View in EDS

M-GENE: Multiview genes expression network ensemble for bone metabolism-related gene classification.

Saved in:
Bibliographic Details
Title: M-GENE: Multiview genes expression network ensemble for bone metabolism-related gene classification.
Authors: Yu, Keyi1 (AUTHOR), Tan, Weilong1,2 (AUTHOR), Ge, Jirong1,3,4 (AUTHOR), Li, Xinyu5 (AUTHOR), Wang, Yingbei5 (AUTHOR), Huang, Jingwen3,4 (AUTHOR), Chen, Xuan3,4 (AUTHOR), Li, Shengqiang3,4 (AUTHOR), Zeng, Nianyin1,5 (AUTHOR) zny@xmu.edu.cn
Source: Neurocomputing. Mar2025, Vol. 622, pN.PAG-N.PAG. 1p.
Subjects: Gene regulatory networks, Gene expression, Data augmentation, Bone metabolism, Phenotypes
Abstract: In this paper, a novel multi-view gene expression network ensemble (M-GENE) pipeline has been proposed to predict correlations between genes and phenotypes using bulk RNA-seq gene expression data. The framework incorporates a preprocessing strategy that reshapes raw RNA-seq data into a structured format compatible with neural network training. To mitigate the effects of data imbalance, a refined application of SMOTE is employed, enhancing the uniformity of data distribution and addressing training bias. A multi-view domain alignment network further strengthens the model by identifying shared gene expression features under varying experimental conditions, enabling a comprehensive and accurate analysis. Extensive experiments validate M-GENE's superior accuracy and robustness, surpassing contemporary models and offering significant potential for practical applications. [ABSTRACT FROM AUTHOR]
Copyright of Neurocomputing is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Description
Abstract:In this paper, a novel multi-view gene expression network ensemble (M-GENE) pipeline has been proposed to predict correlations between genes and phenotypes using bulk RNA-seq gene expression data. The framework incorporates a preprocessing strategy that reshapes raw RNA-seq data into a structured format compatible with neural network training. To mitigate the effects of data imbalance, a refined application of SMOTE is employed, enhancing the uniformity of data distribution and addressing training bias. A multi-view domain alignment network further strengthens the model by identifying shared gene expression features under varying experimental conditions, enabling a comprehensive and accurate analysis. Extensive experiments validate M-GENE's superior accuracy and robustness, surpassing contemporary models and offering significant potential for practical applications. [ABSTRACT FROM AUTHOR]
ISSN:09252312
DOI:10.1016/j.neucom.2024.129318