首页> 外文会议>European Federation for Medical Informatics., Conference >A novel SVM-ID3 Hybrid Feature Selection Method to Build a Disease Model for Melanoma using Integrated Genotyping and Phenotype Data from dbGaP
【24h】

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

机译:一种新的SVM-ID3混合特征选择方法,用于使用DBGAP的集成基因分型和表型数据构建黑色素瘤的疾病模型

获取原文

摘要

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.
机译:单核苷酸多态性(SNP)和复杂疾病之间的关系可能是非线性的并且需要分析高尺寸数据。以前在该领域的研究主要关注各种表型的基因分型,并且不考虑各种表型的影响。为了填充此间隙,设计了支持向量机和决策树的混合特征选择模型。设计方法对黑色素瘤进行了测试。我们能够选择摩尔斯和消化骨质骨骼的表型特征,并将这些地图SNPS与诸如Camk1d等特定基因的映射。拟议的杂种模型的性能结果,黑素瘤数据集的灵敏度为79.07%,曲线下面积为0.81。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号