Rough hypercuboid based supervised clustering of miRNAs

Abstract

The microRNAs are small, endogenous non-coding RNAs found in plants, animals, and some viruses, which function in RNA silencing and post-transcriptional regulation of gene expression. It is suggested by various genome-wide studies that a substantial fraction of miRNA genes is likely to form clusters. The coherent expression of the miRNA clusters can then be used to classify samples according to the clinical outcome. In this regard, a new clustering algorithm, termed as rough hypercuboid based supervised attribute clustering (RH-SAC), is proposed to find such groups of miRNAs. The proposed algorithm is based on the theory of rough set, which directly incorporates the information of sample categories into the miRNA clustering process, generating a supervised clustering algorithm for miRNAs.The effectiveness of the new approach is demonstrated on several publicly available miRNA expression data sets using support vector machine. The so-called B.632+ bootstrap error estimate is used to minimize the variability and biasedness of the derived results. The association of the miRNA clusters to various biological pathways is also shown by doing pathway enrichment analysis.

Identification of miRNA-mRNA Modules in Colorectal Cancer Using Rough Hypercuboid Based Supervised Clustering

“…The rough hypercuboid based supervised clustering (RH-SAC) 36 algorithm has been used to select potential rules/clusters of miRNAs/mRNAs. This algorithm discovers groups of biomarkers, which are not only functionally similar but their average expression values can efficiently discriminate samples.…”

“…The relevance uses information about the class labels and is thus a criterion for supervised clustering. It is a metric that helps to judge the discriminatory capability of a feature 36 . It’s value ranges from 0 to 1.…”

“…They were also used to design methods to select differentially expressed miRNAs 31 34 and to clustering functionally similar miRNAs 35 . A supervised clustering method 36 based on rough sets has been also developed to group miRNAs whose average expression could further classify clinical outcome.…”

“…In this paper, we present a computational approach to identify miRNA-mRNA modules in CRC. It is a two step approach, at first miRNA rules/clusters were generated using the rough hypercuboid based supervised clustering algorithm 36 (RH-SAC). Instead of selecting single miRNAs or mRNAs based on certain criteria as described by Fu et al .…”

Rough Hypercuboid Based Supervised Regularized Canonical Correlation for Multimodal Data Analysis*

“…The concept of hypercuboid equivalence partition matrix [32] of rough hypercuboid is useful to compute the degree of dependency of class labels or decision attribute set on the condition attribute or feature set having numerical values. Rough set theory and its several variants have been successfully applied to omics data analysis [33,34,35,36,20,37,38,39,40,41,42,43,44,45,46,47].…”