Features

KDD Cup 2002 is a data mining competition held in conjuction with the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.

This year the competition includes two tasks that involve data mining in molecular biology domains. The first task focuses on learning models that can assist genome annotators by automatically extracting information from scientific articles. More specifically, The system had to automatically analyze thousands of scientific articles on Drosophila melanogaster to determine which should be curated in the FlyBase, the public fruit fly database. The data mining algorithms had to accurately indicate which articles included results on expression of gene products, and which genes and proteins were involved. 32 teams participated in the task.

The second task focused on learning models that characterize the behavior of individual genes in a hidden experimental setting. The training and test data come from recent experiments with a set of S. cerevisiae (yeast) strains in which each strain is characterized by a single gene being knocked out. The goal of the task is to predict the effect of knock-out genes on different sub-cellular components in yeast cells. 52 teams participated in the task.

Winners are

Task 1: Information Extraction from Biomedical Articles Winner: ClearForest and Celera contacts: Yizhar Regev and Michal Finkelstein

Honorable Mentions:

Design Technology Institute Ltd., National University of Singapore and Genome Institute of Singapore contact: Shi Min

Imperial College and Inforsense Limited contacts: Huma Lodhi and Yong Zhang

Verity Inc. and Exelixis contact: Bin Chen

Task 2: Yeast Gene Regulation Prediction Winner: Adam Kowalczyk and Bhavanni Raskutti Telstra Research Laboratories

Honorable Mentions: David Vogel and Randy Axelrod A.I. Insight Inc. and Sentara Healthcare

Marcus Denecke, Mark-A. Krogel, Marco Landwehr and Tobias Scheffer Magdeburg University

George Forman Hewlett Packard Laboratories

Amal Perera, Bill Jockheck, Willy Valdivia Granda, Anne Denton, Pratap Kotala and William Perrizo North Dakota State University

The prizes were announced during the KDD-2002 conference, held in Edmonton, Canada.

The cup was co-chaired this year by Mark Craven of the University of Wisconsin's Department of Biostatistics and Medical Informatics and by Alexander Yeh of the Mitre Corporation, an information technology organization that performs research and development for government agencies.

For full information on KDD Cup 2002, see http://www.biostat.wisc.edu/~craven/kddcup/index.html