High-throughput Analysis Of Biomolecular Data Using Multiple Hierarchical Consensus Clustering

Thanks to the development of high-throughput sequencing technologies,massive amounts of various biomolecular data have been accumulated to revolutionize the study of genomics and molecular biology.One of the main challenges in analyzing this biomolecular data is to cluster their subtypes into subpopulations to facilitate subsequent downstream analysis.Recently,many clustering methods have been developed to address the biomolecular data.However,the computational methods often suffer from many limitations such as high dimensionality,data heterogeneity and noise.This paper developed a novel Graph-based Multiple Hierarchical Consensus Clustering(GMHCC)method with an unsupervised graph-based feature ranking and a graph-based linking method to explore the multiple hierarchical information of the underlying partitions of the consensus clustering for multiple types of biomolecular data.Indeed,this paper first proposed to use a graph-based unsupervised feature ranking model to measure each feature by building a graph over pairwise features and then providing each feature with a rank.Subsequently,to maintain the diversity and robustness of basic partitions,this paper proposed multiple diverse feature subsets to generate several basic partitions and then explore the hierarchical structures of the multiple basic partitions by refining the global consensus function.Finally,this paper developed a new graph-based linking method,which explicitly considers the relationships between clusters to generate the final partition.Experiments on multiple types of biomolecular data including thirty-five cancer gene expression datasets and eight single-cell RNA-seq datasets validate the effectiveness of our method over several state-of-the-art consensus clustering approaches.Furthermore,differential gene analysis,gene ontology enrichment analysis,and KEGG pathway analysis are conducted,providing novel insights into cell developmental lineages and characterization mechanisms.Furthermore,based on the proposed unsupervised feature ranking method,by introducing a local weighting strategy,this paper also proposed a Locally weighted Multiple Hierarchical Consensus Clustering(LMHCC)method.The cluster validity index is calculated by measuring the cluster uncertainty(entropy),and the co-association matrix is improved to promote the clustering performance of consensus clustering.Experimental results on multiple single-cell RNA-seq datasets show that compared with other integrated clustering algorithms,single-cell data clustering algorithms,and deep learning algorithms,the LMHCC proposed in this paper has more performance advantages.