Multiple SVM-RFE for gene selection in cancer classification with expression data.

This paper proposes a new feature selection method that uses a backward elimination procedure similar to that implemented in support vector machine recursive feature elimination (SVM-RFE). Unlike the SVM-RFE method, at each step, the proposed approach computes the feature ranking score from a statistical analysis of weight vectors of multiple linear SVMs trained on subsamples of the original training data. We tested the proposed method on four gene expression datasets for cancer classification. The results show that the proposed feature selection method selects better gene subsets than the original SVM-RFE and improves the classification accuracy. A Gene Ontology-based similarity assessment indicates that the selected subsets are functionally diverse, further validating our gene selection method. This investigation also suggests that, for gene expression-based cancer classification, average test error from multiple partitions of training and test sets can be recommended as a reference of performance quality.

Proteomic cancer classification with mass spectrometry data.

The ultimate goal of cancer proteomics is to adapt proteomic technologies for routine use in clinical laboratories for the purpose of diagnostic and prognostic classification of disease states, as well as in evaluating drug toxicity and efficacy. Analysis of tumor-specific proteomic profiles may also allow better understanding of tumor development and the identification of novel targets for cancer therapy. The biological variability among patient samples as well as the huge dynamic range of biomarker concentrations are currently the main challenges facing efforts to deduce diagnostic patterns that are unique to specific disease states. While several strategies exist to address this problem, we focus here on cancer classification using mass spectrometry (MS) for proteomic profiling and biomarker identification. Recent advances in MS technology are starting to enable high-throughput profiling of the protein content of complex samples. For cancer classification, the protein samples from cancer patients and noncancer patients or from different cancer stages are analyzed through MS instruments and the MS patterns are used to build a diagnostic classifier. To illustrate the importance of feature selection in cancer classification, we present a method based on support vector machine-recursive feature elimination (SVM-RFE), demonstrated on two cancer datasets from ovarian and lung cancer.