IL10Pred: Prediction of immunosuppresive IL-10 inducing peptides

Welcome to the official documentation for IL-10pred, a computational method developed for the prediction and design of interleukin-10 (IL-10) inducing peptides. IL-10 is a potent anti-inflammatory cytokine that plays a crucial role in suppressing the immune system and maintaining immune homeostasis. This tool is designed to assist researchers in identifying peptides that can modulate immune responses for therapeutic purposes, such as treating autoimmune diseases and preventing organ transplant rejection. Web Server: http://crdd.osdd.net/raghava/il10pred/(https://webs.iiitd.edu.in/raghava/il10pred) Citation Nagpal, G., Usmani, S. S., Dhanda, S. K., Kaur, H., Singh, S., Sharma, M., & Raghava, G. P. S. (2017). Computer-aided designing of immunosuppressive peptides based on IL-10 inducing potential. Scientific Reports, 7, 42851. https://doi.org/10.1038/srep42851 GitHub:-https://github.com/Manish-IIITD-repository/IL10Pred About the Platform While numerous methods exist to predict T-helper epitopes for vaccine design, IL-10pred addresses the lack of tools for predicting peptides that induce specific immunosuppressive cytokines. By utilizing machine learning models trained on experimentally validated data, IL-10pred can discriminate between IL-10 inducing and non-inducing peptides with high accuracy. Dataset Overview The models were trained and tested on a high-quality dataset: IL-10 Inducing Peptides: 394 experimentally validated sequences. Non-inducing Peptides: 848 experimentally validated sequences. Key Features Prediction and Design Induction Prediction: Predicts whether a peptide sequence is likely to induce IL-10 secretion. Mutant Generation: Allows users to generate all possible single-substitution analogs of a peptide to identify variants with enhanced IL-10 inducing potential. Virtual Screening: Facilitates the screening of large peptide libraries to discover novel immunosuppressive leads. Protein Mapping: Scans whole protein sequences to identify specific regions or overlapping segments that may induce IL-10. Model Performance The platform employs various machine learning techniques, with Random Forest achieving the best results: Accuracy: 81.24% using dipeptide composition. Matthews Correlation Coefficient (MCC): 0.59. Technical Overview IL-10pred leverages sequence-based features and motif analysis to model the immunosuppressive potential of peptides. Machine Learning: Developed using algorithms like Random Forest, Support Vector Machines (SVM), and Logistic Regression via the WEKA and Scikit-learn packages. Input Features: Models are based on amino acid composition and dipeptide composition. Motif Analysis: Incorporates information about motifs (e.g., "EEL", "LLE", "LAA") that are significantly more frequent in IL-10 inducing peptides. Multi-Platform Accessibility Web Interface: A user-friendly online portal for peptide prediction and analysis. Mobile App: An Android-based application ("IL-10pred") for performing predictions on the go. Standalone Software: Desktop versions (Linux, Mac, and Windows) available for offline batch processing. Applications Immunotherapy: Designing peptides to treat autoimmune disorders and inflammatory conditions. Transplantation: Identifying leads for suppressing graft-versus-host disease and organ rejection. Vaccinology: Designing subunit vaccines where controlled immune suppression is required to avoid over-inflammation. Contact & Authors Prof. Gajendra P. S. Raghava Department of Computational Biology, Indraprastha Institute of Information Technology (IIIT-Delhi), New Delhi, India. Email: [e-mail] / [e-mail] License This resource is open-access and distributed under the terms of the Creative Commons Attribution 4.0 International License, permitting unrestricted use and distribution provided the original work is properly credited.