Related Experiment Video
Updated: May 21, 2025
10:52
Sample Preparation for Mass Spectrometry-based Identification of RNA-binding Regions
Published on: September 28, 2017
8.0K
CAP-m7G: A capsule network-based framework for specific RNA N7-methylguanosine site identification using image
Peilin Xie1,2, Jiahui Guan1,3, Xuxin He3
1Kobilka Institute of Innovative Drug Discovery, School of Medicine, The Chinese University of Hong Kong, Shenzhen, 2001 Longxiang Blvd, Longgang District, 518172, Shenzhen, China.
Computational and Structural Biotechnology Journal
|March 20, 2025
Summary
N7-methylguanosine (m7G) modifications are crucial for RNA function and gene regulation. A new AI model, CAP-m7G, accurately predicts m7G sites, aiding disease research and offering a user-friendly web server.
Area of Science:
- Molecular Biology
- Bioinformatics
- Computational Biology
Background:
- N7-methylguanosine (m7G) modifications are vital for RNA stability, mRNA export, and protein translation, impacting gene expression.
- Dysregulation of m7G is linked to diseases like cancer and neurodegenerative disorders, highlighting the need for accurate m7G site identification.
- Existing AI models for m7G site prediction have limitations, and a user-friendly web server is lacking.
Purpose of the Study:
- To develop an advanced artificial intelligence model for accurate prediction of N7-methylguanosine (m7G) sites.
- To create a user-friendly web server for accessible m7G site prediction.
- To improve the understanding of m7G modification roles in biological processes and disease.
Main Methods:
- Integration of Chaos Game Representation (CGR) with Capsule Networks (CapsNet) and reconstruction layers.
- Development of the CAP-m7G model for sequence-based m7G site prediction.
- Validation of the model's performance on independent test datasets.
Main Results:
- CAP-m7G achieved high accuracy (96.63%), specificity (95.07%), and MCC (0.933) on independent test data.
- The study demonstrated that CGR combined with CapsNet effectively captures sequence information critical for m7G sites.
- A publicly accessible web server for CAP-m7G is now available.
Conclusions:
- The CAP-m7G model offers a significant advancement in predicting m7G sites, surpassing previous AI approaches.
- The integration of CGR and CapsNet is a powerful strategy for analyzing RNA modification patterns.
- The developed web server facilitates research into the biological roles and disease implications of m7G modifications.
