Non-Hemolytic Peptide Classification Using A Quantum Support Vector Machine

Quantum machine learning (QML) is one of the most promising applications ofquantum computation. However, it is still unclear whether quantum advantagesexist when the data is of a classical nature and the search for practical,real-world applications of QML remains active. In this work, we apply thewell-studied quantum support vector machine (QSVM), a powerful QML model, to abinary classification task which classifies peptides as either hemolytic ornon-hemolytic. Using three peptide datasets, we apply and contrast theperformance of the QSVM, numerous classical SVMs, and the best publishedresults on the same peptide classification task, out of which the QSVM performsbest. The contributions of this work include (i) the first application of theQSVM to this specific peptide classification task, (ii) an explicitdemonstration of QSVMs outperforming the best published results attained withclassical machine learning models on this classification task and (iii)empirical results showing that the QSVM is capable of outperforming many (andpossibly all) classical SVMs on this classification task. This foundationalwork paves the way to verifiable quantum advantages in the field ofcomputational biology and facilitates safer therapeutic development.