iSP-RAAC

As the pathogen of malaria, malaria parasite secretes a variety of specific proteins for its growth and reproduction. The identification of the secretory proteins of malaria parasite has crucial reference significance for the development of anti-malaria vaccines as well as medicine. a computational classification method is developed to identify the secreted proteins of Plasmodium. Three sequence feature extraction methods including amino acid composition, dipeptide composition and tripeptide composition as well as reduced amino acids alphabets are adopted to illuminate protein sequences, we further use SVM to train and predict respectively and optimize the features. 74 reduced amino acids alphabets are employed to predict secretory proteins, the results show that the prediction outcomes are improved to 91.67% accuracy with 0.84 Mathew’s correlation coefficient (MCC) by dipeptide composition. And we hope our predictor by this method will assist annotation of protein function and provide reference value for drug and vaccine researches against malaria caused by P. falciparum.