BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Machine learning models guide viral discovery in museum bat collec
 tions - Maya M. Juman\, Department of Veterinary Medicine
DTSTART:20251124T123000Z
DTEND:20251124T130000Z
UID:TALK240181@talks.cam.ac.uk
CONTACT:Sam Nallaperuma-Herzberg
DESCRIPTION:Natural history museum collections are valuable but underutili
 zed resources for viral discovery\, offering opportunities to test hypothe
 ses about pathogen occurrence across space\, time\, and taxonomic groups. 
 We developed trait-based machine learning models of bat host suitability t
 o guide viral screening of 1821 tissues in a museum collection. Our corona
 virus and paramyxovirus predictive models performed with 79% and 92% predi
 ctive accuracy\, respectively\, and we used these models to generate ranke
 d lists of suspect “novel” host species for screening. For the first t
 ime\, we recovered these viruses from archived museum tissues\, confirming
  three novel coronavirus host species and three novel paramyxovirus host s
 pecies (3% and 33% prediction success rate\, respectively). These sequence
 s included a SARS-like coronavirus from an Angolan bat collected in June 2
 019\, suggesting that viruses with epidemic potential may be more widespre
 ad in sub-Saharan Africa than previously believed. This case study lays ou
 t a framework for using predictive machine learning models to unlock patho
 gen data hidden in historical specimens.
LOCATION:SS03 Seminar Room\, Willam Gates building (Department of Computer
  Science and Technology)
END:VEVENT
END:VCALENDAR