Abstract
BACKGROUND: Hepatocellular carcinoma (HCC) is one of the most common cancers. The discovery of specific genes severing as biomarkers is of paramount significance for cancer diagnosis and prognosis. The high-throughput omics data generated by the cancer genome atlas (TCGA) consortium provides a valuable resource for the discovery of HCC biomarker genes. Numerous methods have been proposed to select cancer biomarkers. However, these methods have not investigated the robustness of identification with different feature selection techniques. METHODS: We use six different recursive feature elimination methods to select the gene signiatures of HCC from TCGA liver cancer data. The genes shared in the six selected subsets are proposed as robust biomarkers. Akaike information criterion (AIC) is employed to explain the optimization process of feature selection, which provides a statistical interpretation for the feature selection in machine learning methods. And we use several methods to validate the screened biomarkers. RESULTS: In this paper, we propose a robust method for discovering biomarker genes for HCC from gene expression data. Specifically, we implement recursive feature elimination cross-validation (RFE-CV) methods based on six different classication algorithms. The overlaps in the discovered gene sets via different methods are referred as the identified biomarkers. We give an interpretation of the feature selection process based on machine learning using AIC in statistics. Furthermore, the features selected by the backward logistic stepwise regression via AIC minimum theory are completely contained in the identified biomarkers. Through the classification results, the superiority of interpretable robust biomarker discovery method is verified. CONCLUSIONS: It is found that overlaps among gene subsets contain different quantitative features selected by the RFE-CV of 6 classifiers. The AIC values in the model selection provide a theoretical foundation for the feature selection process of biomarker discovery via machine learning. What's more, genes containing in more optimally selected subsets make better biological sense and implication. The quality of feature selection is improved by the intersections of biomarkers selected from different classifiers. This is a general method suitable for screening biomarkers of complex diseases from high-throughput data.