iRNA5hmC: The First Predictor to Identify RNA 5-Hydroxymethylcytosine Modifications Using Machine Learning

Abstract

RNA 5-hydroxymethylcytosine (5hmC) modification plays an important role in a series of biological processes. Characterization of its distributions in transcriptome is fundamentally important to reveal the biological functions of 5hmC. Sequencing-based technologies allow the high-throughput identification of 5hmC; however, they are laborintensive, time-consuming, as well as expensive. Thus, there is an urgent need to develop more effective and efficient computational methods, at least complementary to the high-throughput technologies. In this study, we developed iRNA5hmC, a computational predictive protocol to identify RNA 5hmC sites using machine learning. In this predictor, we introduced a sequence-based feature algorithm consisting of two feature representations, (1) k-mer spectrum and (2) positional nucleotide binary vector, to capture the sequential characteristics of 5hmC sites. Afterward, we utilized a two-stage feature space optimization strategy to improve the feature representation ability, and trained a predictive model using support vector machine (SVM). Our feature analysis results showed that feature optimization can help to capture the most discriminative features. As compared to well-known existing feature descriptors, our proposed representations can more accurately separate true 5hmC from non-5hmC sites. To the best of our knowledge, iRNA5hmC is the first RNA 5hmC predictor that enables to make predictions based on RNA primary sequences only, without any need of prior experimental knowledge. Importantly, we have established an easy-to-use webserver which is currently available at http://server.malab.cn/iRNA5hmC. We expect it has potential to be a useful tool for the prediction of 5hmC sites.

Epigenetics: Roles and therapeutic implications of non-coding RNA modifications in human cancers

“…We summarized the prediction tools for m6A and other types of RNA-modifying processes, respectively ( Table 2 ). 138 , 139 , 140 , 141 , 142 , 143 , 144 , 145 , 146 , 147 , 148 , 149 , 150 , 151 , 152 , 153 , 154 , 155 , 156 , 157 , 158 , 159 , 160 , 161 , 162 , 163 , 164 , 165 , 166 , 167 , 168 , 169 , 170 For example, Han et al. 156 mapped m 6 A peaks in different subcellular components and gene regions.…”

Prediction of RNA 5-Hydroxymethylcytosine Modifications Using Deep Learning

“…The dataset used in the study was prepared and utilized by Liu et al [12] and is available at http://server.malab.cn/ iRNA5hmC/Download.html. The balance dataset consisted of 1324 samples.…”

“…We compared the outcomes of the proposed model with the only existing machine learning-based computational model, iRNA5hmC [12] which utilizes the SVM algorithm, where the features representation techniques are k-mer spectrum and positional nucleotide binary vectors. iRNA5hmC was evaluated using 5 folds cross-validation.…”

“…Recently, Liu et al proposed iRNA5hmC, a computational model with a machine learning identifier based on a support vector machine (SVM) as a classifier to predict primary RNA sequences [12]. This model utilized the k-mer spectrum and positional nucleotide binary vector as a feature representation technique.…”

iBitter-Fuse: A Novel Sequence-Based Bitter Peptide Predictor by Fusing Multi-View Features

“…However, iBitter-SCM [17] employed only dipeptide composition (DPC) for representing peptide sequences, which was unable to fully capture the discriminative characteristics between bitter and non-bitter peptides [19][20][21][22][23][24]. Secondly, the embodiment of non-important features in model development might have led to two possible outcomes: information redundancy and over-fitting [23][24][25][26][27][28][29][30]. Finally, the overall performance of existing methods is not yet of satisfactory level.…”