Protein secondary structure prediction based on Wasserstein generative adversarial networks and temporal convolutional networks with convolutional block attention modules
As an important task in bioinformatics, protein secondary structure prediction (PSSP) is not only beneficial to protein function research and tertiary structure prediction, but also to promote the design and development of new drugs. However, current PSSP methods cannot sufficiently extract effectiv...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2023-01-01
|
| Series: | Mathematical Biosciences and Engineering |
| Subjects: | |
| Online Access: | https://www.aimspress.com/article/doi/10.3934/mbe.2023102?viewType=HTML |
| _version_ | 1811175550651203584 |
|---|---|
| author | Lu Yuan Yuming Ma Yihui Liu |
| author_facet | Lu Yuan Yuming Ma Yihui Liu |
| author_sort | Lu Yuan |
| collection | DOAJ |
| description | As an important task in bioinformatics, protein secondary structure prediction (PSSP) is not only beneficial to protein function research and tertiary structure prediction, but also to promote the design and development of new drugs. However, current PSSP methods cannot sufficiently extract effective features. In this study, we propose a novel deep learning model WGACSTCN, which combines Wasserstein generative adversarial network with gradient penalty (WGAN-GP), convolutional block attention module (CBAM) and temporal convolutional network (TCN) for 3-state and 8-state PSSP. In the proposed model, the mutual game of generator and discriminator in WGAN-GP module can effectively extract protein features, and our CBAM-TCN local extraction module can capture key deep local interactions in protein sequences segmented by sliding window technique, and the CBAM-TCN long-range extraction module can further capture the key deep long-range interactions in sequences. We evaluate the performance of the proposed model on seven benchmark datasets. Experimental results show that our model exhibits better prediction performance compared to the four state-of-the-art models. The proposed model has strong feature extraction ability, which can extract important information more comprehensively. |
| first_indexed | 2024-04-10T19:37:37Z |
| format | Article |
| id | doaj.art-5f25209f3e42461e980f4bc8dc1116e1 |
| institution | Directory Open Access Journal |
| issn | 1551-0018 |
| language | English |
| last_indexed | 2024-04-10T19:37:37Z |
| publishDate | 2023-01-01 |
| publisher | AIMS Press |
| record_format | Article |
| series | Mathematical Biosciences and Engineering |
| spelling | doaj.art-5f25209f3e42461e980f4bc8dc1116e12023-01-30T00:55:53ZengAIMS PressMathematical Biosciences and Engineering1551-00182023-01-012022203221810.3934/mbe.2023102Protein secondary structure prediction based on Wasserstein generative adversarial networks and temporal convolutional networks with convolutional block attention modulesLu Yuan0Yuming Ma1Yihui Liu2School of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaSchool of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaSchool of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaAs an important task in bioinformatics, protein secondary structure prediction (PSSP) is not only beneficial to protein function research and tertiary structure prediction, but also to promote the design and development of new drugs. However, current PSSP methods cannot sufficiently extract effective features. In this study, we propose a novel deep learning model WGACSTCN, which combines Wasserstein generative adversarial network with gradient penalty (WGAN-GP), convolutional block attention module (CBAM) and temporal convolutional network (TCN) for 3-state and 8-state PSSP. In the proposed model, the mutual game of generator and discriminator in WGAN-GP module can effectively extract protein features, and our CBAM-TCN local extraction module can capture key deep local interactions in protein sequences segmented by sliding window technique, and the CBAM-TCN long-range extraction module can further capture the key deep long-range interactions in sequences. We evaluate the performance of the proposed model on seven benchmark datasets. Experimental results show that our model exhibits better prediction performance compared to the four state-of-the-art models. The proposed model has strong feature extraction ability, which can extract important information more comprehensively.https://www.aimspress.com/article/doi/10.3934/mbe.2023102?viewType=HTMLprotein secondary structure predictionwasserstein generative adversarial networkconvolutional block attention moduletemporal convolutional networkfeature extraction |
| spellingShingle | Lu Yuan Yuming Ma Yihui Liu Protein secondary structure prediction based on Wasserstein generative adversarial networks and temporal convolutional networks with convolutional block attention modules Mathematical Biosciences and Engineering protein secondary structure prediction wasserstein generative adversarial network convolutional block attention module temporal convolutional network feature extraction |
| title | Protein secondary structure prediction based on Wasserstein generative adversarial networks and temporal convolutional networks with convolutional block attention modules |
| title_full | Protein secondary structure prediction based on Wasserstein generative adversarial networks and temporal convolutional networks with convolutional block attention modules |
| title_fullStr | Protein secondary structure prediction based on Wasserstein generative adversarial networks and temporal convolutional networks with convolutional block attention modules |
| title_full_unstemmed | Protein secondary structure prediction based on Wasserstein generative adversarial networks and temporal convolutional networks with convolutional block attention modules |
| title_short | Protein secondary structure prediction based on Wasserstein generative adversarial networks and temporal convolutional networks with convolutional block attention modules |
| title_sort | protein secondary structure prediction based on wasserstein generative adversarial networks and temporal convolutional networks with convolutional block attention modules |
| topic | protein secondary structure prediction wasserstein generative adversarial network convolutional block attention module temporal convolutional network feature extraction |
| url | https://www.aimspress.com/article/doi/10.3934/mbe.2023102?viewType=HTML |
| work_keys_str_mv | AT luyuan proteinsecondarystructurepredictionbasedonwassersteingenerativeadversarialnetworksandtemporalconvolutionalnetworkswithconvolutionalblockattentionmodules AT yumingma proteinsecondarystructurepredictionbasedonwassersteingenerativeadversarialnetworksandtemporalconvolutionalnetworkswithconvolutionalblockattentionmodules AT yihuiliu proteinsecondarystructurepredictionbasedonwassersteingenerativeadversarialnetworksandtemporalconvolutionalnetworkswithconvolutionalblockattentionmodules |