Related Experiment Video
Updated: Oct 13, 2025
08:04
Identification and Classification of Position-specific GABAA Receptor Subunit Missense Variants for Their Role In Hippocampal Pyramidal Neurons
Published on: June 6, 2025
628
Mul-SNO: A Novel Prediction Tool for S-Nitrosylation Sites Based on Deep Learning Methods
IEEE Journal of Biomedical and Health Informatics
|November 11, 2021
Summary
Protein s-nitrosylation (SNO) is crucial for plant immunity and human diseases. A new tool, Mul-SNO, efficiently predicts SNO sites using deep learning, outperforming existing methods.
Area of Science:
- Biochemistry
- Computational Biology
- Genomics
Background:
- Protein s-nitrosylation (SNO) is a key post-translational modification regulating biological processes.
- SNO is implicated in plant immune responses and human disease pathogenesis.
- Identifying SNO sites is critical but traditional methods are laborious and expensive.
Purpose of the Study:
- To develop an efficient and cost-effective computational tool for predicting SNO sites.
- To leverage deep learning for enhanced SNO site identification.
Main Methods:
- Developed Mul-SNO, a novel prediction tool.
- Ensembled Bidirectional Long Short-Term Memory (BiLSTM) and Bidirectional Encoder Representations from Transformers (BERT) deep learning models.
- Validated performance using 10-fold cross-validation and independent datasets.
Main Results:
- Mul-SNO achieved high accuracy, with an ACC of 0.911 on 10-fold cross-validation.
- The tool demonstrated strong performance on independent datasets, achieving an ACC of 0.796.
- Mul-SNO outperformed existing state-of-the-art SNO site prediction methods.
Conclusions:
- Mul-SNO offers an economical and efficient solution for SNO site prediction.
- The developed tool can accelerate research in SNO-related biological processes and disease mechanisms.
- Deep learning ensemble models show significant promise for post-translational modification site prediction.
