Inference of Genetic Networks using Random Forests: A Quantitative Weighting Method for Gene Expression Data

Several researchers have focused on the inference of genetic networks. A number of genetic network inference methods have therefore been proposed. Among them, the inference methods that use the random forest show promise. Through the numerical experiment with the random-forest-based inference method, we found that its performance is improved by assigning appropriate weight values to gene expression data. In our earlier work, according to this experimental fact, we proposed “the guidelines for determining weight parameters.” We can improve the performance of the random-forest-based inference method using the weight values determined according to the guidelines. As the guidelines are qualitative, however, it is difficult to determine values for the weight parameters uniquely. In this study, we thus propose a new quantitative weighting method. The proposed method determines the weight values only on the basis of the similarity between measurements. Through the numerical experiments, we finally show that the weight values determined by the proposed weighting method are likely to make the performance of the random-forest-based inference method better.