It is time to apply biclustering: a comprehensive review of biclustering applications in biological and biomedical data

Abstract

Biclustering is a powerful data mining technique that allows clustering of rows and columns, simultaneously, in a matrix-format data set. It was first applied to gene expression data in 2000, aiming to identify co-expressed genes under a subset of all the conditions/samples. During the past 17 years, tens of biclustering algorithms and tools have been developed to enhance the ability to make sense out of large data sets generated in the wake of high-throughput omics technologies. These algorithms and tools have been applied to a wide variety of data types, including but not limited to, genomes, transcriptomes, exomes, epigenomes, phenomes and pharmacogenomes. However, there is still a considerable gap between biclustering methodology development and comprehensive data interpretation, mainly because of the lack of knowledge for the selection of appropriate biclustering tools and further supporting computational techniques in specific studies. Here, we first deliver a brief introduction to the existing biclustering algorithms and tools in public domain, and then systematically summarize the basic applications of biclustering for biological data and more advanced applications of biclustering for biomedical data. This review will assist researchers to effectively analyze their big data and generate valuable biological knowledge and novel insights with higher efficiency.

Scalable biclustering — the future of big data exploration?

“…Biclustering has been successfully applied to hundreds of problems in the biological and biomedical domain and has supported detection of functional annotations (e.g., gene regulatory pathways), as well as biological interactions (e.g., transcriptional networks), the discovery of drugs and biomarkers, identification of subtypes of diseases, and analysis of responses to treatments [6]. A biclustering method has also helped to identify novel human microRNA regulatory modules [2].…”

“…This analytical technique of data mining, which is also known as subspace clustering, co-clustering, block clustering, or 2-mode clustering, has already become an essential tool for gene expression analysis because it is capable of capturing similar gene expression profiles under different subsets of experimental conditions [5]. It is not without reason that biclustering has found hundreds of applications in bioinformatics, and, as a result, there has been a call for increased use of this approach [6]. The era of biclustering big data has begun.…”

Identification of Differentially Expressed Gene Modules in Heterogeneous Diseases

“…However, class labels are not always available, and even if they are provided, some classes may be internally heterogeneous and consist of several latent molecular subtypes (McClellan and King, 2010;Perou et al, 2000). Biclustering methods (Pontes et al, 2015;Padilha and Campello, 2017;Xie et al, 2018) perform an unsupervised search for subsets of genes demonstrating similar expression patterns in a subset of samples, given a matrix of genes profiled in these samples. Since biclustering is a much more complex problem than clustering due to the much larger size of the search space, many biclustering methods put additional constraints on the input data or the biclustering result, e.g.…”

ORN: Extracting Latent Pathway Activities in Cancer with OR-gate Network

“…On the other hand, when modelling the mechanism from latent pathway activities to transcriptomics, a pathway perturbed in a set of patients will cause differential expression of a set of genes. In this way, ORN generates the bicluster patterns a plethora of clustering algorithms aimed to recover in RNA expression data (16).…”