Protein phosphorylation is one of the important post-translational modifications, many biological processes are related with phosphorylation, such as DNA repair, transcriptional regulation and signal transduction. Therefore, abnormal regulations of phosphorylation usually cause diseases. If we can accurately predict human phosphorylation sites, this could help to solve human-related diseases. Therefore, this study developed a kinase-specific phosphorylation prediction system, GasPhos, and proposed a feature selection method, called Gas, based on ant colony system and genetic algorithm, and the performance evaluation strategy was used to choose the best learning model for different kinases. Gas uses MDGI as heuristic value on path selection, and adopted binary transition strategies and proposed a new transition rules. GasPhos can predict phosphorylation sites for 20 kinases; however, this article is focuses on six kinases with the properties of larger and common. By 5-foldcross-validation, the average performance of GasPhos is higher than the other five phosphorylation prediction system 10% of Matthews’s correlation coefficient (MCC). In system analysis, we discussed different heuristic value, the role of GA, three kinds of transformation rules, different feature selection methods and the biological properties that frequently selected features; in addition, we observed the correlation of Weblogo and the selected feature number of Gas. In order to let users more precisely using GasPhos, we analyzed the performance of each prediction system for different functional proteins and explored two kinds of human disease-related phosphorylation.