Classifying Regulatory Pathways Using Graph and Biochemical Properties
Author Information
Author(s): Huang Tao, Chen Lei, Cai Yu-Dong, Chou Kuo-Chen
Primary Institution: Institute of Systems Biology, Shanghai University
Hypothesis
Given a regulatory pathway system consisting of a set of proteins, can we predict which pathway class it belongs to?
Conclusion
The study developed a method that successfully predicts the class of regulatory pathways with a success rate of 78.8%.
Supporting Evidence
- The method achieved a success rate of 78.8% in classifying regulatory pathways.
- Feature extraction included biochemical, physicochemical, and functional properties.
- Cross-validation was performed using a jackknife test.
Takeaway
The researchers created a way to figure out what type of job a group of proteins does in a cell, and they did a good job at it!
Methodology
The study used a novel approach involving feature extraction from regulatory pathways and applied the minimum redundancy maximum relevance method for classification.
Limitations
The study is preliminary and may require further validation with additional datasets.
Statistical Information
P-Value
0.032588
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website