期刊
EXPERT SYSTEMS WITH APPLICATIONS
卷 192, 期 -, 页码 -出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.eswa.2021.116336
关键词
Semi-supervised triclustering; Gene sample time data; Breast cancer data; Enrichment analysis; Hub gene identification; Pathway
Exploratory analysis of high throughput gene sample time data plays a crucial role in biomedical and bioinformatics research, providing insights into gene regulatory mechanisms and hidden biological knowledge. In this study, a novel semi-supervised Pathway-based Order Preserving Triclustering algorithm is proposed to identify different types of triclusters. Experimental results on artificial and real datasets, including breast cancer and HIV data, demonstrate the effectiveness of the algorithm.
Exploratory analysis of high throughput gene sample time (GST) data has an impact in biomedical and bioinformatics research. Mining gene expression pattern in such three dimensional data facilitate in understanding hidden biological knowledge as well as underlying complex gene regulatory mechanism. In particular, we propose a novel semi-supervised Pathway-based Order Preserving Triclustering (POPTric) algorithm which records gene expression pattern under subset of sample across subset of time points. Nowadays, integration of external knowledge has gaining popularity in the field of gene expression data analysis. Our algorithm is able to identify different types of triclusters such as additive, multiplicative, and additive-and-multiplicative triclusters. POPTric at first identifies biclusters and then it discovers triclusters from the 3D data. We apply our algorithm in artificial datasets as well as breast cancer, HIV datasets, and compare with other state-of-the-art methods. To establish the biological significance of proposed algorithm we perform Gene Ontology enrichment analysis. We also identify hub genes from the tricluster which are previously known to be associated with breast cancer.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据