Related Experiment Video
Updated: Aug 23, 2025
09:40
A Mass Spectrometry-Based Proteomics Approach for Global and High-Confidence Protein R-Methylation Analysis
Published on: April 28, 2022
2.5K
Multifactorial feature extraction and site prognosis model for protein methylation data
Monika Khandelwal1, Ranjeet Kumar Rout1, Saiyed Umer2
1Computer Science & Engineering, National Institute of Technology Srinagar, Hazratbal, Srinagar, 190006, Jammu and Kashmir, India.
Briefings in Functional Genomics
|October 31, 2022
Summary
Predicting protein methylation sites is crucial for understanding cellular functions. A new computational method, MufeSPM, accurately identifies these sites using information theory and physicochemical properties, outperforming existing predictors.
Area of Science:
- Biomedical Research
- Computational Biology
- Proteomics
Background:
- Protein methylation is a vital posttranslational modification influencing cellular activities.
- Accurate prediction of methylation sites (arginine and lysine) is essential for molecular process understanding.
- Experimental methods for site prediction are costly and time-consuming, necessitating computational approaches.
Purpose of the Study:
- To develop a novel computational method for predicting protein methylation sites.
- To address limitations of existing methods that rely on structural or evolutionary data.
- To utilize information theory features, amino acid composition, and physicochemical properties for prediction.
Main Methods:
- Proposed the multi-factorial feature extraction and site prognosis model (MufeSPM).
- Employed information theory features (Renyi, Shannon, Havrda-Charvat, Arimoto entropy).
- Utilized random forest algorithm for site prediction on arginine and lysine methylation datasets.
Main Results:
- MufeSPM achieved 82.45% accuracy for arginine methylation and 71.94% for lysine methylation.
- Evaluated the impact of different features and classifiers on prediction performance.
- Demonstrated superior performance compared to state-of-the-art prediction methods.
Conclusions:
- MufeSPM offers an effective and efficient computational approach for protein methylation site prediction.
- The method's reliance on intrinsic protein data makes it broadly applicable.
- This work advances the field of computational proteomics and biomarker discovery.
