iEnhancer-Deep: A Computational Predictor for Enhancer Sites and Their Strength Using Deep Learning

Abstract

Enhancers are short motifs that contain high position variability and free scattering. Identifying these non-coding DNA fragments and their strength is vital because they play an important role in the control of gene regulation. Enhancer identification is more complicated than other genetic factors due to free scattering and their very high amount of locational variation. To classify this biological difficulty, several computational tools in bioinformatics have been created over the last few years as current learning models are still lacking. To overcome these limitations, we introduce iEnhancer-Deep, a deep learning-based framework that uses One-Hot Encoding and a convolutional neural network for model construction, primarily for the identification of enhancers and secondarily for the classification of their strength. Parallels between the iEnhancer-Deep and existing state-of-the-art methodologies were drawn to evaluate the performance of the proposed model. Furthermore, a cross-species test was carried out to assess the generalizability of the proposed model. In general, the results show that the proposed model produced comparable results with the state-of-the-art models.

iEnhancer-ELM: improve enhancer identification by extracting position-related multiscale contextual information based on enhancer language models

“…Table 3 shows the comparison between iEnhancer-ELM and existing state-of-the-art methods on the Liu’s dataset. The competing methods include iEnhancer-2L ( Liu et al , 2016 ), iEnhancer-EL ( Liu et al , 2018 ), iEnhancer-5Step ( Le et al , 2019 ), BERT-Enhancer ( Le et al , 2021 ), iEnhancer-XG ( Cai et al , 2021 ), iEnhancer-GAN ( Yang et al , 2021 ), iEnhancer-ECNN ( Nguyen et al , 2019 ) and iEnhancer-Deep ( Kamran et al , 2022 ). iEnhance-2L, iEnhancer-EL and iEnhancer-XG extract the inherent properties from nucleic acid sequences based on manual rules.…”

Analysis of the landscape of human enhancer sequences in biological databases

“…On the other hand, novel software to identify enhancer sequences is being developed [173] , [174] . Comparative studies of algorithms and revisions about these tools have been previously elaborated in other works [130] , [175] , [176] , although a more recent in-depth review regarding this issue would be of interest. In the supplementary material we have included the main algorithms that have been used to identify the enhancers provided in each repository.…”

A comprehensive revisit of the machine‐learning tools developed for the identification of enhancers in the human genome

“…This model is applied to Layer 1 predictions only. (viii) iEnhancer‐Deep [141] used a simple CNN and OHE for model construction. (ix) iEnhancer‐MRBF [102] combined a new classifier MLR‐RBFN with three feature representation techniques, including Kmer, ANF, and NBP, and used LGB to extract features, and then fed these feature vectors into RBFN.…”