Publication: HemoPred: A web server for predicting the hemolytic activity of peptides
Issued Date
2017-03-01
Resource Type
ISSN
17568927
17568919
17568919
Other identifier(s)
2-s2.0-85013468550
Rights
Mahidol University
Rights Holder(s)
SCOPUS
Bibliographic Citation
Future Medicinal Chemistry. Vol.9, No.3 (2017), 275-291
Suggested Citation
Thet Su Win, Aijaz Ahmad Malik, Virapong Prachayasittikul, Jarl E. S Wikberg, Chanin Nantasenamat, Watshara Shoombuatong HemoPred: A web server for predicting the hemolytic activity of peptides. Future Medicinal Chemistry. Vol.9, No.3 (2017), 275-291. doi:10.4155/fmc-2016-0188 Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/41972
Research Projects
Organizational Units
Authors
Journal Issue
Thesis
Title
HemoPred: A web server for predicting the hemolytic activity of peptides
Other Contributor(s)
Abstract
© 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.