Protein Subcellular Location Prediction Based on Pseudo Amino Acid Composition and Immune Genetic Algorithm
Protein subcellular location prediction with computational method is still a hot spot in bioinformatics. In this paper, we present a new method to predict protein subcellular location, which based on pseudo amino acid composition and immune genetic algorithm. Hydrophobic patterns of amino acid couples and approximate entropy are introduced to construct pseudo amino acid composition. Immune Genetic algorithm (IGA) is applied to find the fittest weight factors for pseudo amino acid composition, which are crucial in this method. As such, high success rates are obtained by both self-consistency test and jackknife test. More than 80% predictive accuracy is achieved in independent dataset test. The result demonstrates that this new method is practical. And, the method illuminates that the hydrophobic patterns of protein sequence influence its subcellular location.
KeywordsSupport Vector Machine Markov Chain Model Simple Genetic Algorithm Approximate Entropy Protein Subcellular Location
Unable to display preview. Download preview PDF.
- 19.Hong, B., Tang, Q.Y., Yang, F.S.: Apen and Cross-ApEn: Property, Fast Algorithm and Preliminary Application to the Study of EEG and Cognition. Signal Process 15, 100–108 (1999)Google Scholar