A Multi-classifier Model to Identify Mitochondrial Respiratory Gene Signatures in Human Cancer

Whether alteration of mitochondrial gene expression can serve as an effective molecular signature for cancer classification currently remains controversy. To tackle this challenge, here we present a multi-classifier model to identify mitochondrial aberrant gene signatures and then assess the effectiveness on cancer classification. Specifically, we first applied a supervised learning model, Empirical Bayes statistics, to detect differentially expressed genes from a liver cancer mitochondrial gene expression dataset (GEO accession: GSE64505). Next, we applied two well-known classifiers, Prediction Analysis of Microarrays (PAM) and Random Forest (RF), with several folds of cross-validation, to find molecular signatures that can classify liver cancer samples from normal samples. We obtained a mitochondrial molecular signature comprising 25 genes. Classification accuracy was 87.5% by PAM classifier (5 fold cross-validation with 30 repeats), while it was 87.5% and 75.0% by Random Forest with 5- and 2-fold cross-validations (30 repeats), respectively. We further performed literature mining and Gene Set Enrichment Analysis (GSEA) to evaluate the biological significance and novelty of genes in this gene signature.