Related Experiment Video
Updated: May 28, 2026
17:12
Profiling of Methyltransferases and Other S-adenosyl-L-homocysteine-binding Proteins by Capture Compound Mass Spectrometry (CCMS)
Published on: December 20, 2010
MemHyb: predicting membrane protein types by hybridizing SAAC and PSSM
Maqsood Hayat1, Asifullah Khan
1Department of Computer and Information Sciences, Pakistan Institute of Engineering and Applied Sciences (PIEAS), Islamabad, Pakistan.
Journal of Theoretical Biology
|October 18, 2011
Summary
This study introduces an automated method using sequence data to classify membrane protein types, crucial for drug discovery. The developed system achieved high accuracy, aiding researchers in identifying new membrane proteins.
Area of Science:
- Bioinformatics
- Molecular Biology
- Computational Biology
Background:
- Membrane proteins are vital drug targets, accounting for approximately 50% of current therapeutics.
- Understanding membrane protein structure and function is critical for biological and pharmacological research.
- Automated methods for identifying membrane protein types from sequence data are highly advantageous.
Purpose of the Study:
- To develop an automated classification system for membrane protein types based on primary sequence information.
- To effectively discriminate between different membrane protein types using computational approaches.
Main Methods:
- Utilized evolutionary and physicochemical features for classification.
- Employed a support vector machine (SVM) with error correction code.
- Integrated position-specific scoring matrices and split amino acid composition for sequence encoding.
Main Results:
- Achieved a highest success rate of 91.1% and 93.4% on two independent datasets.
- RBF-based SVM with Bose, Chaudhuri, Hocquenghem coding demonstrated superior performance.
- Leave-one-out cross-validation confirmed the robustness of the classification model.
Conclusions:
- The proposed MemHyb-SVM approach is an effective tool for discriminating membrane protein types.
- This method can significantly assist researchers in drug discovery, cell biology, and bioinformatics.
- A web server is available for accessing the MemHyb-SVM tool.
