Inference of Genetic Regulatory Networks Using an Estimation of Distribution Algorithm

Inference of Genetic Regulatory Networks from sparse and noisy expression data is still a challenge nowadays. In this work we use an Estimation of Distribution Algorithm to infer Genetic Regulatory Networks. In order to evaluate the algorithm we apply it to three types of data: (i) data simulated from a multivariate Gaussian distribution, (ii) data simulated from a realistic simulator, GeneNetWeaver and (iii) data from flow cytometry experiments. The proposed inference method shows a performance comparable with traditional inference algorithms in terms of the network reconstruction accuracy.