A Convolutional Deep Neural Network Approach for miRNA Clustering  

作　　者：Ghada Ali Mohamed Shommo Hadia Abbas Mohammed Elsied Amira Kamil Ibrahim Hassan Sara Elsir Mohamed Ahmed Lamia Hassan Rahmatalla Mohamed Wafa Faisal Mukhtar Ghada Ali Mohamed Shommo;Hadia Abbas Mohammed Elsied;Amira Kamil Ibrahim Hassan;Sara Elsir Mohamed Ahmed;Lamia Hassan Rahmatalla Mohamed;Wafa Faisal Mukhtar(Faculty of Computer Science & Information Technology, Sudan University of Science & Technology, Khartoum, Sudan;Faculty of Business Studies, Department of MIS, Sudan University of Science & Technology, Khartoum, Sudan;School of Management, Ahfad University for Women, Omdurman, Sudan;Department of Management Information Systems, College of Business Administration, King Faisal University, Hofuf, Saudi Arabia)

机构地区：[1]Faculty of Computer Science & Information Technology, Sudan University of Science & Technology, Khartoum, Sudan [2]Faculty of Business Studies, Department of MIS, Sudan University of Science & Technology, Khartoum, Sudan [3]School of Management, Ahfad University for Women, Omdurman, Sudan [4]Department of Management Information Systems, College of Business Administration, King Faisal University, Hofuf, Saudi Arabia

出　　处：《Communications and Network》2024年第4期135-148,共14页通讯与网络（英文）

摘　　要：The regulatory role of the Micro-RNAs (miRNAs) in the messenger RNAs (mRNAs) gene expression is well understood by the biologists since some decades, even though the delving into specific aspects is in progress. Clustering is a cornerstone in bioinformatics research, offering a potent computational tool for analyzing diverse types of data encountered in genomics and related fields. MiRNA clustering plays a pivotal role in deciphering the intricate regulatory roles of miRNAs in biological systems. It uncovers novel biomarkers for disease diagnosis and prognosis and advances our understanding of gene regulatory networks and pathways implicated in health and disease, as well as drug discovery. Namely, we have implemented clustering procedure to find interrelations among miRNAs within clusters, and their relations to diseases. Deep clustering (DC) algorithms signify a departure from traditional clustering methods towards more sophisticated techniques, that can uncover intricate patterns and relationships within gene expression data. Deep learning (DL) models have shown remarkable success in various domains, and their application in genomics, especially for tasks like clustering, holding immense promise. The deep convolutional clustering procedure used is different from other traditional methods, demonstrating unbiased clustering results. In the paper, we implement the procedure on a Multiple Myeloma miRNA dataset publicly available on GEO platform, as a template of a cancer instance analysis, and hazard some biological issues.The regulatory role of the Micro-RNAs (miRNAs) in the messenger RNAs (mRNAs) gene expression is well understood by the biologists since some decades, even though the delving into specific aspects is in progress. Clustering is a cornerstone in bioinformatics research, offering a potent computational tool for analyzing diverse types of data encountered in genomics and related fields. MiRNA clustering plays a pivotal role in deciphering the intricate regulatory roles of miRNAs in biological systems. It uncovers novel biomarkers for disease diagnosis and prognosis and advances our understanding of gene regulatory networks and pathways implicated in health and disease, as well as drug discovery. Namely, we have implemented clustering procedure to find interrelations among miRNAs within clusters, and their relations to diseases. Deep clustering (DC) algorithms signify a departure from traditional clustering methods towards more sophisticated techniques, that can uncover intricate patterns and relationships within gene expression data. Deep learning (DL) models have shown remarkable success in various domains, and their application in genomics, especially for tasks like clustering, holding immense promise. The deep convolutional clustering procedure used is different from other traditional methods, demonstrating unbiased clustering results. In the paper, we implement the procedure on a Multiple Myeloma miRNA dataset publicly available on GEO platform, as a template of a cancer instance analysis, and hazard some biological issues.

关 键 词：MIRNA Deep Clustering DeepTrust Convolutional Neural Network Recurrence Plot 

分 类 号：R73[医药卫生—肿瘤]