Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2607.11701 · JAIIO, Jornadas Argentinas de Informática

$\mathtt{Q^2SAR}$: overcoming classical bottlenecks in drug discovery via quantum multiple kernel learning

Mariano Caruso, Daniel Ruiz, Alejandro Giraldo, Guido Bellomo

quant-phcs.LGSubmitted Jul 13, 2026• Announced Jul 14, 2026• 0 citations
arXivHTMLPDF

Abstract

Quantitative Structure-Activity Relationship ($\mathtt{QSAR}$) modeling is a foundational computational methodology in early-stage drug discovery, heavily relied upon for predicting compound toxicity, bioavailability, and therapeutic potential. However, classical methods often struggle to effectively map the highly complex, non-linear, and high-dimensional interactions inherent in molecular data, leading to reduced predictive accuracy and costly late-stage clinical failures. In this paper, we present a Quantum Multiple Kernel Learning ($\mathtt{QMKL}$) framework, dubbed Next-Gen $\mathtt{Q^2SAR}$, that leverages Quantum Support Vector Machines ($\mathtt{QSVMs}$) to overcome these classical limitations. By encoding molecular descriptors into exponentially large quantum Hilbert spaces, our approach substantially enhances the expressiveness of non-linear modeling. Benchmarking our quantum-enhanced framework on a dataset targeting the $\mathtt{DYRK1A}$ kinase (a critical target for Alzheimer's disease), the $\mathtt{QMKL}$-$\mathtt{SVM}$ achieves an impressive Area Under the Curve ($\mathtt{AUC}$) score of $0.8750$, significantly outperforming classical state-of-the-art Gradient Boosting models ($\mathtt{AUC} = 0.8037$). Furthermore, we establish a theoretical and empirical pathway toward resolving classical data bottlenecks through projected quantum kernels ($\mathtt{PQK}$) and measurement accelerators. As quantum computing architecture matures, this framework paves the way for autonomous cognitive architectures and self-improving drug discovery pipelines, promising to unlock deeper insights across vast chemical spaces and to accelerate the development of life-saving therapeutics.

Related papers

Q2SAR: A Quantum Multiple Kernel Learning Approach for Drug Discovery

Alejandro Giraldo, Ruiz, Daniel, M. Caruso +2 more

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.

arXiv:2506.14920•Jun 17, 2025•0 citations

Q 2 SAR: A Quantum Multiple Kernel Learning Approach for Drug Discovery

Alejandro Giraldo, Daniel Ruiz, M. Caruso +2 more

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 quantumenhanced approach achieves a superior AUC score, highlighting its potential to provide a quantum advantage in challenging cheminformatics classification tasks.

IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies (CHILECON)•Oct 28, 2025•0 citations

Quantum QSAR for drug discovery

M. Caruso, Alejandro Giraldo, Daniel Ruiz +1 more

Quantitative Structure-Activity Relationship (\texttt{QSAR}) modeling is key in drug discovery, but classical methods face limitations when handling high-dimensional data and capturing complex molecular interactions. This research proposes enhancing \texttt{QSAR} techniques through Quantum Support Vector Machines (\texttt{QSVMs}), which leverage quantum computing principles to process information Hilbert spaces. By using quantum data encoding and quantum kernel functions, we aim to develop more accurate and efficient predictive models.

•Apr 24, 2025•0 citations

Quantum QSAR for drug discovery

Alejandro Giraldo, Daniel Ruiz, M. Caruso +1 more

Quantitative Structure-Activity Relationship (QSAR) modeling is key in drug discovery, but classical methods face limitations when handling high-dimensional data and capturing complex molecular interactions. This research proposes enhancing QSAR techniques through Quantum Support Vector Machines (QSVMs), which leverage quantum computing principles to process information Hilbert spaces. By using quantum data encoding and quantum kernel functions, we aim to develop more accurate and efficient predictive models.

arXiv:2505.04648•JAIIO, Jornadas Argentinas de Informática•Apr 28, 2025•2 citations

A Hybrid Quantum-Classical Machine Learning Framework for Accelerated Drug Discovery

