MFPSP: Identification of fungal species-specific phosphorylation site using offspring competition-based genetic algorithm

Protein phosphorylation is essential in various signal transduction and cellular processes. To date, most tools are designed for model organisms, but only a handful of methods are suitable for predicting task in fungal species, and their performance still leaves much to be desired. In this study, a novel tool called MFPSP is developed for phosphorylation site prediction in multi-fungal species. The amino acids sequence features were derived from physicochemical and distributed information, and an offspring competition-based genetic algorithm was applied for choosing the most effective feature subset. The comparison results shown that MFPSP achieves a more advanced and balanced performance to several state-of-the-art available toolkits. Feature contribution and interaction exploration indicating the proposed model is efficient in uncovering concealed patterns within sequence. We anticipate MFPSP to serve as a valuable bioinformatics tool and benefiting practical experiments by pre-screening potential phosphorylation sites and enhancing our functional understanding of phosphorylation modifications in fungi. The source code and datasets are accessible at https://github.com/AI4HKB/MFPSP/.Author summary: Post-translational modifications (PTMs) is one of the key determinant factors of protein’s activity, stability, localization and folding. With the explosive growth of proteomics data, pre-screening of amino acid that with high potential to be phosphorylated is urgently needed before proceeding of wet experiment for the purpose of mechanism and function investigation. Although great progresses have been achieved in PTMs prediction, research on fungi has long been overlooked as algorithms suitable for fungal species PTMs identification are severely lacking. To fill this research gap, we developed a species-specific PTMs identification method, called MFPSP, for eight fungal species. In order to extract informative features, multiple sequence information was generated. The features were optimized by performing a global search strategy to avoid the local optima that traditional feature selection methods may encounter. Moreover, the effectiveness of MFPSP was proved by comparison with current excellent algorithms. It is expected our proposed model can effectively predict the PTMs of fungus and provide reliable candidates for further biological experiments.