BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Novel Methods for Data Integration in Bioinformatics - Colin Campb
 ell\, Engineering Dept. University of Bristol
DTSTART:20080520T150000Z
DTEND:20080520T160000Z
UID:TALK12212@talks.cam.ac.uk
CONTACT:Andrew Teschendorff
DESCRIPTION:In this talk we will outline some novel methods for data integ
 ration for supervised and unsupervised learning. The principal\napplicatio
 ns will be to bioinformatics and cancer informatics.\n\nIn the first part 
 of the talk we briefly review previous work on the use of Bayesian unsuper
 vised and semi-supervised methods to determine structure in cancer dataset
 s: specifically we consider expression array datasets for breast cancer an
 d prostate cancer (work with Luke Carrivick\, Mark Girolami and others).\n
 \nWe then extend these approaches to the joint unsupervised modelling of t
 wo types of data which are assumed functionally dependent.\nThe model we p
 ropose is loosely based on correspondence Latent Dirichlet Allocation (LDA
 ) and we illustrate its performance on a dataset consisting of breast canc
 er microRNA and expression array data with both types of data derived from
  the same patients (work with Phaedra Agius\,Yiming Ying and others).\n\nN
 ext we consider supervised learning with multiple types of data (work with
  Yiming Ying and others). Thus a classifier which is based on multiple typ
 es of input data is potentially more accurate than a classifier which uses
  only one type of input data. These algorithms are applicable to many type
 s of problem in bioinformatics ranging from network inference to protein f
 old prediction. We consider several new approaches based on probabilistic 
 multi-kernel multi-class\nalgorithms. We consider several application doma
 ins for these methods including an application to  protein fold prediction
  based on a dataset with 27 fold classes in which\nthe proposed method out
 performs the closest rival by 4 per centage points (work with Yiming Ying)
 .
LOCATION:in Room 215 at Cambridge Research Institute.
END:VEVENT
END:VCALENDAR