A Hybrid Approach to Selecting Susceptible Single Nucleotide Polymorphisms for Complex Disease Analysis

Authors:
Pengyi Yang;Zili Zhang
Affiliations:
-;-
Venue:
BMEI '08 Proceedings of the 2008 International Conference on BioMedical Engineering and Informatics - Volume 01
Year:
2008

Citing 0
Cited 2

A Clustering Based Hybrid System for Mass Spectrometry Data Analysis

PRIB '08 Proceedings of the Third IAPR International Conference on Pattern Recognition in Bioinformatics
Evolving decision tree rule based system for audio stego anomalies detection based on Hausdorff distance statistics

Information Sciences: an International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

An increasingly popular and promising way for complex disease diagnosis is to employ artificial neural networks(ANN). Single Nucleotide Polymorphisms (SNP) data from individuals is used as the inputs of ANN to find out specific SNP patterns related to certain disease. Due to the large number of SNPs, it is crucial to select optimal SNP subset and their combinations so that the inputs of ANN can be reduced. With this observation in mind, a hybrid approach –a combination of genetic algorithms (GA) and ANN (called GANN) is used to automatically determine optimal SNP set and optimize the structure of ANN. The proposed GANN algorithmis evaluated by using both a synthetic dataset and a real SNP dataset of a complex disease.