Mammalian Enhancer Prediction
Dongwon Lee and Michael A. Beer
from: Genome Analysis: Current Procedures and Applications (Edited by: Maria S. Poptsova). Caister Academic Press, U.K. (2014)
We are still far from a complete understanding of regulatory elements in mammalian genomes, even though their central role in most biological processes is widely appreciated. Development of sequence-based models to predict the function and activity of regulatory elements is a fundamental step in being able to address many unsolved questions. Here we describe the current state of the art in computational methods to predict enhancers, especially recent developments using a support vector machine (SVM) framework, which can accurately identify tissue specific enhancers using only genomic sequence and an unbiased set of general sequence features. These models reveal both enriched and depleted predictive sequence features that are critical for specifying these enhancer activities, and can also be used to identify novel enhancers. Some of these predictions have been validated by several independent experiments both in vitro and in vivo. These methods can be applied to computationally predict the functional consequences of common sequence variants in regulatory regions. We believe that these efforts will significantly contribute to our understanding of mammalian regulatory systems and their role in common disease read more ...