Sequence-Based Prediction of Plant Allergenic Proteins: Machine Learning Classification Approach

Miroslava Nedyalkova; Mahdi Vasighi; Amirreza Azmoon; Ludmila Naneva; Vasil Simeonov

doi:10.1021/acsomega.2c02842

Sequence-Based Prediction of Plant Allergenic Proteins: Machine Learning Classification Approach

ACS Omega. 2023 Jan 20;8(4):3698-3704. doi: 10.1021/acsomega.2c02842. eCollection 2023 Jan 31.

Authors

Miroslava Nedyalkova^{1

2}, Mahdi Vasighi³, Amirreza Azmoon³, Ludmila Naneva⁴, Vasil Simeonov⁵

Affiliations

¹ Department of Chemistry, University of Fribourg, Chemin de Muse 9, CH-1700Fribourg, Switzerland.
² Faculty of Chemistry and Pharmacy, Inorganic Chemistry, University of Sofia, 1172Sofia, Bulgaria.
³ Department of Computer Science and Information Technology, Institute for Advanced Studies in Basic Sciences (IASBS), Zanjan45137, Iran.
⁴ Medical University, 9002Varna, Bulgaria.
⁵ Department of Inorganic Chemistry, University of Sofia, 1172Sofia, Bulgaria.

Abstract

This Article proposes a novel chemometric approach to understanding and exploring the allergenic nature of food proteins. Using machine learning methods (supervised and unsupervised), this work aims to predict the allergenicity of plant proteins. The strategy is based on scoring descriptors and testing their classification performance. Partitioning was based on support vector machines (SVM), and a k-nearest neighbor (KNN) classifier was applied. A fivefold cross-validation approach was used to validate the KNN classifier in the variable selection step as well as the final classifier. To overcome the problem of food allergies, a robust and efficient method for protein classification is needed.