Gene classification: issues and challenges for relational learning

Authors:
Claudia Perlich;Srujana Merugu
Affiliations:
IBM, T. J. Watson Research Center;University of Texas at Austin
Venue:
MRDM '05 Proceedings of the 4th international workshop on Multi-relational mining
Year:
2005

Citing 7
Cited 0

Linkage and Autocorrelation Cause Feature Selection Bias in Relational Learning

ICML '02 Proceedings of the Nineteenth International Conference on Machine Learning
Data Mining the Yeast Genome in a Lazy Functional Language

PADL '03 Proceedings of the 5th International Symposium on Practical Aspects of Declarative Languages
DLAB: A Declarative Language Bias Formalism

ISMIS '96 Proceedings of the 9th International Symposium on Foundations of Intelligent Systems
Aggregation-based feature invention and relational concept classes

Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining
Why collective inference improves relational classification

Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining
Distribution-based aggregation for relational learning with identifier attributes

Machine Learning
The use of the area under the ROC curve in the evaluation of machine learning algorithms

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present ongoing research that applies statistical relational learning techniques, in particular, propositionalization, to the challenging and interesting real-world domain of functional gene classification of the Yeast genome Sachharomyces Cerevisiae. The main objective of this paper is to identify and describe the structural and statistical properties of this domain and examine how they conflict with the assumptions of relational learning approaches. Such properties are, in fact, shared by many relational application domains and potential solutions will be of interest far beyond the particular genetic application. We show in the last part some preliminary experimental results on potential approaches to overcome such limitations by extending the existing automated feature construction strategies to accommodate the specific domain properties.