AntiBP: Analysis and prediction of antibacterial peptides

Welcome to the official repository for AntiBP, a computational platform developed for the analysis and prediction of antibacterial peptides using machine learning techniques such as Support Vector Machines (SVM), Artificial Neural Networks (ANN), and Quantitative Matrices (QM). Web Server: https://webs.iiitd.edu.in/raghava/antibp/ Brief Description Antibacterial peptides are important components of the innate immune system and serve as natural defense molecules against pathogenic bacteria. Due to the rapid emergence of antibiotic-resistant bacterial strains, antibacterial peptides have become promising candidates for the development of next-generation peptide therapeutics. AntiBP was developed to computationally predict antibacterial peptides directly from amino acid sequences. The study analyzed experimentally validated antibacterial peptides to identify residue preferences, positional patterns, and compositional biases associated with antibacterial activity. The prediction models were developed using machine learning approaches including Support Vector Machine (SVM), Artificial Neural Networks (ANN), and Quantitative Matrices (QM). The system utilizes N-terminal residues, C-terminal residues, and combined terminal sequence information to classify peptides as antibacterial or non-antibacterial. The platform provides tools for peptide prediction, antibacterial region mapping, and peptide screening, making it useful for peptide therapeutics, computational biology, and antimicrobial drug discovery research. Citation Lata, S., Sharma, B. K., & Raghava, G. P. S. (2007). Analysis and prediction of antibacterial peptides. BMC Bioinformatics, 8, 263. https://doi.org/10.1186/1471-2105-8-263 About the Platform AntiBP is a sequence-based prediction server designed to identify antibacterial peptides using computational learning techniques. The platform focuses on: Prediction of antibacterial peptides Analysis of terminal residue patterns Mapping antibacterial regions in proteins Computational peptide screening The study analyzed: 486 antibacterial peptides from APD database 436 non-redundant antibacterial peptides Random non-antibacterial peptide datasets