BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Statistical Machine Learning for Modeling Early Respiratory Microb
 iota Composition - Tsivtsivadze\, E (TNO Research Institute)
DTSTART:20140328T110000Z
DTEND:20140328T114500Z
UID:TALK51681@talks.cam.ac.uk
CONTACT:Mustapha Amrani
DESCRIPTION:Co-authors: Giske Biesbroek (UMC Utrecht)\, Elisabeth A.M. San
 ders (UMC Utrecht)\, Roy Montijn (TNO Research Institute)\, Reinier H. Vee
 nhoven (4. Research Center Linnaeus Institute)\, Bart J.F. Keijser (TNO Re
 search Institute)\, Debby Bogaert (UMC Utrecht) \n\nMany bacterial pathoge
 ns causing respiratory infections in children are common residents of the 
 respiratory tract. Insight into bacterial colonization patterns and stabil
 ity at young age may allow identification of biomarker strains that elucid
 ate healthy or susceptible conditions for development of respiratory disea
 se. \n\nWe used statistical machine learning algorithms for analysis of co
 mplex nasopharyngeal microbiota profiles of 60 healthy children at the age
 s of 6 weeks\, and 6\, 12 and 24 months. Our unsupervised and semi-supervi
 sed learning methods are particularly suitable for high dimensional metage
 nomic datasets. The methods stem from a recently proposed class of multi-v
 iew algorithms (closely related to ensembles and consensus techniques) tha
 t aim to combine multiple clustering hypotheses for increased accuracy and
  are not limited to a single similarity measure\, thus leading to robust a
 nd reliable results. Furthermore\, our algorithms allow identification of 
 the optimal number of clusters via construction of co-occurrence matrices 
 and detection of biomarker species by using unsupervised greedy forward fe
 ature selection approach. \n\nWe identified 6 distinct microbiota profiles
  represented by the dominant genera Moraxella\, Haemophilus\, Streptococcu
 s\, or Staphylococcus\, a combination of Dolosigranulum and Corynebacteriu
 m\, plus cluster-specific low abundant biomarker bacteria. The current stu
 dy enabled us to gain insight in the dynamic nature of nasoparyngeal micro
 biota in infants. Our results suggest that the composition of early-life m
 icrobiota is associated with long-term stability and may predict susceptib
 ility to disease. \n
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR