A semi-supervised approach for the integration of multi-omics data based on transformer multi-head self-attention mechanism and graph convolutional networks.

Wang, Jiahui; Liao, Nanqing; Du, Xiaofei; Chen, Qingfeng; Wei, Bizhong

Wang, Jiahui; Liao, Nanqing; Du, Xiaofei; Chen, Qingfeng; Wei, Bizhong.

Afiliación

Wang J; School of Computer and Information Security, Guilin University of Electronic Technology, No. 1 Jinji Road, Guilin City, 541004, Guangxi Zhuang Autonomous Region, China.
Liao N; School of Medical, Guangxi University, No. 100 East University Road, Nanning, 530004, Guangxi, China.
Du X; School of Computer and Information Security, Guilin University of Electronic Technology, No. 1 Jinji Road, Guilin City, 541004, Guangxi Zhuang Autonomous Region, China.
Chen Q; School of Computer, Electronics and Information, Guangxi University, No. 100 East University Road, Nanning, 530004, Guangxi, China. qingfeng@gxu.edu.cn.
Wei B; School of Computer and Information Security, Guilin University of Electronic Technology, No. 1 Jinji Road, Guilin City, 541004, Guangxi Zhuang Autonomous Region, China. wbz@guet.edu.cn.

BMC Genomics ; 25(1): 86, 2024 Jan 22.

Article en En | MEDLINE | ID: mdl-38254021

ABSTRACT

ABSTRACT

BACKGROUND AND

OBJECTIVES:

Comprehensive analysis of multi-omics data is crucial for accurately formulating effective treatment plans for complex diseases. Supervised ensemble methods have gained popularity in recent years for multi-omics data analysis. However, existing research based on supervised learning algorithms often fails to fully harness the information from unlabeled nodes and overlooks the latent features within and among different omics, as well as the various associations among features. Here, we present a novel multi-omics integrative method MOSEGCN, based on the Transformer multi-head self-attention mechanism and Graph Convolutional Networks(GCN), with the aim of enhancing the accuracy of complex disease classification. MOSEGCN first employs the Transformer multi-head self-attention mechanism and Similarity Network Fusion (SNF) to separately learn the inherent correlations of latent features within and among different omics, constructing a comprehensive view of diseases. Subsequently, it feeds the learned crucial information into a self-ensembling Graph Convolutional Network (SEGCN) built upon semi-supervised learning methods for training and testing, facilitating a better analysis and utilization of information from multi-omics data to achieve precise classification of disease subtypes.

RESULTS:

The experimental results show that MOSEGCN outperforms several state-of-the-art multi-omics integrative analysis approaches on three types of omics data mRNA expression data, microRNA expression data, and DNA methylation data, with accuracy rates of 83.0% for Alzheimer's disease and 86.7% for breast cancer subtyping. Furthermore, MOSEGCN exhibits strong generalizability on the GBM dataset, enabling the identification of important biomarkers for related diseases.

CONCLUSION:

MOSEGCN explores the significant relationship information among different omics and within each omics' latent features, effectively leveraging labeled and unlabeled information to further enhance the accuracy of complex disease classification. It also provides a promising approach for identifying reliable biomarkers, paving the way for personalized medicine.

Asunto(s)

Enfermedad de Alzheimer; Multiómica; Humanos; Metilación de ADN; Algoritmos; Biomarcadores

Palabras clave

Graph Convolutional Networks; Multi-head self-attention mechanism; Multi-omics; Semi-supervised learning

Texto completo

Añadir a Mi BVS

Imprimir

XML

PubMed Links

Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Enfermedad de Alzheimer / Multiómica Límite: Humans Idioma: En Revista: BMC Genomics Asunto de la revista: GENETICA Año: 2024 Tipo del documento: Article País de afiliación: China Pais de publicación: Reino Unido

Texto completo

Añadir a Mi BVS

Imprimir

XML

PubMed Links

Buscar en Google