Functional gene prediction with vital reduced features: Further topics for feature reduction and evaluation criteria for classifiers

Aiming at the prediction of protein solubility, four feature reduction methods are discussed in this paper, including Correlation coefficient method, Filter method, Relief method and Genetic method. With the Top 100 features discovered by genetic method, the best classifier achieves the accuracy of...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaochuan Ai, Jingbo Xia
Format: Conference Proceeding
Language:English
Subjects:
Accuracy
classification
Correlation
cross validation
Feature extraction
Genetics
Proteins
Reliability
Support vector machine
Support vector machines
verification
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Aiming at the prediction of protein solubility, four feature reduction methods are discussed in this paper, including Correlation coefficient method, Filter method, Relief method and Genetic method. With the Top 100 features discovered by genetic method, the best classifier achieves the accuracy of 86% and MCC of 0.7236 in Jackknife test. Moreover, further discussions about feature reduction and classifier reliability evaluation criteria are given. The author claim the exclusive importance of capacity of expansion prediction for classifiers.
ISSN:2161-8151
2161-816X
DOI:10.1109/ICAL.2011.6024771