A feature generation algorithm for sequences with application to splice-site prediction

Authors:
Rezarta Islamaj;Lise Getoor;W. John Wilbur
Affiliations:
Computer Science Department, University of Maryland, College Park, MD;Computer Science Department, University of Maryland, College Park, MD;National Center for Biotechnology Information, NLM, NIH, Bethesda, MD
Venue:
PKDD'06 Proceedings of the 10th European conference on Principle and Practice of Knowledge Discovery in Databases
Year:
2006

Citing 5
Cited 2

Selection of relevant features and examples in machine learning

Artificial Intelligence - Special issue on relevance
Text Categorization Based on Regularized Linear Classification Methods

Information Retrieval
Maximum entropy modeling of short sequence motifs with applications to RNA splicing signals

RECOMB '03 Proceedings of the seventh annual international conference on Research in computational molecular biology
A Comparative Study on Feature Selection in Text Categorization

ICML '97 Proceedings of the Fourteenth International Conference on Machine Learning
SpliceMachine: predicting splice sites from high-dimensional local context representations

Bioinformatics

Analytical features: a knowledge-based approach to audio feature generation

EURASIP Journal on Audio, Speech, and Music Processing
A high recall DNA splice site prediction based on association analysis

ACS'10 Proceedings of the 10th WSEAS international conference on Applied computer science

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we present a new approach to feature selection for sequence data. We identify general feature categories and give construction algorithms for each of them. We show how they can be integrated in a system that tightly couples feature construction and feature selection. This integrated process, which we refer to as feature generation, allows us to systematically search a large space of potential features. We demonstrate the effectiveness of our approach for an important component of the gene finding problem, splice-site prediction. We show that predictive models built using our feature generation algorithm achieve a significant improvement in accuracy over existing, state-of-the-art approaches.