A novel SVM-ID3 Hybrid Feature Selection Method to Build a Disease Model for Melanoma using Integrated Genotyping and Phenotype Data from dbGaP

Date

2014-09-03

Author

Aydın Son, Yeşim
YÜCEBAŞ, SAİT CAN

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

1
views

0
downloads

The relations between Single Nucleotide Polymorphism (SNP) and complex diseases are likely to be non-linear and require analysis of the high dimensional data. Previous studies in the field mostly focus on genotyping and effects of various phenotypes are not considered. To fill this gap a hybrid feature selection model of support vector machine and decision tree has been designed. The designed method is tested on melanoma. We were able to select phenotypic features such as moles and dysplastic nevi, and SNPs those maps to specific genes such as CAMK1D. The performance results of the proposed hybrid model, on melanoma dataset are 79.07% of sensitivity and 0.81 of area under ROC curve.

Subject Keywords

Genome Wide Association Studies (GWAS), Single Nucleotide Polymorphism (SNP), Data mining, Support Vector Machines (SVM), Decision trees, Hybrid models

URI

https://hdl.handle.net/11511/31532

Collections

Graduate School of Informatics, Conference / Seminar