Related Experiment Video
Updated: Jan 4, 2026
The Detection of 5-Hydroxymethylcytosine in Neural Stem Cells and Brains of Mice
Published on: September 19, 2019
4mCpred-EL: An Ensemble Learning Framework for Identification of DNA N4-methylcytosine Sites in the Mouse Genome
Balachandran Manavalan1, Shaherin Basith2, Tae Hwan Shin3
1Department of Physiology, Ajou University School of Medicine, Suwon 16499, Korea. bala@ajou.ac.kr.
Abstract:
DNA N4-methylcytosine (4mC) is one of the key epigenetic alterations, playing essential roles in DNA replication, differentiation, cell cycle, and gene expression. To better understand 4mC biological functions, it is crucial to gain knowledge on its genomic distribution. In recent times, few computational studies, in particular machine learning (ML) approaches have been applied in the prediction of 4mC site predictions. Although ML-based methods are promising for 4mC identification in other species, none are available for detecting 4mCs in the mouse genome. Our novel computational approach, called 4mCpred-EL, is the first method for identifying 4mC sites in the mouse genome where four different ML algorithms with a wide range of seven feature encodings are utilized. Subsequently, those feature encodings predicted probabilistic values are used as a feature vector and are once again inputted to ML algorithms, whose corresponding models are integrated into ensemble learning. Our benchmarking results demonstrated that 4mCpred-EL achieved an accuracy and MCC values of 0.795 and 0.591, which significantly outperformed seven other classifiers by more than 1.5-5.9% and 3.2-11.7%, respectively. Additionally, 4mCpred-EL attained an overall accuracy of 79.80%, which is 1.8-5.1% higher than that yielded by seven other classifiers in the independent evaluation. We provided a user-friendly web server, namely 4mCpred-EL which could be implemented as a pre-screening tool for the identification of potential 4mC sites in the mouse genome.
Insights
This study introduces 4mCpred-EL, the first machine learning tool to predict DNA N4-methylcytosine (4mC) sites in the mouse genome. It offers a user-friendly web server for efficient identification of potential 4mC locations.
Area of Science:
- Epigenetics and Genomics
- Computational Biology
- Bioinformatics
Background:
- DNA N4-methylcytosine (4mC) is a critical epigenetic modification involved in fundamental cellular processes.
- Understanding the genomic distribution of 4mC is essential for elucidating its biological functions.
- Existing computational methods for 4mC prediction are limited, with none specifically available for the mouse genome.
Purpose of the Study:
- To develop the first computational approach for identifying 4mC sites in the mouse genome.
- To leverage machine learning and ensemble learning for accurate 4mC prediction.
- To provide a user-friendly web server for pre-screening potential 4mC sites.
Main Methods:
- Development of 4mCpred-EL, a novel computational method utilizing four machine learning algorithms.
- Integration of seven diverse feature encoding strategies.
- Application of ensemble learning by feeding probabilistic predictions from initial models into further machine learning algorithms.
Main Results:
- 4mCpred-EL achieved high accuracy (0.795) and MCC (0.591) in benchmarking, outperforming seven other classifiers.
- Independent evaluation showed 4mCpred-EL with an overall accuracy of 79.80%, surpassing other methods by 1.8-5.1%.
- The method significantly improved 4mC site identification accuracy in the mouse genome.
Conclusions:
- 4mCpred-EL represents a significant advancement in predicting 4mC sites within the mouse genome.
- The developed web server offers a valuable tool for researchers investigating epigenetic regulation in mice.
- This work facilitates deeper understanding of 4mC's role in DNA replication, differentiation, and gene expression.