Sriramadasu Sri Sainadh, Saigeetha S.B., Jeeru Bharath Reddy +4 more

The pharmaceutical industry faces mounting challenges in drug discovery, where exploring a chemical space exceeding 10 60 possible compounds remains computationally prohibitive. Traditional in-silico screening approaches struggle to capture the quantum mechanical interactions that determine molecular behavior. To overcome these limitations, this study introduces a hybrid quantum–classical machine learning framework that uniquely integrates molecular graph theory with quantum-enhanced learning for accelerated drug discovery. Using the QM9 benchmark dataset containing 133,885 molecules of low-to-medium structural complexity, we extract Laplacian eigenvalue spectra as topological descriptors that preserve both connectivity and electronic information. These features are jointly processed by Random Forest (RF), Support Vector Machine (SVM), and a Variational Quantum Classifier (VQC) in a weighted ensemble architecture designed for balanced generalization. The Quantum Graph Neural Network (QGNN) component achieves 97.5% accuracy, while the hybrid ensemble attains 100.0% accuracy, confirming strong predictive reliability. Although quantum training requires roughly 3.2× longer computation, it captures high-dimensional correlations that classical methods overlook. Overall, the proposed framework bridges the gap between theoretical quantum computing and practical pharmaceutical modeling, providing a scalable, physics-inspired pathway toward intelligent molecular screening and next-generation drug discovery systems.

Procedia Computer Science•Jan 1, 2026•0 citations

Quantum Machine Learning for Drug Discovery: From Molecular Descriptors to Explainable Quantum Pharmacology

Volkan Erol

Recent advances in quantum machine learning (QML) have opened new pathways for accelerating early-stage drug discovery through molecular representation in Hilbert space [1]–[3]. In this work, we present a hybrid quantum–classical framework that integrates quantum kernel estimation and variational quantum neural networks (QNNs) for ligand–target binding prediction [4], [5].A synthetic dataset reflecting the statistical behavior of the BindingDB database [6] was constructed to evaluate quantum descriptors and kernel performance under controlled conditions. The proposed quantum feature maps translate seven key molecular descriptors—molecular weight (MW), logP, hydrogen bond donors (HBD), acceptors (HBA), rotatable bonds (RB), aromatic rings (AR), and topological polar surface area (TPSA)—into entangled qubit states [7], [8].Comparative analyses with classical baselines (SVR, Random Forest, and deep neural networks) revealed that quantum embeddings achieve competitive predictive accuracy (RMSE ≈ 0.06) with improved stability under bootstrap resampling [9]. Quantum kernel alignment and sensitivity studies demonstrated that aromaticity and polarity jointly determine the representational power of QML models [10].Beyond performance, we emphasize Explainable Quantum Pharmacology (EQP)—a paradigm in which interpretability, reproducibility, and physicochemical causality are as essential as accuracy [11].Our findings establish a reproducible, interpretable, and computationally efficient foundation for hybrid QML pipelines in molecular modeling, paving the way for next-generation AI-driven drug discovery.

