2018/11/23 by Amina Houari, Houari, Amina, A. El Houari
Computer Science · #Rough Sets and Fuzzy Logic #Neural Networks and Applications #Data Mining Algorithms and Applications
paper · pdf · doi:10.48550/arxiv.1811.09562
Biclustering is an unsupervised data mining technique that aims to unveil\npatterns (biclusters) from gene expression data matrices. In the framework of\nthis thesis, we propose new biclustering algorithms for microarray data. The\nlatter is done using data mining techniques. The objective is to identify\npositively and negatively correlated biclusters.\n This thesis is divided into two part: In the first part, we present an\noverview of the pattern-mining techniques and the biclustering of microarray\ndata. In the second part, we present our proposed biclustering algorithms where\nwe rely on two axes. In the first axis, we initially focus on extracting\nbiclusters of positive correlations. For this, we use both Formal Concept\nAnalysis and Association Rules. In the second axis, we focus on the extraction\nof negatively correlated biclusters.\n The performed experimental studies highlight the very promising results\noffered by the proposed algorithms. Our biclustering algorithms are evaluated\nand compared statistically and biologically.\n