Bergner, L. M., Chen, B., … Carlson, C. J. (2022). Optimising predictive models to prioritise viral discovery in zoonotic reservoirs. LANCET MICROBE, 3(8), e625–e637. https://doi.org/10.1016/S2666-5247(21)00245-7
Chicago author-date
Becker, Daniel J, Gregory F Albery, Anna R Sjodin, Timothee Poisot, Laura M Bergner, Binqi Chen, Lily E Cohen, et al. 2022. “Optimising Predictive Models to Prioritise Viral Discovery in Zoonotic Reservoirs.” LANCET MICROBE 3 (8): e625–37. https://doi.org/10.1016/S2666-5247(21)00245-7.
Chicago author-date (all authors)
Becker, Daniel J, Gregory F Albery, Anna R Sjodin, Timothee Poisot, Laura M Bergner, Binqi Chen, Lily E Cohen, Tad A Dallas, Evan A Eskew, Anna C Fagre, Maxwell J Farrell, Sarah Guth, Barbara A Han, Nancy B Simmons, Michiel Stock, Emma C Teeling, and Colin J Carlson. 2022. “Optimising Predictive Models to Prioritise Viral Discovery in Zoonotic Reservoirs.” LANCET MICROBE 3 (8): e625–e637. doi:10.1016/S2666-5247(21)00245-7.
Vancouver
1.
Becker DJ, Albery GF, Sjodin AR, Poisot T, Bergner LM, Chen B, et al. Optimising predictive models to prioritise viral discovery in zoonotic reservoirs. LANCET MICROBE. 2022;3(8):e625–37.
IEEE
[1]
D. J. Becker et al., “Optimising predictive models to prioritise viral discovery in zoonotic reservoirs,” LANCET MICROBE, vol. 3, no. 8, pp. e625–e637, 2022.
@article{01GVZ5XQMGWKXNCAH73SG9XY03,
  abstract     = {{Despite the global investment in One Health disease surveillance, it remains difficult and costly to identify and monitor the wildlife reservoirs of novel zoonotic viruses. Statistical models can guide sampling target prioritisation, but the predictions from any given model might be highly uncertain; moreover, systematic model validation is rare, and the drivers of model performance are consequently under-documented. Here, we use the bat hosts of betacoronaviruses as a case study for the data-driven process of comparing and validating predictive models of probable reservoir hosts. In early 2020, we generated an ensemble of eight statistical models that predicted host-virus associations and developed priority sampling recommendations for potential bat reservoirs of betacoronaviruses and bridge hosts for SARS-CoV-2. During a time frame of more than a year, we tracked the discovery of 47 new bat hosts of betacoronaviruses, validated the initial predictions, and dynamically updated our analytical pipeline. We found that ecological trait-based models performed well at predicting these novel hosts, whereas network methods consistently performed approximately as well or worse than expected at random. These findings illustrate the importance of ensemble modelling as a buffer against mixed-model quality and highlight the value of including host ecology in predictive models. Our revised models showed an improved performance compared with the initial ensemble, and predicted more than 400 bat species globally that could be undetected betacoronavirus hosts. We show, through systematic validation, that machine learning models can help to optimise wildlife sampling for undiscovered viruses and illustrates how such approaches are best implemented through a dynamic process of prediction, data collection, validation, and updating. © 2022 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license.}},
  author       = {{Becker, Daniel J and  Albery, Gregory F and  Sjodin, Anna R and  Poisot, Timothee and  Bergner, Laura M and  Chen, Binqi and  Cohen, Lily E and  Dallas, Tad A and  Eskew, Evan A and  Fagre, Anna C and  Farrell, Maxwell J and  Guth, Sarah and  Han, Barbara A and  Simmons, Nancy B and Stock, Michiel and  Teeling, Emma C and  Carlson, Colin J}},
  issn         = {{2666-5247}},
  journal      = {{LANCET MICROBE}},
  keywords     = {{RESPIRATORY SYNDROME CORONAVIRUS,BAT CORONAVIRUS,INFECTION,HOST,TRANSMISSION,PERSISTENCE,EVOLUTION,ROUSETTUS,COVID-19,GENOMES}},
  language     = {{eng}},
  number       = {{8}},
  pages        = {{e625--e637}},
  title        = {{Optimising predictive models to prioritise viral discovery in zoonotic reservoirs}},
  url          = {{http://doi.org/10.1016/S2666-5247(21)00245-7}},
  volume       = {{3}},
  year         = {{2022}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: