Dataset Information

Ensemble Feature Learning of Genomic Data Using Support Vector Machine.

ABSTRACT: The identification of a subset of genes having the ability to capture the necessary information to distinguish classes of patients is crucial in bioinformatics applications. Ensemble and bagging methods have been shown to work effectively in the process of gene selection and classification. Testament to that is random forest which combines random decision trees with bagging to improve overall feature selection and classification accuracy. Surprisingly, the adoption of these methods in support vector machines has only recently received attention but mostly on classification not gene selection. This paper introduces an ensemble SVM-Recursive Feature Elimination (ESVM-RFE) for gene selection that follows the concepts of ensemble and bagging used in random forest but adopts the backward elimination strategy which is the rationale of RFE algorithm. The rationale behind this is, building ensemble SVM models using randomly drawn bootstrap samples from the training set, will produce different feature rankings which will be subsequently aggregated as one feature ranking. As a result, the decision for elimination of features is based upon the ranking of multiple SVM models instead of choosing one particular model. Moreover, this approach will address the problem of imbalanced datasets by constructing a nearly balanced bootstrap sample. Our experiments show that ESVM-RFE for gene selection substantially increased the classification performance on five microarray datasets compared to state-of-the-art methods. Experiments on the childhood leukaemia dataset show that an average 9% better accuracy is achieved by ESVM-RFE over SVM-RFE, and 5% over random forest based approach. The selected genes by the ESVM-RFE algorithm were further explored with Singular Value Decomposition (SVD) which reveals significant clusters with the selected data.

SUBMITTER: Anaissi A

PROVIDER: S-EPMC4909287 | biostudies-literature | 2016

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Ensemble Feature Learning of Genomic Data Using Support Vector Machine.

Anaissi Ali A Goyal Madhu M Catchpoole Daniel R DR Braytee Ali A Kennedy Paul J PJ

PloS one 20160615 6

The identification of a subset of genes having the ability to capture the necessary information to distinguish classes of patients is crucial in bioinformatics applications. Ensemble and bagging methods have been shown to work effectively in the process of gene selection and classification. Testament to that is random forest which combines random decision trees with bagging to improve overall feature selection and classification accuracy. Surprisingly, the adoption of these methods in support ve ...[more]

PMID: 27304923

Similar Datasets

Project description:Biological data are accumulating at a faster rate, but interpreting them still remains a problem. Classifying biological data into distinct groups is the first step in understanding them. Data classification in response to a certain treatment is an extremely important aspect for differentially expressed genes in making present/absent calls. Many feature selection algorithms have been developed including the support vector machine recursive feature elimination procedure (SVM-RFE) and its variants. Support vector machine RFEs are greedy methods that attempt to find superlative possible combinations leading to binary classification, which may not be biologically significant. To overcome this limitation of SVM-RFE, we propose a novel feature selection algorithm, termed as "sigFeature" (https://bioconductor.org/packages/sigFeature/), based on SVM and t statistic to discover the differentially significant features along with good performance in classification. The "sigFeature" R package is centered around a function called "sigFeature," which provides automatic selection of features for the binary classification. Using six publicly available microarray data sets (downloaded from Gene Expression Omnibus) with different biological attributes, we further compared the performance of "sigFeature" to three other feature selection algorithms. A small number of selected features (by "sigFeature") also show higher classification accuracy. For further downstream evaluation of its biological signature, we conducted gene set enrichment analysis with the selected features (genes) from "sigFeature" and compared it with the outputs of other algorithms. We observed that "sigFeature" is able to predict the signature of four out of six microarray data sets accurately, whereas the other algorithms predict less data set signatures. Thus, "sigFeature" is considerably better than related algorithms in discovering differentially significant features from microarray data sets.

Project description:BackgroundBreast cancer belongs to the most frequent and severe cancer types in human. Since excretion of modified nucleosides from increased RNA metabolism has been proposed as a potential target in pathogenesis of breast cancer, the aim of the present study was to elucidate the predictability of breast cancer by means of urinary excreted nucleosides.MethodsWe analyzed urine samples from 85 breast cancer women and respective healthy controls to assess the metabolic profiles of nucleosides by a comprehensive bioinformatic approach. All included nucleosides/ribosylated metabolites were isolated by cis-diol specific affinity chromatography and measured with liquid chromatography ion trap mass spectrometry (LC-ITMS). A valid set of urinary metabolites was selected by exclusion of all candidates with poor linearity and/or reproducibility in the analytical setting. The bioinformatic tool of Oscillating Search Algorithm for Feature Selection (OSAF) was applied to iteratively improve features for training of Support Vector Machines (SVM) to better predict breast cancer.ResultsAfter identification of 51 nucleosides/ribosylated metabolites in the urine of breast cancer women and/or controls by LC- ITMS coupling, a valid set of 35 candidates was selected for subsequent computational analyses. OSAF resulted in 44 pairwise ratios of metabolite features by iterative optimization. Based on this approach ultimately estimates for sensitivity and specificity of 83.5% and 90.6% were obtained for best prediction of breast cancer. The classification performance was dominated by metabolite pairs with SAH which highlights its importance for RNA methylation in cancer pathogenesis.ConclusionExtensive RNA-pathway analysis based on mass spectrometric analysis of metabolites and subsequent bioinformatic feature selection allowed for the identification of significant metabolic features related to breast cancer pathogenesis. The combination of mass spectrometric analysis and subsequent SVM-based feature selection represents a promising tool for the development of a non-invasive prediction system.

Dataset Information

Ensemble Feature Learning of Genomic Data Using Support Vector Machine.

Publications

Ensemble Feature Learning of Genomic Data Using Support Vector Machine.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets