Thet Su WinAijaz Ahmad MalikVirapong PrachayasittikulJarl E. S WikbergChanin NantasenamatWatshara ShoombuatongMahidol UniversityUniversity of Medical TechnologyUppsala Universitet2018-12-212019-03-142018-12-212019-03-142017-03-01Future Medicinal Chemistry. Vol.9, No.3 (2017), 275-29117568927175689192-s2.0-85013468550https://repository.li.mahidol.ac.th/handle/20.500.14594/41972© 2017 Future Science Ltd. Aim: Toxicity arising from hemolytic activity of peptides hinders its further progress as drug candidates. Materials & methods: This study describes a sequence-based predictor based on a random forest classifier using amino acid composition, dipeptide composition and physicochemical descriptors (named HemoPred). Results: This approach could outperform previously reported method and typical classification methods (e.g., support vector machine and decision tree) verified by fivefold cross-validation and external validation with accuracy and Matthews correlation coefficient in excess of 95% and 0.91, respectively. Results revealed the importance of hydrophobic and Cys residues on α-helix and β-sheet, respectively, on the hemolytic activity. Conclusion: A sequence-based predictor which is publicly available as the web service of HemoPred, is proposed to predict and analyze the hemolytic activity of peptides.Mahidol UniversityBiochemistry, Genetics and Molecular BiologyArticleSCOPUS10.4155/fmc-2016-0188