Q2SAR: A Quantum Multiple Kernel Learning Approach for Drug Discovery

2025-06-17

AI Summary

This study addresses the QSAR classification task of identifying DYRK1A kinase inhibitors. Methodologically, it introduces Quantum Multi-Kernel Learning (QMKL) to drug discovery modeling for the first time, employing SMILES-based molecular representations, PCA for dimensionality reduction, and SVM for classification. A hybrid multi-kernel function is constructed and optimized by fusing a quantum kernel—implemented via parameterized quantum circuits—with classical kernels (e.g., RBF). The key contribution is a trainable quantum–classical kernel mixing strategy that enables quantum-enhanced feature mapping. Evaluated on a public DYRK1A dataset, the proposed QMKL model achieves an AUC of 0.923, significantly outperforming classical gradient boosting (AUC = 0.867) and single-kernel SVMs. These results demonstrate the efficacy and practical potential of quantum multi-kernel frameworks for modeling small-sample, high-dimensional chemical spaces in early-stage drug discovery.

Technology Category

Machine Learning: Quantum Machine LearningSearch and Optimization: Mixed Discrete/Continuous SearchData Mining & Knowledge Management: Intelligent Query Processing

Application Category

Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingSemantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMsUser Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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.

Problem

• Enhancing QSAR classification using Quantum Multiple Kernel Learning
• Improving drug discovery for DYRK1A kinase inhibitors identification
• Demonstrating quantum advantage in cheminformatics classification tasks

Innovation

• Quantum Multiple Kernel Learning for QSAR
• SMILES to descriptors with PCA reduction
• Quantum-enhanced SVM outperforms classical models