IL13Pred: A method for predicting immunoregulatory cytokine IL-13 inducing peptides

Shipra Jain; Anjali Dhall; Sumeet Patiyal; Gajendra P S Raghava

doi:10.1016/j.compbiomed.2022.105297

IL13Pred: A method for predicting immunoregulatory cytokine IL-13 inducing peptides

Comput Biol Med. 2022 Apr:143:105297. doi: 10.1016/j.compbiomed.2022.105297. Epub 2022 Feb 8.

Authors

Shipra Jain¹, Anjali Dhall², Sumeet Patiyal³, Gajendra P S Raghava⁴

Affiliations

¹ Department of Computational Biology, Indraprastha Institute of Information Technology, Okhla Phase 3, New Delhi, 110020, India. Electronic address: shipra@iiitd.ac.in.
² Department of Computational Biology, Indraprastha Institute of Information Technology, Okhla Phase 3, New Delhi, 110020, India. Electronic address: anjalid@iiitd.ac.in.
³ Department of Computational Biology, Indraprastha Institute of Information Technology, Okhla Phase 3, New Delhi, 110020, India. Electronic address: sumeetp@iiitd.ac.in.
⁴ Department of Computational Biology, Indraprastha Institute of Information Technology, Okhla Phase 3, New Delhi, 110020, India. Electronic address: raghava@iiitd.ac.in.

PMID: 35152041
DOI: 10.1016/j.compbiomed.2022.105297

Abstract

Background: Interleukin 13 (IL-13) is an immunoregulatory cytokine, primarily released by activated T-helper 2 cells. IL-13 induces the pathogenesis of many allergic diseases, such as airway hyperresponsiveness, glycoprotein hypersecretion, and goblet cell hyperplasia. In addition, IL-13 inhibits tumor immunosurveillance, leading to carcinogenesis. Since elevated IL-13 serum levels are severe in COVID-19 patients, predicting IL-13 inducing peptides or regions in a protein is vital to designing safe protein therapeutics particularly immunotherapeutic.

Objective: The present study describes a method to develop, predict, design, and scan IL-13 inducing peptides.

Methods: The dataset experimentally validated 313 IL-13 inducing peptides, and 2908 non-inducing homo-sapiens peptides extracted from the immune epitope database (IEDB). A total of 95 key features using the linear support vector classifier with the L1 penalty (SVC-L1) technique was extracted from the originally generated 9165 features using Pfeature. These key features were ranked based on their prediction ability, and the top 10 features were used to build machine learning prediction models. Various machine learning techniques were deployed to develop models for predicting IL-13 inducing peptides. These models were trained, tested, and evaluated using five-fold cross-validation techniques; the best model was evaluated on an independent dataset.

Results: Our best model based on XGBoost achieves a maximum AUC of 0.83 and 0.80 on the training and independent dataset, respectively. Our analysis indicates that certain SARS-COV2 variants are more prone to induce IL-13 in COVID-19 patients.

Conclusion: The best performing model was incorporated in web-server and standalone package named 'IL-13Pred' for precise prediction of IL-13 inducing peptides. For large dataset analysis standalone package of IL-13Pred is available at (https://webs.iiitd.edu.in/raghava/il13pred/) webserver and over GitHub link: https://github.com/raghavagps/il13pred.

Keywords: COVID-19; IL-4 receptors; Immunoregulatory cytokine; Interleukin 13; SARS-COV2.