A Deep Neural Network for Identifying DNA N4-Methylcytosine Sites

Abstract

Motivation: N4-methylcytosine (4mC) plays an important role in host defense and transcriptional regulation. Accurate identification of 4mc sites provides a more comprehensive understanding of its biological effects. At present, the traditional machine learning algorithms are used in the research on 4mC sites prediction, but the complexity of the algorithms is relatively high, which is not suitable for the processing of large data sets, and the accuracy of prediction needs to be improved. Therefore, it is necessary to develop a new and effective method to accurately identify 4mC sites.Results: In this work, we found a large number of 4mC sites and non 4mC sites of Caenorhabditis elegans (C. elegans) from the latest MethSMRT website, which greatly expanded the dataset of C. elegans, and developed a hybrid deep neural network framework named 4mcDeep-CBI, aiming to identify 4mC sites. In order to obtain the high latitude information of the feature, we input the preliminary extracted features into the Convolutional Neural Network (CNN) and Bidirectional Long Short Term Memory network (BLSTM) to generate advanced features. Taking the advanced features as algorithm input, we have proposed an integrated algorithm to improve feature representation. Experimental results on large new dataset show that the proposed predictor is able to achieve generally better performance in identifying 4mC sites as compared to the state-of-art predictor. Notably, this is the first study of identifying 4mC sites using deep neural network. Moreover, our model runs much faster than the state-of-art predictor.

Empirical Comparison and Analysis of Web-Based DNA N4-Methylcytosine Site Prediction Tools

“…Zeng et al. 1 developed 4mCDeep-CBI, a predictor for E. coli . The authors constructed a new imbalanced dataset containing 11,173 4mCs and 6635 non-4mCs.…”

“…It alters chromatin structure, DNA conformation, DNA-protein interactions, and DNA stability. 1 This modification plays important roles in the regulation of several developmental and pathological processes, such as aging, carcinogenesis, genomic imprinting, repression of transposable elements, and X chromosome inactivation. 2 , 3 , 4 , 5 Analysis of the differentiating capacity of foreign DNA and host DNA indicates that certain modifications, such as cytosine methylation, may protect the host DNA from enzyme-mediated degradation.…”

“…Two additional methods (4mCPred 20 and 4mcPred-SVM 21 ) were developed in 2018; five methods (Meta-4mCpred, 8 4mcPred-IFL, 22 4mCCNN, 23 4mCpred-EL, 24 and i4mCROSE 25 ) were reported in 2019. By April 2020, five more methods (iEC4mC-SVM, 26 DNA4mC-LIP, 27 4mcDeep-CBI, 1 iDNA-MS, 2 and i4mC-Mouse 28 ) were reported. An overview of the existing 4mC prediction methods is provided in Figure 1 .…”

iMethyl-Deep: N6 Methyladenosine Identification of Yeast Genome with Automatic Feature Extraction Technique by Using Deep Learning Algorithm

“…Four standard evaluation metrics were used in many research publication [45,46], which consist of overall accuracy (ACC), Mathew's correlation coefficient (MCC), specificity (Sp), and sensitivity (Sn). The following are the mathematical formulation of four metrics [47][48][49][50].…”

DNC4mC-Deep: Identification and Analysis of DNA N4-Methylcytosine Sites Based on Different Encoding Schemes By Using Deep Learning

“…Then, those scores were combined with a linear regression model for enhanced prediction performance [24]. The 4mcDeep-CBI [27] as a deep learning framework has been proposed to predict the 4mC sites in an expanded dataset of Caenorhabditis elegans (C. elegans). 3-CNN and BLSTM were used to extract deep information and to obtain advanced features.…”