aCary Institute of Ecosystem Studies, Millbrook, NY 12545; and
bOdum School of Ecology, University of Georgia, Athens, GA 30602
Edited by Simon A. Levin, Princeton University, Princeton, NJ, and approved April 20, 2015 (received for review February 10, 2015)
Forecasting reservoirs of zoonotic disease is a pressing public health priority. We apply machine learning to datasets describing the biological, ecological, and life history traits of rodents, which collectively carry a disproportionate number of zoonotic pathogens. We identify particular rodent species predicted to be novel zoonotic reservoirs and geographic regions from which new emerging pathogens are most likely to arise. We also describe trait profiles—complexes of biological features—that distinguish reservoirs from nonreservoirs. Generally, the most permissive rodent reservoirs display a fast-paced life history strategy, maximizing near-term fitness by having many altricial young that begin reproduction early and reproduce frequently. These findings may constitute an important lead in guiding the search for novel disease reservoirs in the wild.
The increasing frequency of zoonotic disease events underscores a need to develop forecasting tools toward a more preemptive approach to outbreak investigation. We apply machine learning to data describing the traits and zoonotic pathogen diversity of the most speciose group of mammals, the rodents, which also comprise a disproportionate number of zoonotic disease reservoirs. Our models predict reservoir status in this group with over 90% accuracy, identifying species with high probabilities of harboring undiscovered zoonotic pathogens based on trait profiles that may serve as rules of thumb to distinguish reservoirs from nonreservoir species. Key predictors of zoonotic reservoirs include biogeographical properties, such as range size, as well as intrinsic host traits associated with lifetime reproductive output. Predicted hotspots of novel rodent reservoir diversity occur in the Middle East and Central Asia and the Midwestern United States.
↵1To whom correspondence should be addressed. Email: hanb@caryinstitute.org.
Author contributions: B.A.H. and J.M.D. designed research; B.A.H., J.P.S., S.E.B., and J.M.D. performed research; S.E.B. contributed new reagents/analytic tools; B.A.H. and J.P.S. analyzed data; and B.A.H., J.P.S., S.E.B., and J.M.D. wrote the paper.
The authors declare no conflict of interest.
This article is a PNAS Direct Submission.
Data deposition: The data reported in this paper have been deposited in the Dryad Digital Repository, datadryad.org (DOI no. 10.5061/dryad.7fh4q).
This article contains supporting information online at www.pnas.org/lookup/suppl/doi:10.1073/pnas.1501598112/-/DCSupplemental.
Freely available online through the PNAS open access option.