A biomarker ensemble ranking framework for prioritizing depression candidate genes

It is a great challenge in human health clinic to find parsimonious set of genes responsible for depression disease. Many prioritization approaches have been developed for depression candidate genes. However, most of the methods primarily rank depression candidate genes based on the similarities with known depression genes. Those approaches do not effectively consider relativeness of depression candidate genes with non-disease genes for precise ranking. In this paper, we propose a Biomarker Ensemble Ranking Framework (BERF) for depression candidate gene prioritization, which applies 2-ranking models scheme by considering both candidate genes and non-disease genes. We first clusterize training genes which consists of both known depression and non-disease genes. Then, we introduce a global loss function in the 2-ranking learning model. Finally, we propose a modified SVM-based learning strategy with minimizing the global loss. An ensemble technique is applied to generate the ranking results for depression candidate genes. The experimental results show that our BERF outperforms existing approach in terms of ROC and AUC.