Abstract
Selection of biologically relevant genes from high-dimensional expression data is a key research problem in gene expression genomics. Most of the available gene selection methods are either based on relevancy or redundancy measure, which are usually adjudged through post selection classification accuracy. Through these methods the ranking of genes was conducted on a single high-dimensional expression data, which led to the selection of spuriously associated and redundant genes. Hence, we developed a statistical approach through combining a support vector machine with Maximum Relevance and Minimum Redundancy under a sound statistical setup for the selection of biologically relevant genes. Here, the genes were selected through statistical significance values and computed using a nonparametric test statistic under a bootstrap-based subject sampling model. Further, a systematic and rigorous evaluation of the proposed approach with nine existing competitive methods was carried on six different real crop gene expression datasets. This performance analysis was carried out under three comparison settings, i.e., subject classification, biological relevant criteria based on quantitative trait loci and gene ontology. Our analytical results showed that the proposed approach selects genes which are more biologically relevant as compared to the existing methods. Moreover, the proposed approach was also found to be better with respect to the competitive existing methods. The proposed statistical approach provides a framework for combining filter and wrapper methods of gene selection.
Highlights
The emergence of high-throughput sequencing technologies exponentially increase the size of output data in genome sciences with respect to a number of features [1]
The distributions of weights computed from Support Vector Machine (SVM)-Maximum Relevance and Minimum Redundancy (MRMR) method [13] and adj. p-values for genes computed from the proposed BSM approach for abiotic and biotic stresses in rice are shown in Figure 2 and Figure S3, respectively
From the distribution of adj. p-values computed through the proposed approach, it was observed that the relevant genes were well separated from the irrelevant genes, and a small number of genes found to be statistically significant (Figure 2(A1))
Summary
The emergence of high-throughput sequencing technologies exponentially increase the size of output data in genome sciences with respect to a number of features [1]. GEO, ArrayExpress, etc., over the years by researchers across the globe [4,5] These publicly available high-throughput data need to be analyzed in order to gain valid biological insights. One such aspect of this research is to select genes, which are highly relevant to the phenotype/trait under study, out of several thousands of genes in the data. This is called feature selection in machine learning in general and gene selection in genomics [5,6,7]. The selected genes can be used as predictors for other predictive analysis, i.e., subjects classification [7,8,11], gene regulation modeling [14], gene network analysis [5,6], etc., which enhances the stability, power and feasibility of the developed models [15]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
