BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Finding interesting clusters using Bayesian data fusion - Richard 
 Savage (University of Warwick)
DTSTART:20101101T160000Z
DTEND:20101101T170000Z
UID:TALK24783@talks.cam.ac.uk
CONTACT:Florian Markowetz
DESCRIPTION:We are increasingly able to make multiple types of measurement
  of \ninteresting biological systems. To benefit fully from these advances
 \, we need to \ndevelop statistical methods that can combine multiple data
  sets in sensible ways.\n\nI'll present some of our recent work on data fu
 sion.  Our work is a development \nof the hierarchical Dirichlet Process m
 ixture model and can be regarded as data \nfusion clustering\, with the ad
 ded benefit that we can identify subsets of items \nthat are most strongly
  clustered across the data sets.  This turns out to give \nus greater insi
 ght into the underlying biology\, which I'll illustrate with some \nof our
  work on gene clustering.  I'll also talk briefly about where we're \nstar
 ting to take this work in relation to clustering samples from cancer studi
 es.\n\n\nREF:  http://bioinformatics.oxfordjournals.org/content/26/12/i158
 .full
LOCATION:Cancer Research UK Cambridge Research Institute\, Lecture Theatre
END:VEVENT
END:VCALENDAR