Related Experiment Video
Updated: Oct 3, 2025
07:59
A High Throughput MHC II Binding Assay for Quantitative Analysis of Peptide Epitopes
Published on: March 25, 2014
15.1K
IL13Pred: A method for predicting immunoregulatory cytokine IL-13 inducing peptides
Shipra Jain1, Anjali Dhall1, Sumeet Patiyal1
1Department of Computational Biology, Indraprastha Institute of Information Technology, Okhla Phase 3, New Delhi, 110020, India.
Computers in Biology and Medicine
|February 13, 2022
Summary
Predicting Interleukin 13 (IL-13) inducing peptides is crucial for developing safe immunotherapeutics. A new machine learning model, IL-13Pred, accurately identifies these peptides, aiding in therapeutic design.
Area of Science:
- Computational biology
- Immunoinformatics
- Biotechnology
Background:
- Interleukin 13 (IL-13) is a cytokine linked to allergic diseases and cancer.
- Elevated IL-13 levels are observed in severe COVID-19 cases.
- Accurate prediction of IL-13 inducing peptides is vital for safe protein therapeutic design.
Purpose of the Study:
- To develop a computational method for predicting IL-13 inducing peptides.
- To design and scan potential IL-13 inducing regions in proteins.
Main Methods:
- Utilized a dataset of 313 IL-13 inducing and 2908 non-inducing peptides.
- Extracted 95 key features using support vector classifier with L1 penalty (SVC-L1).
- Developed and evaluated machine learning models, including XGBoost, using five-fold cross-validation.
Main Results:
- The best XGBoost model achieved an AUC of 0.83 on the training set and 0.80 on an independent dataset.
- Identified specific SARS-CoV-2 variants associated with increased IL-13 induction in COVID-19 patients.
Conclusions:
- The developed model, IL-13Pred, provides precise prediction of IL-13 inducing peptides.
- IL-13Pred is available as a web server and standalone package for broader accessibility and analysis.
