Your browser doesn't support javascript.
loading
A new hybrid algorithm for three-stage gene selection based on whale optimization.
Liu, Junjian; Qu, Chiwen; Zhang, Lupeng; Tang, Yifan; Li, Jinlong; Feng, Huicong; Zeng, Xiaomin; Peng, Xiaoning.
Afiliação
  • Liu J; Department of Statistics, College of Mathematics and Computer Science, Hunan Normal University, Changsha, 410081, Hunan, China.
  • Qu C; Department of Statistics, College of Mathematics and Computer Science, Hunan Normal University, Changsha, 410081, Hunan, China.
  • Zhang L; School of Information Engineering, Baise University, Baise, 533000, Guangxi, China.
  • Tang Y; Department of Biochemistry and Molecular Biology, Jishou University School of Medicine, Jishou, 416000, Hunan, China.
  • Li J; Department of Pathology and Pathophysiology, Hunan Normal University School of Medicine, Changsha, 410013, Hunan, China.
  • Feng H; Department of Biochemistry and Molecular Biology, Jishou University School of Medicine, Jishou, 416000, Hunan, China.
  • Zeng X; Department of Pathology and Pathophysiology, Hunan Normal University School of Medicine, Changsha, 410013, Hunan, China.
  • Peng X; Department of Epidemiology and Health Statistics, Xiangya Public Health School, Central South University, Changsha, 410078, Hunan, China. zxiaomin@csu.edu.cn.
Sci Rep ; 13(1): 3783, 2023 03 07.
Article em En | MEDLINE | ID: mdl-36882446
In biomedical data mining, the gene dimension is often much larger than the sample size. To solve this problem, we need to use a feature selection algorithm to select feature gene subsets with a strong correlation with phenotype to ensure the accuracy of subsequent analysis. This paper presents a new three-stage hybrid feature gene selection method, that combines a variance filter, extremely randomized tree, and whale optimization algorithm. First, a variance filter is used to reduce the dimension of the feature gene space, and an extremely randomized tree is used to further reduce the feature gene set. Finally, the whale optimization algorithm is used to select the optimal feature gene subset. We evaluate the proposed method with three different classifiers in seven published gene expression profile datasets and compare it with other advanced feature selection algorithms. The results show that the proposed method has significant advantages in a variety of evaluation indicators.
Assuntos

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Baleias / Algoritmos Tipo de estudo: Prognostic_studies Limite: Animals Idioma: En Revista: Sci Rep Ano de publicação: 2023 Tipo de documento: Article País de afiliação: China País de publicação: Reino Unido

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Baleias / Algoritmos Tipo de estudo: Prognostic_studies Limite: Animals Idioma: En Revista: Sci Rep Ano de publicação: 2023 Tipo de documento: Article País de afiliação: China País de publicação: Reino Unido