Related Experiment Video
Updated: Nov 15, 2025
The Detection of 5-Hydroxymethylcytosine in Neural Stem Cells and Brains of Mice
Published on: September 19, 2019
4mCPred-CNN-Prediction of DNA N4-Methylcytosine in the Mouse Genome Using a Convolutional Neural Network
Zeeshan Abbas1,2, Hilal Tayara3, Kil To Chong1,4
1Department of Electronics and Information Engineering, Jeonbuk National University, Jeonju 54896, Korea.
Abstract:
Among DNA modifications, N4-methylcytosine (4mC) is one of the most significant ones, and it is linked to the development of cell proliferation and gene expression. To know different its biological functions, the accurate detection of 4mC sites is required. Although we have several techniques for the prediction of 4mC sites in different genomes based on both machine learning (ML) and convolutional neural networks (CNNs), there is no CNN-based tool for the identification of 4mC sites in the mouse genome. In this article, a CNN-based model named 4mCPred-CNN was developed to classify 4mC locations in the mouse genome. Until now, we had only two ML-based models for this purpose; they utilized several feature encoding schemes, and thus still had a lot of space available to improve the prediction accuracy. Utilizing only a single feature encoding scheme-one-hot encoding-we outperformed both of the previous ML-based techniques. In a ten-fold validation test, the proposed model, 4mCPred-CNN, achieved an accuracy of 85.71% and Matthews correlation coefficient (MCC) of 0.717. On an independent dataset, the achieved accuracy was 87.50% with an MCC value of 0.750. The attained results exhibit that the proposed model can be of great use for researchers in the fields of biology and bioinformatics.
Insights
Researchers developed 4mCPred-CNN, a novel convolutional neural network (CNN) tool, to accurately identify N4-methylcytosine (4mC) sites in the mouse genome. This advancement improves upon existing machine learning methods for DNA modification analysis.
Area of Science:
- Bioinformatics
- Genomics
- Molecular Biology
Background:
- N4-methylcytosine (4mC) is a significant DNA modification impacting cell proliferation and gene expression.
- Accurate detection of 4mC sites is crucial for understanding its biological functions.
- Existing machine learning (ML) and convolutional neural network (CNN) tools for 4mC prediction are limited, with no specific CNN-based tool for the mouse genome.
Purpose of the Study:
- To develop a CNN-based model for identifying 4mC sites in the mouse genome.
- To improve the prediction accuracy of 4mC sites compared to existing ML-based models.
- To provide a valuable tool for researchers in biology and bioinformatics.
Main Methods:
- Development of a CNN-based model named 4mCPred-CNN.
- Utilizing one-hot encoding as the sole feature encoding scheme.
- Evaluation through ten-fold cross-validation and testing on an independent dataset.
Main Results:
- The 4mCPred-CNN model achieved 85.71% accuracy and a Matthews correlation coefficient (MCC) of 0.717 in ten-fold validation.
- On an independent dataset, the model attained 87.50% accuracy with an MCC of 0.750.
- The model outperformed previous ML-based techniques using a single feature encoding scheme.
Conclusions:
- 4mCPred-CNN is an effective CNN-based tool for 4mC site identification in the mouse genome.
- The model demonstrates superior prediction accuracy compared to existing ML-based methods.
- This tool offers significant utility for biological and bioinformatics research involving DNA modifications.
