A New Robust Method for Predicting Hemolytic Toxicity from Peptide Se-quence

The desirable pharmacological properties and a broad number of therapeutic activities have placed peptides as promising drugs over small organic molecules and antibody drugs. Nevertheless, toxic effects such as hemolysis have hampered the development of such promising drugs. Hence, a reliable computational tool to predict peptide hemolytic toxicity is enormously useful before synthesis and ex-perimental evaluation. Currently, four web servers that predict hemolytic activity using Machine Learning (ML) algorithms; however, they exhibit some limitations such as the need for a reliable negative set and limited application domain. Hence, we developed a robust model based on a novel theoretical approach that combines network science and a multi-query similarity searching (MQSS) method. A total of 1152 initial models were constructed from 144 scaffolds generated in a previous report. These were evaluated on external datasets, and the best models were fused and improved. Our best MQSS model I1 outperformed all state-of-the-art ML-based models and was used to characterize the prevalence of hemolytic toxicity on therapeutic peptides. Based on our model’s estimation, the number of hemolytic peptides might be 3.9-fold higher than the reported.