Welcome to the official repository for AntiBP2, an improved and robust computational method for predicting and classifying antibacterial peptides (ABPs) from amino acid sequences. This resource is designed to support researchers in antimicrobial peptide therapeutics, innate immunity, and computational drug discovery.
Web Server: https://webs.iiitd.edu.in/raghava/antibp2/
Lata, S., Mishra, N. K., & Raghava, G. P. S. (2010). AntiBP2: improved version of antibacterial peptide prediction. BMC Bioinformatics, 11(Suppl 1):S19. https://doi.org/10.1186/1471-2105-11-S1-S19
AntiBP2 is an updated version of the original AntiBP method, developed to predict and classify antibacterial peptides using Support Vector Machine (SVM) models trained on a significantly larger dataset. It consolidates sequence-level features into a unified prediction framework, enabling systematic identification of antibacterial peptides from raw amino acid sequences.
The tool integrates data from:
- Antimicrobial Peptide Database (APD)
- Swiss-Prot / UniProt
- MitPred dataset (for negative peptide generation)
Large Dataset
- 999 unique antibacterial peptides (positive set)
- 999 randomly extracted non-antibacterial peptides (negative set)
- Nearly double the dataset size compared to the original AntiBP
Multiple Prediction Models
- NT15 — binary pattern of first 15 N-terminal residues
- CT15 — binary pattern of last 15 C-terminal residues
- NTCT15 — combined N- and C-terminal binary patterns
- Whole Peptide — amino acid composition of full-length peptide
Source Classification
- 5 biological sources: Bacteria, Frog, Insects, Mammals, Plants
- Overall classification accuracy up to 98.95%
Subfamily Classification
- Insect families: Apidaecin, Attacin, Cecropin, Invertebrate Defensin, Lebocin
- Mammalian families: Alpha-defensin, Beta-defensin, Cathelicidin, Hepcidin, Histatin
- Frog families: Bombinin, Brevinin, Caerin, Dermaseptin, Other
Rich Performance Metrics
- Sensitivity, Specificity, Accuracy, and MCC for every model
- Validated on an independent blind dataset of 466 sequences
AntiBP2 provides SVM-based prediction along with:
- Antibacterial activity prediction (antibacterial vs. non-antibacterial)
- Source-level classification of predicted ABPs
- Subfamily-level classification (insects, frogs, mammals)
- Terminal residue preference analysis (N- and C-terminus sequence logos)
- Whole peptide composition profiling
Models were developed using five-fold cross-validation:
| Model | Accuracy (%) | MCC |
|---|---|---|
| NT15 | 85.46 | 0.705 |
| CT15 | 85.05 | 0.701 |
| NTCT15 | 91.64 | 0.831 |
| Whole Peptide | 92.14 | 0.843 |
Performance on independent dataset (466 sequences):
| Model | Accuracy (%) |
|---|---|
| NT15 | 77.47 |
| CT15 | 77.04 |
| NTCT15 | 84.76 |
| Whole Peptide | 87.55 |
- ~100% increase in training data size
- Added source-level classification (5 biological origins)
- Added subfamily-level classification for insects, frogs, and mammals
- Retained whole peptide model for short peptides (<15 residues)
- Re-validated sequence logo trends on the larger dataset
- Independent blind dataset evaluation on 466 Swiss-Prot sequences
- Terminal binary models (NT15, CT15, NTCT15) cannot process peptides shorter than 15 residues
- Negative dataset is computationally generated (no experimentally verified non-ABPs exist)
- Low sequence homology among ABPs makes family-level generalization challenging
- Antibacterial peptide discovery and design
- Screening peptide libraries for antimicrobial activity
- Machine learning model training for AMP research
- Combat against antibiotic-resistant bacteria
- Innate immunity and host-defense research
Prof. Gajendra P. S. Raghava raghava@imtech.res.in Institute of Microbial Technology (IMTECH), Sector 39A, Chandigarh, India
Sneh Lata — sheh@imtech.res.in Nitish K Mishra — nitish@imtech.res.in
Developed at the Institute of Microbial Technology (IMTECH), Chandigarh, India
This tool is distributed under the Creative Commons Attribution License (CC BY 2.0)
Supported by:
- Council of Scientific and Industrial Research (CSIR), New Delhi
- Department of Biotechnology (DBT), Government of India
Sneh Lata and Nitish Kumar Mishra are Senior Research Fellows financially supported by CSIR, New Delhi, India.
We acknowledge all researchers whose published work on antibacterial peptides contributed to this dataset.