MSVM-RFE: extensions of SVM-RFE for multiclass gene selection on DNA microarray data. Bioinformatics

Yale University, New Haven, Connecticut, United States
Bioinformatics (Impact Factor: 4.98). 06/2007; 23(9):1106-14. DOI: 10.1093/bioinformatics/btm036
Source: PubMed


MOTIVATION: Given the thousands of genes and the small number of samples, gene selection has emerged as an important research problem in microarray data analysis. Support Vector Machine-Recursive Feature Elimination (SVM-RFE) is one of a group of recently described algorithms which represent the stat-of-the-art for gene selection. Just like SVM itself, SVM-RFE was originally designed to solve binary gene selection problems. Several groups have extended SVM-RFE to solve multiclass problems using one-versus-all techniques. However, the genes selected from one binary gene selection problem may reduce the classification performance in other binary problems. RESULTS: In the present study, we propose a family of four extensions to SVM-RFE (called MSVM-RFE) to solve the multiclass gene selection problem, based on different frameworks of multiclass SVMs. By simultaneously considering all classes during the gene selection stages, our proposed extensions identify genes leading to more accurate classification.

  • Source
    • "After that, IC Z-scores of subjects in each statistically significant voxel were entered into a voxelwise five-level one-way analysis of covariance (ANCOVA) with age and gender as covariates. Next, based on the voxels extracted from all INs, which show main effects of group difference using ANCOVA (p b 0.05), multiclass support vector machine recursive feature elimination (MSVM-RFE) (Zhou and Tuck, 2007) with 10-fold cross-validation was applied to further select voxels (features) in a backward elimination procedure. In ANCOVA, we chose a relatively loose threshold (p b 0.05, uncorrected), considering that more features for selection could benefit the performance of MSVM-RFE. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Schizophrenia (SZ), bipolar disorder (BP) and schizoaffective disorder (SAD) share some common symptoms, and there is a debate about whether SAD is an independent category. To the best of our knowledge, no study has been done to differentiate these three disorders or to investigate the distinction of SAD as an independent category using fMRI data. The present study is aimed to explore biomarkers from resting-state fMRI networks for differentiating these disorders and investigate the relationship among these disorders based on fMRI networks with an emphasis on SAD. Firstly, a novel group ICA method, group information guided independent component analysis (GIG-ICA), was applied to extract subject-specific brain networks from fMRI data of 20 healthy controls (HC), 20 SZ patients, 20 BP patients, 20 patients suffering SAD with manic episodes (SADM), and 13 patients suffering SAD with depressive episodes exclusively (SADD). Then, five-level one-way analysis of covariance and multiclass support vector machine recursive feature elimination were employed to identify discriminative regions from the networks. Subsequently, the t-distributed stochastic neighbor embedding (t-SNE) projection and the hierarchical clustering methods were implemented to investigate the relationship among those groups. Finally, to evaluate the generalization ability, 16 new subjects were classified based on the found regions and the trained model using original 93 subjects. Results show that the discriminative regions mainly include frontal, parietal, precuneus, cingulate, supplementary motor, cerebellar, insula and supramarginal cortices, which performed well in distinguishing different groups. SADM and SADD were the most similar to each other, although SADD had greater similarity to SZ compared to other groups, which indicates SAD may be an independent category. BP was closer to HC compared with other psychotic disorders. In summary, resting-state fMRI brain networks extracted via GIG-ICA provide a promising potential to differentiate SZ, BP, and SAD. Copyright © 2015. Published by Elsevier Inc.
    Full-text · Article · Jul 2015 · NeuroImage
    • "Thus, we need feature selection algorithms with a controlled redundancy. Note that, like the method in [17] "
    [Show abstract] [Hide abstract]
    ABSTRACT: We first present a feature selection method based on a multilayer perceptron (MLP) neural network, called feature selection MLP (FSMLP). We explain how FSMLP can select essential features and discard derogatory and indifferent features. Such a method may pick up some useful but dependent (say correlated) features, all of which may not be needed. We then propose a general scheme for dealing with feature selection with "controlled redundancy" (CoR). The proposed scheme, named as FSMLP-CoR, can select features with a controlled redundancy both for classification and function approximation/prediction type problems. We have also proposed a new more effective training scheme named mFSMLP-CoR. The idea is general in nature and can be used with other learning schemes also. We demonstrate the effectiveness of the algorithms using several data sets including a synthetic data set. We also show that the selected features are adequate to solve the problem at hand. Here, we have considered a measure of linear dependency to control the redundancy. The use of nonlinear measures of dependency, such as mutual information, is straightforward. Here, there are some advantages of the proposed schemes. They do not require explicit evaluation of the feature subsets. Here, feature selection is integrated into designing of the decision-making system. Hence, it can look at all features together and pick up whatever is necessary. Our methods can account for possible nonlinear subtle interactions between features, as well as that between features, tools, and the problem being solved. They can also control the level of redundancy in the selected features. Of the two learning schemes, mFSMLP-CoR, not only improves the performance of the system, but also significantly reduces the dependency of the network's behavior on the initialization of connection weights.
    No preview · Article · Jan 2015 · IEEE transactions on neural networks and learning systems
  • Source
    • "We also conducted a comprehensive comparison of various feature selection methods on the classification of the 14 classes of compounds. For training purposes, we found that SVM-RFE usually outperformed other methods as has been confirmed elsewhere [21,39,40]. However, when an independent dataset, dataset 1, was used for a prediction, SVM-RFE gave a high overfitting rate. "
    [Show abstract] [Hide abstract]
    ABSTRACT: High throughput transcriptomics profiles such as those generated using microarrays have been useful in identifying biomarkers for different classification and toxicity prediction purposes. Here, we investigated the use of microarrays to predict chemical toxicants and their possible mechanisms of action. In this study, in vitro cultures of primary rat hepatocytes were exposed to 105 chemicals and vehicle controls, representing 14 compound classes. We comprehensively compared various normalization of gene expression profiles, feature selection and classification algorithms for the classification of these 105 chemicals into14 compound classes. We found that normalization had little effect on the averaged classification accuracy. Two support vector machine (SVM) methods, LibSVM and sequential minimal optimization, had better classification performance than other methods. SVM recursive feature selection (SVM-RFE) had the highest overfitting rate when an independent dataset was used for a prediction. Therefore, we developed a new feature selection algorithm called gradient method that had a relatively high training classification as well as prediction accuracy with the lowest overfitting rate of the methods tested. Analysis of biomarkers that distinguished the 14 classes of compounds identified a group of genes principally involved in cell cycle function that were significantly downregulated by metal and inflammatory compounds, but were induced by anti-microbial, cancer related drugs, pesticides, and PXR mediators. Our results indicate that using microarrays and a supervised machine learning approach to predict chemical toxicants, their potential toxicity and mechanisms of action is practical and efficient. Choosing the right feature and classification algorithms for this multiple category classification and prediction is critical.
    Full-text · Article · Mar 2014 · BMC Genomics
Show more