A survey of recently emerged genome-wide computational enhancer predictor tools. (June 2018)

• Record Type: Journal Article
• Authors: Lim, Leonard Whye Kit; Chung, Hung Hui; Chong, Yee Ling; Lee, Nung Kion
• Is Part Of: Computational biology and chemistry. Volume 74(2018)
• Page Start: 132
• Page End: 141
• Publication Date: 2018-06
• Subjects: Enhancer prediction -- Supervised learning -- Unsupervised learning -- Semi-supervised learning; Chemistry -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; Biochemistry -- Data processing; Biology -- Data processing; Molecular biology -- Data processing; Periodicals; Electronic journals; 542.85
• DOI: 10.1016/j.compbiolchem.2018.03.019
• Languages: English
• ISSNs: 1476-9271

Abstract

Graphical abstract: Highlights: Major methods for enhancer prediction genome-wide are supervised, unsupervised and semi-supervised. Comparison of their prediction methods and outcomes was done across their functionally similar counterparts. Some recommendations and insights for future development of more comprehensive and robust tools were provided. Abstract: The race for the discovery of enhancers at a genome-wide scale has been on since the commencement of next generation sequencing decades after the discovery of the first enhancer, SV40. A few enhancer-predicting features such as chromatin feature, histone modifications and sequence feature had been implemented with varying success rates. However, to date, there is no consensus yet on the single enhancer marker that can be employed to ultimately distinguish and uncover enhancers from the enormous genomic regions. Many supervised, unsupervised and semi-supervised computational approaches had emerged to complement and facilitate experimental approaches in enhancer discovery. In this review, we placed our focus on the recently emerged enhancer predictor tools that work on general enhancer features such as sequences, chromatin states and histone modifications, eRNA and of multiple feature approach. Comparisons of their prediction methods and outcomes were done across their functionally similar counterparts. We provide some recommendations and insights for future development of more comprehensive and robust tools.