GBDT_KgluSite: An improved computational prediction model for lysine glutarylation sites based on Feature Fusion and GBDT classifier

Background: Lysine glutarylation(Kglu) is one of the most important Post-translational modifications(PTMs), which plays significant roles in various cellular functions, including metabolism, mitochondrial processes, and translation. Therefore, accurate identification of Kglu site is important for elucidating protein molecular function. Due to the time-consuming and expensive limitations of traditional biological experiment, computational-based Kglu site prediction research are gaining more and more attention. Results: In this study, we proposed a new model named GBDT_KgluSite to identify Kglu and non-Kglu sequences based on the gradient-boosting decision tree (GBDT). Here, sequence-based features, physicochemical property-based features, structural-based features, and evolutionary-derived features were used to characterize proteins. The imbalance between positive and negative samples was addressed using the NearMiss-3 approach, and extraneous data was eliminated using the Elastic Net. The experimental results show that GBDT_KgluSite has good robustness and generalization ability, with accuracy and AUC values of 93.73%, and 98.14% on five-fold cross-validation as well as 90.11%, and 96.75% on the independent test dataset, respectively. Conclusion: GBDT_KgluSite is an effectively computational method for identifying Kglu sites in protein sequences. It has good stability and generalization ability and could be useful for the identification of new Kglu sites in Mus musculus protein. The code and dataset of GBDT_KgluSite is available at https://github.com/flyinsky6/GBDT_KgluSite.