Informative structure priors: joint learning of dynamic regulatory networks from multiple types of data.

摘要: We present a method for jointly learning dynamic models of transcriptional regulatory networks from gene expression data and transcription factor binding location data. Models are automatically learned using Bayesian network inference algorithms; joint is accomplished by incorporating evidence through the likelihood, prior. propose new informative structure prior with two advantages. First, incorporates probabilistically, allowing it to be weighed against Second, takes on factorable form that computationally efficient when networks. Results obtained both simulated experimental yeast cell cycle demonstrate this algorithm can recover multiple types more accurate than those recovered each type in isolation.