Thet Su Win1,2, Aijaz Ahmad Malik1, Virapong Prachayasittikul3, Jarl E S Wikberg4, Chanin Nantasenamat1, Watshara Shoombuatong1. 1. Center of Data Mining & Biomedical Informatics, Faculty of Medical Technology, Mahidol University, Bangkok 10700, Thailand. 2. Department of Medical Laboratory Technology, University of Medical Technology, Yangon 11012, Myanmar. 3. Department of Clinical Microbiology & Applied Technology, Faculty of Medical Technology, Mahidol University, Bangkok 10700, Thailand. 4. Department of Pharmaceutical Biosciences, BMC, Uppsala University, Sweden.
Abstract
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.
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.
Entities:
Keywords:
classification; decision tree; hemolytic activity; hemolytic peptide; machine learning; random forest; support vector machine; therapeutic peptides
Authors: Tomás Ortiz-Rodríguez; Fernanda Mendoza-Acosta; Sheila A Martínez-Zavala; Rubén Salcedo-Hernández; Luz E Casados-Vázquez; Dennis K Bideshi; José E Barboza-Corona Journal: Probiotics Antimicrob Proteins Date: 2022-05-24 Impact factor: 4.609