Related Experiment Video
Updated: Jan 5, 2026
11:45
The CryoAPEX Method for Electron Microscopy Analysis of Membrane Protein Localization Within Ultrastructurally-Preserved Cells
Published on: February 27, 2020
10.1K
Prediction of apoptosis protein subcellular location based on position-specific scoring matrix and isometric mapping
Xiaoli Ruan1, Dongming Zhou2, Rencan Nie1
1Information College, Yunnan University, Kunming, 650504, China.
Medical & Biological Engineering & Computing
|October 18, 2019
Summary
Predicting apoptosis protein subcellular localization is key for disease understanding and drug development. A new method, ERT-ECT-PSSM-IS, improves prediction accuracy using evolutionary transformations and machine learning.
Area of Science:
- Computational biology
- Bioinformatics
- Molecular biology
Background:
- Apoptosis proteins are implicated in various diseases.
- Understanding their subcellular localization aids disease mechanism insights and drug discovery.
- Current prediction methods based on primary sequences have limitations in accuracy.
Purpose of the Study:
- To develop an improved computational method for predicting the subcellular localization of apoptosis proteins.
- To enhance the accuracy and robustness of apoptosis protein subcellular localization prediction.
Main Methods:
- Utilized Position-Specific Scoring Matrix (PSSM) for feature extraction.
- Employed Evolutionary Row Transformation (ERT) and Evolutionary Column Transformation (ECT) for local and global feature extraction (ERT-ECT-PSSM).
- Applied an Improved Isometric Mapping Algorithm (I-SMA) for feature reduction.
- Classified predictions using a Support Vector Machine (SVM) and validated with jackknife cross-validation.
Main Results:
- The ERT-ECT-PSSM-IS method extracts richer feature expressions compared to existing approaches.
- Demonstrated superior predictive performance and robustness in predicting apoptosis protein subcellular localization.
- Achieved high accuracy across multiple benchmark datasets (ZD98, ZW225, CL317).
Conclusions:
- The proposed ERT-ECT-PSSM-IS method offers a significant advancement in predicting apoptosis protein subcellular localization.
- This approach provides a more accurate and reliable tool for bioinformatics research.
- Enhanced prediction capabilities can accelerate the development of novel therapeutic strategies targeting apoptosis pathways.
