Machine Learning and Genetic Regulatory Networks: A Review and a Roadmap

Abstract

Genetic regulatory networks are large graphical structures and their inference is a central problem in bioinformatics. However, because of the paucity of the training data and its noisiness, machine learning is essential to good and tractable inference. This literature review first surveys the relevant theoretical and empirical biochemistry. Next it describes the two types of GRN inference that are problems, the data which can be used for machine learning, and how different kinds of machine learning have been used in previous research. The survey concludes with an analysis of the field as a whole, some underlying methodological issues and a few possible areas for future research.