Welcome to the official documentation for IFNepitope, a comprehensive computational tool developed to predict and design interferon-gamma (IFN-γ) inducing peptides. IFN-γ is a vital cytokine secreted by MHC class II-activated CD4+ T helper cells, playing a substantial role in controlling infections like Mycobacterium tuberculosis.
Web Server: http://crdd.osdd.net/raghava/ifnepitope/(https://webs.iiitd.edu.in/raghava/ifnepitope)
Dhanda, S. K., Vir, P., & Raghava, G. P. S. (2013). Designing of interferon-gamma inducing MHC class-II binders. Biology Direct, 8, 30. https://doi.org/10.1186/1745-6150-8-30
zonedo:_(https://doi.org/10.5281/zenodo.20096942)
IFNepitope is the first method developed to predict the specific type of cytokine (specifically IFN-γ) secreted by T-helper epitopes. While many tools can predict MHC class II binders, IFNepitope adds a crucial layer of functional annotation by determining if those binders will actually induce an IFN-γ response.
The models were trained and validated on extensive datasets:
- Main Dataset: Contains 3,705 IFN-γ inducing and 6,728 non-IFN-γ inducing MHC class II binders.
- IFNgOnly Dataset: Contains 4,483 IFN-γ inducing epitopes and 2,160 epitopes that induce other cytokines.
- Induction Prediction: Predicts whether a given peptide is an IFN-γ inducer or a non-inducer.
- Motif Identification: Utilizes motifs identified via MERCI software that are characteristic of IFN-γ inducing binders.
- Positional Conservation: Analyzes the positional conservation of residues at the N and C terminals to enhance prediction accuracy.
- Hybrid Approach: The SVM-based models achieved high accuracy by utilizing amino acid composition and positional information.
- Sequence Scans: Users can scan entire protein sequences to identify potential IFN-γ inducing regions.
IFNepitope utilizes various sequence-based features to model the biological activity of T-helper epitopes.
- Machine Learning: Built using Support Vector Machines (SVM) and validated through 5-fold cross-validation.
- Input Features: Includes amino acid composition, dipeptide composition, and binary profiles.
- Motif Library: Incorporates a library of motifs that are significantly enriched in IFN-γ inducing peptides.
- Vaccine Design: Identifying T-helper epitopes that will trigger a protective IFN-γ response.
- Immunotherapy: Designing therapeutic peptides to modulate cytokine production in autoimmune or infectious diseases.
- Epitope Mapping: Mapping functional regions in antigens that are responsible for cell-mediated immunity.
Prof. Gajendra P. S. Raghava Bioinformatics Centre, CSIR-Institute of Microbial Technology, Chandigarh, India.
Email: raghava@imtech.res.in
This resource is open-access and distributed under the terms of the Creative Commons Attribution License, permitting unrestricted use and distribution provided the original work is properly credited.