A study on B-cell epitope prediction based on QSVM and VQC

Abstract

This study investigates quantum computing's role in B-cell epitope prediction using Quantum Support Vector Machine (QSVM) and Variational Quantum Classifier (VQC). It highlights the potential of quantum machine learning in bioinformatics, addressing computational efficiency limitations of traditional methods as data complexity grows. QSVM uses quantum kernel functions for data mapping, while VQC employs parameterized quantum circuits for classification. Results show QSVM and VQC achieving 70% and 73% accuracy, respectively, with QSVM excelling in balancing classes. Despite challenges like computational demands and hardware limitations, quantum methods show promise, suggesting future improvements with ongoing advancements.