Antifp: In Silico Approach for Prediction of Antifungal Peptides

Welcome to the official repository for Antifp, a computational method and web server for predicting and designing antifungal peptides (AFPs) from amino acid sequences. This resource is designed to support researchers in antifungal therapeutics, antimicrobial peptide research, and computational drug discovery. Web Server: http://webs.iiitd.edu.in/raghava/antifp Standalone Software: Available via the Download menu on the web server Mobile App (Android): Available via the Download menu on the web server Citation Agrawal, P., Bhalla, S., Chaudhary, K., Kumar, R., Sharma, M., & Raghava, G. P. S. (2018). In Silico Approach for Prediction of Antifungal Peptides. Frontiers in Microbiology, 9:323. https://doi.org/10.3389/fmicb.2018.00323 About the Tool Antifp is a sequence-based computational method developed to predict and design antifungal peptides using Support Vector Machine (SVM) and other machine learning classifiers. It is built on the largest AFP dataset to date (1459 unique AFPs) and employs a wide range of peptide features including amino acid composition, dipeptide composition, binary profiles, and terminus-based patterns. The tool integrates data from: DRAMP — Data Repository of Antimicrobial Peptides (1585 AFPs extracted, 1459 unique after filtering) SwissProt (for randomly generated negative peptides in DS2 and Main datasets) AMPs with no antifungal activity (for negative dataset in DS1)