•Oct 10, 2025•0 citations
Q2SAR\mathtt{Q^2SAR}Q2SAR: overcoming classical bottlenecks in drug discovery via quantum multiple kernel learning
Quantitative Structure-Activity Relationship (QSAR\mathtt{QSAR}QSAR) modeling is a foundational computational methodology in early-stage drug discovery, heavily relied upon for predicting compound toxicity, bioavailability, and therapeutic potential. However, classical methods often struggle to effectively map the highly complex, non-linear, and high-dimensional interactions inherent in molecular data, leading to reduced predictive accuracy and costly late-stage clinical failures. In this paper, we present a Quantum Multiple Kernel Learning (QMKL\mathtt{QMKL}QMKL) framework, dubbed Next-Gen Q2SAR\mathtt{Q^2SAR}Q2SAR, that leverages Quantum Support Vector Machines (QSVMs\mathtt{QSVMs}QSVMs) to overcome these classical limitations. By encoding molecular descriptors into exponentially large quantum Hilbert spaces, our approach substantially enhances the expressiveness of non-linear modeling. Benchmarking our quantum-enhanced framework on a dataset targeting the DYRK1A\mathtt{DYRK1A}DYRK1A kinase (a critical target for Alzheimer's disease), the QMKL\mathtt{QMKL}QMKL-SVM\mathtt{SVM}SVM achieves an impressive Area Under the Curve (AUC\mathtt{AUC}AUC) score of 0.87500.87500.8750, significantly outperforming classical state-of-the-art Gradient Boosting models (AUC=0.8037\mathtt{AUC} = 0.8037AUC=0.8037). Furthermore, we establish a theoretical and empirical pathway toward resolving classical data bottlenecks through projected quantum kernels (PQK\mathtt{PQK}PQK) and measurement accelerators. As quantum computing architecture matures, this framework paves the way for autonomous cognitive architectures and self-improving drug discovery pipelines, promising to unlock deeper insights across vast chemical spaces and to accelerate the development of life-saving therapeutics.
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.
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 quantumenhanced approach achieves a superior AUC score, highlighting its potential to provide a quantum advantage in challenging cheminformatics classification tasks.
Quantitative Structure-Activity Relationship (\texttt{QSAR}) modeling is key in drug discovery, but classical methods face limitations when handling high-dimensional data and capturing complex molecular interactions. This research proposes enhancing \texttt{QSAR} techniques through Quantum Support Vector Machines (\texttt{QSVMs}), which leverage quantum computing principles to process information Hilbert spaces. By using quantum data encoding and quantum kernel functions, we aim to develop more accurate and efficient predictive models.
Quantitative Structure-Activity Relationship (QSAR) modeling is key in drug discovery, but classical methods face limitations when handling high-dimensional data and capturing complex molecular interactions. This research proposes enhancing QSAR techniques through Quantum Support Vector Machines (QSVMs), which leverage quantum computing principles to process information Hilbert spaces. By using quantum data encoding and quantum kernel functions, we aim to develop more accurate and efficient predictive models.
The pharmaceutical industry faces mounting challenges in drug discovery, where exploring a chemical space exceeding 10 60 possible compounds remains computationally prohibitive. Traditional in-silico screening approaches struggle to capture the quantum mechanical interactions that determine molecular behavior. To overcome these limitations, this study introduces a hybrid quantum–classical machine learning framework that uniquely integrates molecular graph theory with quantum-enhanced learning for accelerated drug discovery. Using the QM9 benchmark dataset containing 133,885 molecules of low-to-medium structural complexity, we extract Laplacian eigenvalue spectra as topological descriptors that preserve both connectivity and electronic information. These features are jointly processed by Random Forest (RF), Support Vector Machine (SVM), and a Variational Quantum Classifier (VQC) in a weighted ensemble architecture designed for balanced generalization. The Quantum Graph Neural Network (QGNN) component achieves 97.5% accuracy, while the hybrid ensemble attains 100.0% accuracy, confirming strong predictive reliability. Although quantum training requires roughly 3.2× longer computation, it captures high-dimensional correlations that classical methods overlook. Overall, the proposed framework bridges the gap between theoretical quantum computing and practical pharmaceutical modeling, providing a scalable, physics-inspired pathway toward intelligent molecular screening and next-generation drug discovery systems.
Recent advances in quantum machine learning (QML) have opened new pathways for accelerating early-stage drug discovery through molecular representation in Hilbert space [1]–[3]. In this work, we present a hybrid quantum–classical framework that integrates quantum kernel estimation and variational quantum neural networks (QNNs) for ligand–target binding prediction [4], [5].A synthetic dataset reflecting the statistical behavior of the BindingDB database [6] was constructed to evaluate quantum descriptors and kernel performance under controlled conditions. The proposed quantum feature maps translate seven key molecular descriptors—molecular weight (MW), logP, hydrogen bond donors (HBD), acceptors (HBA), rotatable bonds (RB), aromatic rings (AR), and topological polar surface area (TPSA)—into entangled qubit states [7], [8].Comparative analyses with classical baselines (SVR, Random Forest, and deep neural networks) revealed that quantum embeddings achieve competitive predictive accuracy (RMSE ≈ 0.06) with improved stability under bootstrap resampling [9]. Quantum kernel alignment and sensitivity studies demonstrated that aromaticity and polarity jointly determine the representational power of QML models [10].Beyond performance, we emphasize Explainable Quantum Pharmacology (EQP)—a paradigm in which interpretability, reproducibility, and physicochemical causality are as essential as accuracy [11].Our findings establish a reproducible, interpretable, and computationally efficient foundation for hybrid QML pipelines in molecular modeling, paving the way for next-generation AI-driven drug discovery.