Q2SAR: A Quantum Multiple Kernel Learning Approach for Drug Discovery

TL;DR

This paper introduces a Quantum Multiple Kernel Learning framework that enhances QSAR classification in drug discovery, demonstrating improved performance over classical methods using quantum and classical kernel combinations.

Contribution

It presents a novel quantum-enhanced kernel learning approach for QSAR modeling, integrating quantum kernels with classical machine learning to improve classification accuracy.

Findings

QMKL-SVM outperforms classical Gradient Boosting in AUC score

Quantum kernels provide a performance boost in cheminformatics tasks

The approach shows potential for quantum advantage in drug discovery

Abstract

Quantitative Structure-Activity Relationship (QSAR) modeling is a cornerstone of computational drug discovery. This research demonstrates the successful application of a Quantum Multiple Kernel Learning (QMKL) framework to enhance QSAR classification, showing a notable performance improvement over classical methods. We apply this methodology to a dataset for identifying DYRK1A kinase inhibitors. The workflow involves converting SMILES representations into numerical molecular descriptors, reducing dimensionality via Principal Component Analysis (PCA), and employing a Support Vector Machine (SVM) trained on an optimized combination of multiple quantum and classical kernels. By benchmarking the QMKL-SVM against a classical Gradient Boosting model, we show that the quantum-enhanced approach achieves a superior AUC score, highlighting its potential to provide a quantum advantage in challenging cheminformatics classification tasks.