Data-Driven Discovery of Antiviral Peptides Against PRRSV Using Multiple Machine Learning Models

Wafa YousafAbdul HaseebYongheng ShenHongquan LiKuohai FanNa SunPanpan SunYaogui SunHuizhen YangWei YinHua ZhangZhenbiao ZhangJia ZhongJianzhong WangNairui Huo^*

• Shanxi Agricultural University, Taiyuan, China

Cellular machinery is built upon proteins and their functional interrelationships. Their network evaluation is essential for a comprehensive insight into biological processes and may establish a foundation for predicting antivirulence. Antiviral peptides (AVPs) possess potenthave robust, broad-spectrum anti-virulence capabilities. Nevertheless, the existingcurrent predicted AVPs database is insufficient and necessitates more precise, reliable annotations. This study aimedintended to screen differentially expressed proteins and peptides of healthy and porcine reproductive and respiratory syndrome virus (PRRSV)-infected lungs, small and large intestine samples, throughusing proteomics, followed by predicting AVPs by employing machine learning (ML) and deep learning (DL). Models were developedconstructed exploiting significant features based on physicochemical characteristics, encompassingincluding amino acid composition (AAC), secondary structure, and hydrophilicity. Proteomics analysis facilitated peptide qualification through GO, KEGG, COG, and PPI analysis. To predict AVPs, we employed a DL graph neural network (GNN) by making its inaugural implication in this domain and benchmarked its efficacy against conventionaltraditional ML random forest (RF) and support vector machine (SVM) models. Results demonstrated that lysine, arginine, and leucine were ranked nearly 0.1, highlighting their significant importance in prediction. Additionally, the correlation heatmap showed that lysine and glutamate exhibited the strongest positive association (0.57). RF model achieved an area under the curve (AUC) of 0.95 ± 2, verified via 5-fold cross-validation. In contrast, GNN and SVM models yielded 0.94 ± 1 AUC, demonstrating comparable performance across models, and revealed that the RF model outperformed compared to the others. Consequently, these comparative predictive resultsoutcomes may serve as revolutionized and distinctive resources for the experimental validation and identification of PRRSV AVPs as prospective therapeutics.