Predicting viral proteins that evade the innate immune system: a machine learning-based immunoinformatics tool

Abstract

Viral proteins that evade the host's innate immune response play a crucial role in pathogenesis, significantly impacting viral infections and potential therapeutic strategies. Identifying these proteins through traditional methods is challenging and time-consuming due to the complexity of virus-host interactions. Leveraging advancements in computational biology, we present VirusHound-II, a novel tool that utilizes machine learning techniques to predict viral proteins evading the innate immune response with high accuracy. We evaluated a comprehensive range of machine learning models, including ensemble methods, neural networks, and support vector machines. Using a dataset of 1337 viral proteins known to evade the innate immune response (VPEINRs) and an equal number of non-VPEINRs, we employed pseudo amino acid composition as the molecular descriptor. Our methodology involved a tenfold cross-validation strategy on 80% of the data for training, followed by testing on an independent dataset comprising the remaining 20%. The random forest model demonstrated superior performance metrics, achieving 0.9290 accuracy, 0.9283 F1 score, 0.9354 precision, and 0.9213 sensitivity in the independent testing phase. These results establish VirusHound-II as an advancement in computational virology, accessible via a user-friendly web application. We anticipate that VirusHound-II will be a crucial resource for researchers, enabling the rapid and reliable prediction of viral proteins evading the innate immune response. This tool has the potential to accelerate the identification of therapeutic targets and enhance our understanding of viral evasion mechanisms, contributing to the development of more effective antiviral strategies and advancing our knowledge of virus-host interactions.

Keywords: Deep learning; Immune system; Machine learning; Protein; Virus.

Fig. 1

General workflow used in this study. Starting from sequences of real VPEINRs and non-VPEINRs, molecular descriptors (PAAC and DPC) were computed. The obtained descriptor values were used to create datasets with binary labels (1 for VPEINRs, 0 for non-VPEINRs). These datasets were split into 80% training and 20% testing sets. Various machine learning algorithms, including RF, ET, LGBM, XGBoost, MLP, SVM (radial and linear kernels), GPC, GBC, KNN, ABC, DTC, QDA, NB, RC, and LR, were evaluated using tenfold stratified cross-validation on the training set. The models were then assessed on the independent test set. Performance was monitored using multiple metrics including accuracy, precision, recall, F1 score, kappa, and MCC. Based on these performance measures, the best predictive model was selected for incorporation into a web application developed in Python 3.11