Using Feature Selection Filtering Methods for Binding Site Predictions

Currently the best algorithms for transcription factor binding site prediction are severely limited in accuracy. In previous work we applied classification techniques on predictions from 12 key prediction algorithms. In this paper, we investigate the classification results when 4 feature selection f...

Full description

Saved in:
Bibliographic Details
Main Authors: Yi Sun, Robinson, M., Adams, R., te Boekhorst, R., Rust, A.G., Davey, N.
Format: Conference Proceeding
Language:English
Subjects:
Bioinformatics
DNA
Entropy
Feature Selection
Filtering algorithms
Filters
Genetics
Genomics
Iterative algorithms
Prediction algorithms
Proteins
Sequences
Support Vector Machines
Transcription Factors
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Currently the best algorithms for transcription factor binding site prediction are severely limited in accuracy. In previous work we applied classification techniques on predictions from 12 key prediction algorithms. In this paper, we investigate the classification results when 4 feature selection filtering methods are used. They are bi-normal separation, correlation coefficients, F-score and a cross entropy based algorithm. It is found that all 4 filtering methods perform equally well. Moreover, we show that the worst performing algorithms are not detrimental to the overall performance
DOI:10.1109/COGINF.2006.365547