Non-hemolytic Peptide Classification using a Quantum Support Vector Machine

Shengxin Zhuang, John Tanner, Yusen Wu, Du Q. Huynh, Wei Liu, Xavier Cadet, Nicolas Tristan Fontaine, Philippe Charton, Cédric Damour, Frederic CADET, Jingbo Wang

Abstract: Quantum machine learning (QML) is one of the most promising applications of quantum computation. Despite the theoretical advantages, it is still unclear exactly what kind of problems QML techniques can be used for, given the current limitation of noisy intermediate-scale quantum devices. In this work, we apply the well-studied quantum support vector machine (QSVM), a powerful QML model, to a binary classification task which classifies peptides as either hemolytic or non-hemolytic. Using three peptide datasets, we apply and contrast the performance of the QSVM with a number of popular classical SVMs, out of which the QSVM performs best overall. The contributions of this work include: (i) the first application of the QSVM to this specific peptide classification task and (ii) empirical results showing that the QSVM is capable of outperforming many (and possibly all) classical SVMs on this classification task. This foundational work provides insight into possible applications of QML in computational biology and may facilitate safer therapeutic developments by improving our ability to identify hemolytic properties in peptides.