IEnhancer-PsedeKNC: Identification of enhancers and their subgroups based on Pseudo degenerate kmer nucleotide composition

Abstract

Enhancers are regulatory DNA elements that play a crucial role in promoting gene transcription in eukaryotes. According to the distinct levels of biological activities and regulatory effects on target genes, enhancers can be classified into several subgroups, such as strong and weak enhancers. Although some computational predictors have been proposed to identify enhancers and non-enhancers, only a few studies focus on predicting their subgroups. In this work, we employed a two-layer framework to formulate a computational method called iEnhancer-PsedeKNC. The first layer is used to identify if a query DNA sequence is a enhancer or not, if it is predicted as a enhancer, then the second layer is used to further classify it into a strong enhancer or weak enhancer. On a high-quality benchmark dataset, iEnhancer-PsedeKNC achieved an AUC score of 0.85 for enhancer identification, and an AUC score of 0.69 for enhancer subgroup prediction, indicating that iEnhancer-PsedeKNC would be a useful computational tool for enhancer study.