OSU integrative biology team uses machine learning in newly published Ebola virus research

Monday, September 25, 2023
Media Contact:
Elizabeth Gosney | CAS Marketing and Communications Manager | 405-744-7497 | [email protected]

A team of researchers led by Oklahoma State University integrative biology assistant professor Dr. Patrick Stephens lately unveiled vital insights into
the transmission of the Ebola virus. 

The research team, which additionally included researchers from the University of Georgia
and the Cary Institute of Ecosystems Studies, published the primary complete examine
of the potential host vary of Ebola viruses together with each mammal species in Africa.
This examine was led by Dr. Mekala Sundaram, who was a postdoctoral scholar in the Stephens
Lab at OSU when it was published.

For years, the query of which animals had been the pure hosts — or “reservoirs”
— for the Ebola virus had baffled scientists, Stephens defined. It was beforehand
identified that Ebola viruses can infect numerous wild mammal species, together with primates
like chimpanzees, however primates are likely to succumb rapidly to an infection, making them unlikely
major reservoirs. So, the research targeted on figuring out these pure reservoir
species that in the end transmit the virus to people, both instantly or by different

“This is de facto necessary as a result of species which can be each prone to develop infections
when uncovered to the virus and tolerate infections effectively are the very best candidates for
major reservoir species,” Stephens stated. “These species will survive lengthy sufficient
to unfold the virus to many different species. Our fashions seem to have the ability to predict
which species will succumb rapidly to or tolerate infections with about 90% accuracy.”

The research addressed this enigma by conducting a complete examine encompassing
over 500 species of untamed mammals in Africa. No earlier examine included greater than 120.
Additionally, the examine explored the position of the Newman Pick or NPC1 gene, which is
identified to have an effect on Ebola virus an infection in host cells, throughout a number of mammal species.
Using machine learning, the team developed a mannequin based mostly on ecological and morphological
traits to foretell which species are prone to be contaminated.  

The research strongly implicated fruit bats in the household Pteropodidae as the first reservoirs of Ebola viruses that preserve the virus in the wild, underlining
their collective significance. An evaluation of NPC1 sequences additionally proved particularly
promising; it was in a position to establish with 100% accuracy bat species in which infections
have been beforehand documented in the wild. This means that NPC1 might be a vital
genetic marker to think about in future research of Ebola virus susceptibility in different

Using their findings from this research, Stephens’ team has a number of follow-up research
at the moment underway. One examine, additionally led by Sundaram, is in assessment in an instructional journal.
It employs a statistical methodology referred to as path evaluation to discover how mammal traits
work together with components like fruit abundance in shaping transmission threat to human populations.
Prior findings counsel that areas ample in ficus fruits, resembling wild figs, pose
larger dangers as a consequence of their attraction of fruit bats and primates, that are intermediaries
in illness transmission to people. 

“It’s form of an ideal storm of things,” Stephens stated. “Fruit bats and primates
go there to eat fruit, and people go there each to eat the fruit and to hunt bats
and primates for meat. Bats are those spreading it to different species, and people
get it both instantly from the bats or from primates contaminated by bats.” 

Members of the research team included Drs. John Paul Schmidt and John Drake from the
University of Georgia, Dr. Barbara Han from the Cary Institute of Ecosystems Studies
and Sundaram, who lately joined the college at UGA. 

“By soliciting and synthesizing the experience of different team members, I conceived the
thought for analyses, collected knowledge, developed the fashions utilizing acceptable machine
learning strategies, and led the writing of this paper for publication. I coordinated
writing efforts amongst all team members,” Sundaram stated.

This OSU-UGA collaborative research was performed as a part of an NIH-funded venture,
“Spillover of Ebola and different Filoviruses at Ecological Boundaries,” with whole funding
of $2.4 million. It will proceed for almost three extra years.

“Ultimately there are two potential broad impacts of our work. First is a greater understanding
of how Ebola viruses are entering into human populations, and the way they’re being maintained
in the wild.  However, in the end we hope that the research will assist forestall future
outbreaks by figuring out what areas and what human behaviors are prone to be excessive
threat,” Stephens stated.

Read the complete research article, “Traits, phylogeny and host cell receptors predict
Ebolavirus host standing amongst African mammals” on the PLOS Biology web site. You can discover a hyperlink to this and Stephens’ and Sundaram’s different latest publications
right here.

Story By:
Allie Putman, CAS Graduate Student | [email protected]


Recommended For You