Machine Learning Based Comparative Analysis of Methods for Enhancer Prediction in Genomic Data

The duel for discovery of enhancer along with the beginning of next generation sequencing is a consequence of discovery simian virus 40 (SV40) that is believed to be first enhancers noticed in wide set of genomic data. Features for predicting enhancers such as marks for histone modification, elements mined from sequences characteristics, epigenetic marks right away from primary tissues are implemented with a capricious success rate. Though till date there is no distinct enhancer indicator fetching an agreement in discriminating and exposing enhancer from massive genomic data sets. Machine learning has arisen out to be one of the competent computational approaches with a diversity of supervised, unsupervised and hybrid architectures used for enhancer identification. In this paper, attention is given to the tools lately developed for enhancer prediction working on common feature of enhancer. Comparative analysis of methods for enhancer prediction and corresponding results are prepared amid functionally analogous counterparts.