22 November 2017 in BMC Bioinformatics
Classification of biological samples of gene expression data is a basic building block in solving several problems in the field of bioinformatics like cancer and other disease diagnosis and making a proper treatment plan. One big challenge in sample classification is handling large dimensional and redundant gene expression data. To reduce the complexity of handling this high dimensional data, gene/feature selection plays a major role. The current paper explores the use of biological knowledge acquired from Gene Ontology database in selecting the proper subset of genes which can further participate in clustering of samples. The proposed feature selection technique is unsupervised in nature as it does not utilize any class label information in the process of gene selection. At the end, a multi-objective clustering approach is deployed to cluster the available set of samples in the reduced gene space. Reported results show that consideration of biological knowledge in gene selection technique not only reduces the feature space dimensionality in great extent but also improves the accuracy of sample classification. The obtained reduced gene space is validated using strong biological significance tests. In order to prove the supremacy of our proposed gene selection based sample clustering technique, a thorough comparative analysis has also been performed with state-of-the-art techniques.
6 November 2020 in IEEE Transactions on Knowledge and Data Engineering
In the era of big data, data analysis of high-dimensional data-sets often suffers from Curse-of-dimensionality. In the current article, we propose a dimensionality-reduction method through feature selection from high-dimensional gene expression (GE) data-set using a Multi-objective optimization based Multi-view Co-Clustering algorithm (named M2Co-Clus). A popular evolutionary technique- Non-dominated Sorting Genetic Algorithm-II or NSGA-II has been utilized as the underlying optimization strategy of the proposed method. First, we construct two views of the chosen data-set, utilizing knowledge from two different biological data sources. Next, we develop the M2Co-Clus algorithm considering the constructed views to identify a set of good co-clustering solutions. Finally, based on a concept of consensus operation on co-clustering outcome, a small number of most relevant and non-redundant features are extracted from the original feature-space. The reduced dimension formed by new feature-space causes to decrease the computational burden and noise level of original data. For experimental analysis, we have chosen three benchmark GE data-sets. Our feature selection strategy's effectiveness is evaluated through sample-classification accuracy, accompanied by visualization tests like cluster profile plot/Eisen plot, and biological significance test. A thorough comparative analysis with existing feature selection algorithms using external and internal evaluation metrics supports the potency of our proposed method.
16 June 2023 in Expert Systems with Applications
9 May 2018 in Soft Computing
12 July 2018 in Expert Systems with Applications