University of Konstanz
Graduiertenkolleg / PhD Program
Computer and Information Science

Colloquium of the Department and the PhD Program

title

Hierarchical Classification Methods and Applications in Protein Function Prediction

speaker

Dr. Alex Feritas, University of Kent, UK

date & place

Wednesday, 08.02.2012, 16:15 h
Room C 252

abstract

The problem of protein function prediction can be cast as a classification problem in data mining, where the goal is to predict the functional class of a protein based on values of predictor attributes describing that protein's sequence of amino acids. Protein functions are often described in a hierarchy of functional classes, but most classification methods perform "flat" classification, i.e. they cannot directly cope with a hierarchy of classes to be predicted. In this talk we present an overview of several hierarchical classification methods and a summary of results of their application to protein datasets.