ILeukin10Pred: A Computational Approach for Predicting IL-10-Inducing Immunosuppressive Peptides Using Combinations of Amino Acid Global Features

Simple Summary Interleukin-10 is a cytokine that exhibits potent anti-inflammatory characteristics that play an essential role in limiting the host's immune response to pathogens and regulating the growth or differentiation of various immune cells. Moreover, interleukin-10 prediction via conventional approaches is time-consuming and labor-intensive. Hence, researchers are inclined towards an alternative approach to predict interleukin-10-inducing peptides. Additionally, numerous in silico tools are available to predict T cell epitopes. These methods generally follow a direct or indirect approach where they directly predict cytotoxic T-lymphocyte epitopes rather than major histocompatibility complex binders or indirectly predict single components of the T cell recognition pathway. However, very few studies are available that address cytokine-specific predictions. Our research utilized a computer-aided approach to develop a model to predict IL-10-inducing peptides. This study outperformed the existing state-of-the-art method and achieved an accuracy of 87.5% and Matthew's correlation coefficient (MCC) of 0.755 on the hybrid feature types and outperformed an existing state-of-the-art method based on dipeptide compositions that achieved an accuracy of 81.24% and an MCC value of 0.59. Therefore, our model is promising to assist in predicting immunosuppressive peptides that induce interleukin-10 cytokines. Interleukin (IL)-10 is a homodimer cytokine that plays a crucial role in suppressing inflammatory responses and regulating the growth or differentiation of various immune cells. However, the molecular mechanism of IL-10 regulation is only partially understood because its regulation is environment or cell type-specific. In this study, we developed a computational approach, ILeukin10Pred (interleukin-10 prediction), by employing amino acid sequence-based features to predict and identify potential immunosuppressive IL-10-inducing peptides. The dataset comprises 394 experimentally validated IL-10-inducing and 848 non-inducing peptides. Furthermore, we split the dataset into a training set (80%) and a test set (20%). To train and validate the model, we applied a stratified five-fold cross-validation method. The final model was later evaluated using the holdout set. An extra tree classifier (ETC)-based model achieved an accuracy of 87.5% and Matthew's correlation coefficient (MCC) of 0.755 on the hybrid feature types. It outperformed an existing state-of-the-art method based on dipeptide compositions that achieved an accuracy of 81.24% and an MCC value of 0.59. Our experimental results showed that the combination of various features achieved better predictive performance..