Deep learning approach for cancer subtype classification using high-dimensional gene expression data
Abstract Motivation Studies have shown that classifying cancer subtypes can provide valuable information for a range of cancer research, from aetiology and tumour biology to prognosis and personalized treatment. Current methods usually adopt gene expression data to perform cancer subtype classificat...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2022-10-01
|
Series: | BMC Bioinformatics |
Subjects: | |
Online Access: | https://doi.org/10.1186/s12859-022-04980-9 |
_version_ | 1811250038140043264 |
---|---|
author | Jiquan Shen Jiawei Shi Junwei Luo Haixia Zhai Xiaoyan Liu Zhengjiang Wu Chaokun Yan Huimin Luo |
author_facet | Jiquan Shen Jiawei Shi Junwei Luo Haixia Zhai Xiaoyan Liu Zhengjiang Wu Chaokun Yan Huimin Luo |
author_sort | Jiquan Shen |
collection | DOAJ |
description | Abstract Motivation Studies have shown that classifying cancer subtypes can provide valuable information for a range of cancer research, from aetiology and tumour biology to prognosis and personalized treatment. Current methods usually adopt gene expression data to perform cancer subtype classification. However, cancer samples are scarce, and the high-dimensional features of their gene expression data are too sparse to allow most methods to achieve desirable classification results. Results In this paper, we propose a deep learning approach by combining a convolutional neural network (CNN) and bidirectional gated recurrent unit (BiGRU): our approach, DCGN, aims to achieve nonlinear dimensionality reduction and learn features to eliminate irrelevant factors in gene expression data. Specifically, DCGN first uses the synthetic minority oversampling technique algorithm to equalize data. The CNN can handle high-dimensional data without stress and extract important local features, and the BiGRU can analyse deep features and retain their important information; the DCGN captures key features by combining both neural networks to overcome the challenges of small sample sizes and sparse, high-dimensional features. In the experiments, we compared the DCGN to seven other cancer subtype classification methods using breast and bladder cancer gene expression datasets. The experimental results show that the DCGN performs better than the other seven methods and can provide more satisfactory classification results. |
first_indexed | 2024-04-12T15:58:11Z |
format | Article |
id | doaj.art-5564e7ab413d4eb899bb87a30a201721 |
institution | Directory Open Access Journal |
issn | 1471-2105 |
language | English |
last_indexed | 2024-04-12T15:58:11Z |
publishDate | 2022-10-01 |
publisher | BMC |
record_format | Article |
series | BMC Bioinformatics |
spelling | doaj.art-5564e7ab413d4eb899bb87a30a2017212022-12-22T03:26:18ZengBMCBMC Bioinformatics1471-21052022-10-0123111710.1186/s12859-022-04980-9Deep learning approach for cancer subtype classification using high-dimensional gene expression dataJiquan Shen0Jiawei Shi1Junwei Luo2Haixia Zhai3Xiaoyan Liu4Zhengjiang Wu5Chaokun Yan6Huimin Luo7School of Software, Henan Polytechnic UniversitySchool of Software, Henan Polytechnic UniversitySchool of Software, Henan Polytechnic UniversitySchool of Software, Henan Polytechnic UniversitySchool of Software, Henan Polytechnic UniversitySchool of Software, Henan Polytechnic UniversitySchool of Computer and Information Engineering, Henan UniversitySchool of Computer and Information Engineering, Henan UniversityAbstract Motivation Studies have shown that classifying cancer subtypes can provide valuable information for a range of cancer research, from aetiology and tumour biology to prognosis and personalized treatment. Current methods usually adopt gene expression data to perform cancer subtype classification. However, cancer samples are scarce, and the high-dimensional features of their gene expression data are too sparse to allow most methods to achieve desirable classification results. Results In this paper, we propose a deep learning approach by combining a convolutional neural network (CNN) and bidirectional gated recurrent unit (BiGRU): our approach, DCGN, aims to achieve nonlinear dimensionality reduction and learn features to eliminate irrelevant factors in gene expression data. Specifically, DCGN first uses the synthetic minority oversampling technique algorithm to equalize data. The CNN can handle high-dimensional data without stress and extract important local features, and the BiGRU can analyse deep features and retain their important information; the DCGN captures key features by combining both neural networks to overcome the challenges of small sample sizes and sparse, high-dimensional features. In the experiments, we compared the DCGN to seven other cancer subtype classification methods using breast and bladder cancer gene expression datasets. The experimental results show that the DCGN performs better than the other seven methods and can provide more satisfactory classification results.https://doi.org/10.1186/s12859-022-04980-9Cancer subtypeClassificationDeep learning |
spellingShingle | Jiquan Shen Jiawei Shi Junwei Luo Haixia Zhai Xiaoyan Liu Zhengjiang Wu Chaokun Yan Huimin Luo Deep learning approach for cancer subtype classification using high-dimensional gene expression data BMC Bioinformatics Cancer subtype Classification Deep learning |
title | Deep learning approach for cancer subtype classification using high-dimensional gene expression data |
title_full | Deep learning approach for cancer subtype classification using high-dimensional gene expression data |
title_fullStr | Deep learning approach for cancer subtype classification using high-dimensional gene expression data |
title_full_unstemmed | Deep learning approach for cancer subtype classification using high-dimensional gene expression data |
title_short | Deep learning approach for cancer subtype classification using high-dimensional gene expression data |
title_sort | deep learning approach for cancer subtype classification using high dimensional gene expression data |
topic | Cancer subtype Classification Deep learning |
url | https://doi.org/10.1186/s12859-022-04980-9 |
work_keys_str_mv | AT jiquanshen deeplearningapproachforcancersubtypeclassificationusinghighdimensionalgeneexpressiondata AT jiaweishi deeplearningapproachforcancersubtypeclassificationusinghighdimensionalgeneexpressiondata AT junweiluo deeplearningapproachforcancersubtypeclassificationusinghighdimensionalgeneexpressiondata AT haixiazhai deeplearningapproachforcancersubtypeclassificationusinghighdimensionalgeneexpressiondata AT xiaoyanliu deeplearningapproachforcancersubtypeclassificationusinghighdimensionalgeneexpressiondata AT zhengjiangwu deeplearningapproachforcancersubtypeclassificationusinghighdimensionalgeneexpressiondata AT chaokunyan deeplearningapproachforcancersubtypeclassificationusinghighdimensionalgeneexpressiondata AT huiminluo deeplearningapproachforcancersubtypeclassificationusinghighdimensionalgeneexpressiondata |