Two-stage feature selection for classification of gene expression data based on an improved Salp Swarm Algorithm
Microarray technology has developed rapidly in recent years, producing a large number of ultra-high dimensional gene expression data. However, due to the huge sample size and dimension proportion of gene expression data, it is very challenging work to screen important genes from gene expression data...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2022-09-01
|
| Series: | Mathematical Biosciences and Engineering |
| Subjects: | |
| Online Access: | https://www.aimspress.com/article/doi/10.3934/mbe.2022641?viewType=HTML |
| _version_ | 1811265351778828288 |
|---|---|
| author | Xiwen Qin Shuang Zhang Dongmei Yin Dongxue Chen Xiaogang Dong |
| author_facet | Xiwen Qin Shuang Zhang Dongmei Yin Dongxue Chen Xiaogang Dong |
| author_sort | Xiwen Qin |
| collection | DOAJ |
| description | Microarray technology has developed rapidly in recent years, producing a large number of ultra-high dimensional gene expression data. However, due to the huge sample size and dimension proportion of gene expression data, it is very challenging work to screen important genes from gene expression data. For small samples of high-dimensional biomedical data, this paper proposes a two-stage feature selection framework combining Wrapper, embedding and filtering to avoid the curse of dimensionality. The proposed framework uses weighted gene co-expression network (WGCNA), random forest and minimal redundancy maximal relevance (mRMR) for first stage feature selection. In the second stage, a new gene selection method based on the improved binary Salp Swarm Algorithm is proposed, which combines machine learning methods to adaptively select feature subsets suitable for classification algorithms. Finally, the classification accuracy is evaluated using six methods: lightGBM, RF, SVM, XGBoost, MLP and KNN. To verify the performance of the framework and the effectiveness of the proposed algorithm, the number of genes selected and the classification accuracy was compared with the other five intelligent optimization algorithms. The results show that the proposed framework achieves an accuracy equal to or higher than other advanced intelligent algorithms on 10 datasets, and achieves an accuracy of over 97.6% on all 10 datasets. This shows that the method proposed in this paper can solve the feature selection problem related to high-dimensional data, and the proposed framework has no data set limitation, and it can be applied to other fields involving feature selection. |
| first_indexed | 2024-04-12T20:21:01Z |
| format | Article |
| id | doaj.art-fbd22ff5f55d40cab86ef4d59fa1dd5a |
| institution | Directory Open Access Journal |
| issn | 1551-0018 |
| language | English |
| last_indexed | 2024-04-12T20:21:01Z |
| publishDate | 2022-09-01 |
| publisher | AIMS Press |
| record_format | Article |
| series | Mathematical Biosciences and Engineering |
| spelling | doaj.art-fbd22ff5f55d40cab86ef4d59fa1dd5a2022-12-22T03:17:59ZengAIMS PressMathematical Biosciences and Engineering1551-00182022-09-011912137471378110.3934/mbe.2022641Two-stage feature selection for classification of gene expression data based on an improved Salp Swarm AlgorithmXiwen Qin0Shuang Zhang1Dongmei Yin2Dongxue Chen3Xiaogang Dong4School of Mathematics and Statistics, Changchun University of Technology, Changchun 130012, ChinaSchool of Mathematics and Statistics, Changchun University of Technology, Changchun 130012, ChinaSchool of Mathematics and Statistics, Changchun University of Technology, Changchun 130012, ChinaSchool of Mathematics and Statistics, Changchun University of Technology, Changchun 130012, ChinaSchool of Mathematics and Statistics, Changchun University of Technology, Changchun 130012, ChinaMicroarray technology has developed rapidly in recent years, producing a large number of ultra-high dimensional gene expression data. However, due to the huge sample size and dimension proportion of gene expression data, it is very challenging work to screen important genes from gene expression data. For small samples of high-dimensional biomedical data, this paper proposes a two-stage feature selection framework combining Wrapper, embedding and filtering to avoid the curse of dimensionality. The proposed framework uses weighted gene co-expression network (WGCNA), random forest and minimal redundancy maximal relevance (mRMR) for first stage feature selection. In the second stage, a new gene selection method based on the improved binary Salp Swarm Algorithm is proposed, which combines machine learning methods to adaptively select feature subsets suitable for classification algorithms. Finally, the classification accuracy is evaluated using six methods: lightGBM, RF, SVM, XGBoost, MLP and KNN. To verify the performance of the framework and the effectiveness of the proposed algorithm, the number of genes selected and the classification accuracy was compared with the other five intelligent optimization algorithms. The results show that the proposed framework achieves an accuracy equal to or higher than other advanced intelligent algorithms on 10 datasets, and achieves an accuracy of over 97.6% on all 10 datasets. This shows that the method proposed in this paper can solve the feature selection problem related to high-dimensional data, and the proposed framework has no data set limitation, and it can be applied to other fields involving feature selection.https://www.aimspress.com/article/doi/10.3934/mbe.2022641?viewType=HTMLhigh-dimensional datafeature selectionswarm intelligence optimization algorithmgene expression datacancer classification |
| spellingShingle | Xiwen Qin Shuang Zhang Dongmei Yin Dongxue Chen Xiaogang Dong Two-stage feature selection for classification of gene expression data based on an improved Salp Swarm Algorithm Mathematical Biosciences and Engineering high-dimensional data feature selection swarm intelligence optimization algorithm gene expression data cancer classification |
| title | Two-stage feature selection for classification of gene expression data based on an improved Salp Swarm Algorithm |
| title_full | Two-stage feature selection for classification of gene expression data based on an improved Salp Swarm Algorithm |
| title_fullStr | Two-stage feature selection for classification of gene expression data based on an improved Salp Swarm Algorithm |
| title_full_unstemmed | Two-stage feature selection for classification of gene expression data based on an improved Salp Swarm Algorithm |
| title_short | Two-stage feature selection for classification of gene expression data based on an improved Salp Swarm Algorithm |
| title_sort | two stage feature selection for classification of gene expression data based on an improved salp swarm algorithm |
| topic | high-dimensional data feature selection swarm intelligence optimization algorithm gene expression data cancer classification |
| url | https://www.aimspress.com/article/doi/10.3934/mbe.2022641?viewType=HTML |
| work_keys_str_mv | AT xiwenqin twostagefeatureselectionforclassificationofgeneexpressiondatabasedonanimprovedsalpswarmalgorithm AT shuangzhang twostagefeatureselectionforclassificationofgeneexpressiondatabasedonanimprovedsalpswarmalgorithm AT dongmeiyin twostagefeatureselectionforclassificationofgeneexpressiondatabasedonanimprovedsalpswarmalgorithm AT dongxuechen twostagefeatureselectionforclassificationofgeneexpressiondatabasedonanimprovedsalpswarmalgorithm AT xiaogangdong twostagefeatureselectionforclassificationofgeneexpressiondatabasedonanimprovedsalpswarmalgorithm |