Welcome to Antifungipept
Antifungipept is a comprehensive tool designed for the prediction and design of antifungal peptides. It integrates advanced quantitative structure-activity relationship (QSAR) models for accurate antifungal activity prediction and provides a robust platform for rational peptide design.
Key Features:
- Achieved identification accuracy for antifungal peptides exceeding 89%.
- Antifungal activity (minimum inhibitory concentration, MIC) predictions for multiple Candida species and Cryptococcus neoformans have reached experimental accuracy levels.
- The Antifungal Index (AFI) provides scoring functions for virtual screening and the rational design of antifungal and even antibacterial peptides.
- AFP20200317 database contains over 40 million putative antifungal peptide sequences.
Successful Applications
From the AFP20200317 database, two antifungal peptides have been discovered and synthesized, demonstrating significant efficacy in animal models infected with multidrug-resistant microbes. For detailed studies, see the references below:
-
DvAMP (AFP20200317_001408) combats cryptococcosis and carbapenem-resistant Acinetobacter baumannii infection:
- Yang et al., "Antimicrobial peptide DvAMP combats carbapenem-resistant Acinetobacter baumannii infection," International Journal of Antimicrobial Agents, 2024. DOI: 10.1016/j.ijantimicag.2024.107106
- Yang et al.,, "Novel antimicrobial peptide DvAMP serves as a promising antifungal agent," Bioorganic Chemistry, 2023. DOI: 10.1016/j.bioorg.2023.106679
-
MR-22 (AFP20200317_000127) against multidrug-resistant Escherichia coli:
- Tian et al., "The antibacterial activity and mechanism of a novel peptide MR-22 against multidrug-resistant Escherichia coli," Journal of Antimicrobial Chemotherapy, 2024. DOI: 10.3389/fcimb.2024.1334378
Model Performance Metrics
Table 1. Results of the Antifungal Peptide Classification Model
| Sample size | Calibration | Validation | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Acc. | Sen. | Spec. | F1 | MCC | Acc. | Sen. | Spec. | F1 | MCC | |
| n=9240, 2310 a | 0.95 | 0.95 | 0.95 | 0.95 | 0.90 | 0.89 | 0.90 | 0.89 | 0.89 | 0.79 |
a Sample size of calibration and validation set, respectively.
Table 2. Results of Antifungal Activity Prediction Models| Targets | Calibration | Validation | ||
|---|---|---|---|---|
| RMSE | R2 | RMSE | R2 | |
| C. albicans (n=1266, 317) | 0.69 | 0.90 | 1.23 | 0.66 |
| C. krusei (n=76, 19) | 0.48 | 0.94 | 1.10 | 0.69 |
| C. neoformans (n=220, 55) | 0.82 | 0.90 | 0.89 | 0.89 |
| C. parapsilosis (n=118, 30) | 0.73 | 0.90 | 1.17 | 0.69 |
Dataset Availability
Datasets for model training and validation:
- Antifungal peptide classification: Download
- Antifungal activity (pMIC) prediction:
Backend and Source Code
The backend of Antifungipept is the python package antifungal. We invite contributions to our open-source repository on GitHub.
References
Please cite these publications when using our data and methods:
- J. Zhang, et al. In Silico Design and Synthesis of Antifungal Peptides Guided by Quantitative Antifungal Activity. J. Chem. Inf. Model., 2024, 64 (10): 4277-4285. https://doi.org/10.1021/acs.jcim.4c00142.
- J. Zhang, et al. Large-Scale Screening of Antifungal Peptides Based on Quantitative Structure-Activity Relationship", ACS Med. Chem. Lett., 2022, 13(1): 99-104. https://pubs.acs.org/doi/10.1021/acsmedchemlett.1c00556.