An Ensemble Deep Learning Model with a Gene Attention Mechanism for Estimating the Prognosis of Low-Grade Glioma
While estimating the prognosis of low-grade glioma (LGG) is a crucial problem, it has not been extensively studied to introduce recent improvements in deep learning to address the problem. The attention mechanism is one of the significant advances; however, it is still unclear how attention mechanis...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Biology |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-7737/11/4/586 |
| _version_ | 1797436808092450816 |
|---|---|
| author | Minhyeok Lee |
| author_facet | Minhyeok Lee |
| author_sort | Minhyeok Lee |
| collection | DOAJ |
| description | While estimating the prognosis of low-grade glioma (LGG) is a crucial problem, it has not been extensively studied to introduce recent improvements in deep learning to address the problem. The attention mechanism is one of the significant advances; however, it is still unclear how attention mechanisms are used in gene expression data to estimate prognosis because they were designed for convolutional layers and word embeddings. This paper proposes an attention mechanism called gene attention for gene expression data. Additionally, a deep learning model for prognosis estimation of LGG is proposed using gene attention. The proposed Gene Attention Ensemble NETwork (GAENET) outperformed other conventional methods, including survival support vector machine and random survival forest. When evaluated by C-Index, the GAENET exhibited an improvement of 7.2% compared to the second-best model. In addition, taking advantage of the gene attention mechanism, <i>HILS1</i> was discovered as the most significant prognostic gene in terms of deep learning training. While <i>HILS1</i> is known as a pseudogene, <i>HILS1</i> is a biomarker estimating the prognosis of LGG and has demonstrated a possibility of regulating the expression of other prognostic genes. |
| first_indexed | 2024-03-09T11:07:57Z |
| format | Article |
| id | doaj.art-3cb34a6c24834494b5a836e9a6822cb1 |
| institution | Directory Open Access Journal |
| issn | 2079-7737 |
| language | English |
| last_indexed | 2024-03-09T11:07:57Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biology |
| spelling | doaj.art-3cb34a6c24834494b5a836e9a6822cb12023-12-01T00:51:56ZengMDPI AGBiology2079-77372022-04-0111458610.3390/biology11040586An Ensemble Deep Learning Model with a Gene Attention Mechanism for Estimating the Prognosis of Low-Grade GliomaMinhyeok Lee0School of Electrical and Electronics Engineering, Chung-Ang University, Seoul 06974, KoreaWhile estimating the prognosis of low-grade glioma (LGG) is a crucial problem, it has not been extensively studied to introduce recent improvements in deep learning to address the problem. The attention mechanism is one of the significant advances; however, it is still unclear how attention mechanisms are used in gene expression data to estimate prognosis because they were designed for convolutional layers and word embeddings. This paper proposes an attention mechanism called gene attention for gene expression data. Additionally, a deep learning model for prognosis estimation of LGG is proposed using gene attention. The proposed Gene Attention Ensemble NETwork (GAENET) outperformed other conventional methods, including survival support vector machine and random survival forest. When evaluated by C-Index, the GAENET exhibited an improvement of 7.2% compared to the second-best model. In addition, taking advantage of the gene attention mechanism, <i>HILS1</i> was discovered as the most significant prognostic gene in terms of deep learning training. While <i>HILS1</i> is known as a pseudogene, <i>HILS1</i> is a biomarker estimating the prognosis of LGG and has demonstrated a possibility of regulating the expression of other prognostic genes.https://www.mdpi.com/2079-7737/11/4/586survival estimationprognosis estimationdeep learningattention mechanismgene expressionlow-grade glioma |
| spellingShingle | Minhyeok Lee An Ensemble Deep Learning Model with a Gene Attention Mechanism for Estimating the Prognosis of Low-Grade Glioma Biology survival estimation prognosis estimation deep learning attention mechanism gene expression low-grade glioma |
| title | An Ensemble Deep Learning Model with a Gene Attention Mechanism for Estimating the Prognosis of Low-Grade Glioma |
| title_full | An Ensemble Deep Learning Model with a Gene Attention Mechanism for Estimating the Prognosis of Low-Grade Glioma |
| title_fullStr | An Ensemble Deep Learning Model with a Gene Attention Mechanism for Estimating the Prognosis of Low-Grade Glioma |
| title_full_unstemmed | An Ensemble Deep Learning Model with a Gene Attention Mechanism for Estimating the Prognosis of Low-Grade Glioma |
| title_short | An Ensemble Deep Learning Model with a Gene Attention Mechanism for Estimating the Prognosis of Low-Grade Glioma |
| title_sort | ensemble deep learning model with a gene attention mechanism for estimating the prognosis of low grade glioma |
| topic | survival estimation prognosis estimation deep learning attention mechanism gene expression low-grade glioma |
| url | https://www.mdpi.com/2079-7737/11/4/586 |
| work_keys_str_mv | AT minhyeoklee anensembledeeplearningmodelwithageneattentionmechanismforestimatingtheprognosisoflowgradeglioma AT minhyeoklee ensembledeeplearningmodelwithageneattentionmechanismforestimatingtheprognosisoflowgradeglioma |