Finding Informative Genes from Multiple Microarray Experiments: A Graph-based Consensus Maximization Model

With the rapid advancement of biology technology, many microarray experiments are conducted towards the same problem of finding informative genes. Therefore, it is important to find a set of informative genes integrating multiple microarray experiments that achieves maximal consensus. Most previous re- searches formulated this problem as a rank aggregation problem. In this paper, we propose a novel Graph-based Consensus Maximization (GCM) model to estimate the conditional probability of each gene being informative, then the genes are ranked by this probability. The estimation of the probabilities is formulated as an optimization problem on a bipartite graph, where the criterion function favors the smoothness of the prediction over the graph and penalizes deviations from the initial input ranked lists from microarray experiments. We solve this problem through iterative propagation of probability estimates among neighboring nodes. In addition, when certain genes have already been identified to be informative, it has never been explored in the literature how to take advantage of such information to improve the consensus result. Our proposed GCM model can be naturally extended to incorporate such information, thus increasing the quality of the predicted result. In the experimental evaluation, we conducted experiments on the five prostate cancer microarray studies. The results showed that our model outperformed other baseline methods in finding informative genes. Furthermore, by adding only one piece of information that some gene is informative, our model yielded a significantly better result. The experimental evaluation demonstrates that the proposed GCM model is effective and superior in finding informative genes from multiple microarray experiments.