Related Experiment Video
Updated: Nov 2, 2025
08:56
A Method for Measuring RNA N6-methyladenosine Modifications in Cells and Tissues
Published on: December 5, 2016
11.1K
m6AGE: A Predictor for N6-Methyladenosine Sites Identification Utilizing Sequence Characteristics and Graph
Yan Wang1,2, Rui Guo1, Lan Huang1
1Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education, and College of Computer Science and Technology, Jilin University, Changchun, China.
Frontiers in Genetics
|June 14, 2021
Summary
N6-methyladenosine (m6A) site identification is crucial for understanding RNA modifications. The m6AGE predictor combines sequence and graph features, outperforming existing methods for accurate m6A site detection.
Area of Science:
- Molecular Biology
- Bioinformatics
- Computational Biology
Background:
- N6-methyladenosine (m6A) is a prevalent RNA modification impacting biological processes.
- Experimental identification of m6A sites is laborious and expensive.
- Computational methods are needed for efficient m6A site prediction.
Purpose of the Study:
- To develop a high-confidence computational predictor for m6A sites.
- To integrate sequence-derived and graph embedding features for enhanced prediction accuracy.
Main Methods:
- Proposed a novel predictor, m6AGE.
- Utilized a combination of sequence-derived and graph embedding features.
- Evaluated performance on four public datasets across three species.
Main Results:
- m6AGE achieved superior performance compared to existing predictors.
- Demonstrated significant improvements in accuracy, MCC, specificity, and AUC on the A101 dataset.
- The predictor is the first to combine sequence-derived and graph embedding features for m6A site prediction.
Conclusions:
- m6AGE is an effective computational tool for m6A site prediction.
- The integration of diverse features enhances prediction capabilities.
- The findings contribute to a better understanding of m6A modification mechanisms.
