An Ensemble Deep Learning Model with a Gene Attention Mechanism for Estimating the Prognosis of Low-Grade Glioma
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Minhyeok | - |
dc.date.accessioned | 2023-03-08T07:49:14Z | - |
dc.date.available | 2023-03-08T07:49:14Z | - |
dc.date.issued | 2022-04 | - |
dc.identifier.issn | 2079-7737 | - |
dc.identifier.issn | 2079-7737 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/61475 | - |
dc.description.abstract | Simple Summary This paper proposes a deep learning model for prognosis estimation and an attention mechanism for gene expression. In the prognosis estimation of low-grade glioma (LGG), the proposed model, Gene Attention Ensemble NETwork (GAENET), demonstrated superior performance compared to conventional models, where GAENET exhibited an improvement of 7.2% compared to the second-best model. By the proposed gene attention, HILS1 was discovered as the most significant prognostic gene for LGG. While HILS1 is classified as a pseudogene, it functions as a biomarker for predicting the prognosis of LGG and has been shown to have the ability to regulate the expression of other prognostic genes. 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, HILS1 was discovered as the most significant prognostic gene in terms of deep learning training. While HILS1 is known as a pseudogene, HILS1 is a biomarker estimating the prognosis of LGG and has demonstrated a possibility of regulating the expression of other prognostic genes. | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | MDPI | - |
dc.title | An Ensemble Deep Learning Model with a Gene Attention Mechanism for Estimating the Prognosis of Low-Grade Glioma | - |
dc.type | Article | - |
dc.identifier.doi | 10.3390/biology11040586 | - |
dc.identifier.bibliographicCitation | BIOLOGY-BASEL, v.11, no.4 | - |
dc.description.isOpenAccess | Y | - |
dc.identifier.wosid | 000785357000001 | - |
dc.identifier.scopusid | 2-s2.0-85129227882 | - |
dc.citation.number | 4 | - |
dc.citation.title | BIOLOGY-BASEL | - |
dc.citation.volume | 11 | - |
dc.type.docType | Article | - |
dc.publisher.location | 스위스 | - |
dc.subject.keywordAuthor | survival estimation | - |
dc.subject.keywordAuthor | prognosis estimation | - |
dc.subject.keywordAuthor | deep learning | - |
dc.subject.keywordAuthor | attention mechanism | - |
dc.subject.keywordAuthor | gene expression | - |
dc.subject.keywordAuthor | low-grade glioma | - |
dc.subject.keywordAuthor | HILS1 | - |
dc.subject.keywordPlus | SURVIVAL | - |
dc.subject.keywordPlus | SIGNATURE | - |
dc.relation.journalResearchArea | Life Sciences & Biomedicine - Other Topics | - |
dc.relation.journalWebOfScienceCategory | Biology | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
84, Heukseok-ro, Dongjak-gu, Seoul, Republic of Korea (06974)02-820-6194
COPYRIGHT 2019 Chung-Ang University All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.