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

International Conference on Computation System and Information Technology for Sustainable Solutions (CSITSS)

A Critical Benchmark of Hybrid Quantum-Classical Graph Neural Networks for Molecular Property Prediction: Revealing Performance Bottlenecks in Current Architectures

Rakesh Kalshetty, Sreenivasa Manish, Shashank Kotagi, Vishwas Desai

Published Nov 20, 2025• 0 citations
Publisher

Abstract

Hybrid quantum-classical neural networks (HQCNNs) represent a promising but largely unproven paradigm for enhancing molecular property prediction in drug discovery. Despite growing interest and optimistic claims in recent literature, rigorous benchmarks comparing these hybrid architectures against strong classical baselines remain scarce. This work implements and systematically evaluates a representative HQCNN architecture against its classical equivalent using standardized molecular datasets (QM9 and ZINC-250K) within a reproducible, multi-seed experimental framework. Contrary to optimistic expectations, our results reveal that the hybrid model consistently underperforms the classical baseline, showing a 49% increase in MAE on QM9 (1.0834 vs 0.7256) and a devastating 107% degradation on ZINC (1.4006 vs 0.6755), with R2values dropping by over 80% on both datasets. Through detailed analysis, we identify fundamental challenges including information bottlenecks during quantum encoding and difficult optimization landscapes in variational quantum circuits as primary causes of performance degradation. This work provides a crucial, datadriven reality check for the field, demonstrating that current “plug-and-play” quantum layer approaches may be insufficient for practical quantum advantages. All experimental code and data are publicly released to enable community replication and investigation of more sophisticated quantum-native architectures.

DOI
10.1109/csitss67709.2025.11294553

Related papers

Quantum-Embedded Graph Neural Network Architecture for Molecular Property Prediction

Min Lu, Lei Du, Ziwei Cui +8 more

Accurate prediction of molecular properties is crucial for accelerating the development of new drugs, and quantum machine learning (QML) holds great promise in this domain. A typical QML pipeline comprises two core stages: encoding classical data into quantum representations followed by training and prediction using quantum computing-based machine learning (ML) models. In this article, we focus on the initial encoding stage and propose an effective quantum feature extraction approach for molecular graph data, introducing quantum node embedding and quantum edge embedding methods. We developed a hybrid quantum-classical ML framework and implemented several quantum-embedded graph neural network (QEGNN) models to evaluate the proposed method. Experiments conducted on three benchmark data sets with diverse molecular property prediction tasks demonstrate that QEGNN models consistently achieve higher accuracy, improved stability, and significantly reduced parameter complexity─hallmarks of quantum advantage. Furthermore, we validate the reliability of the quantum embedding approach on the superconducting quantum processor "Wukong," showing that the models retain stable performance even under the constraints of current noisy quantum hardware. This work highlights the potential of QML and paves the way for the development of universal QML models.

Journal of Chemical Information and Modeling•Jul 26, 2025•8 citations

Hybrid Quantum-Classical Neural Networks for Healthcare Prediction Powered by Automated Scientific Discovery

Karthik Meduri, Ruthvik Yedla, Santosh Reddy Addula +5 more

This study presents a reproducible evaluation framework for hybrid quantum-classical neural networks (HQCNNs) in healthcare classification, rather than a new architecture. We assess a four-qubit HQCNN combining a compact classical encoder, a two-layer parameterized quantum circuit (PQC), and a classical readout (441 trainable parameters) against carefully tuned classical baselines on the Wisconsin Diagnostic Breast Cancer (WDBC) dataset under identical five-fold cross-validation. The work is framed as a single-dataset proof-of-concept: the contribution is a documented, shared-fold evaluation protocol with a parameter-matched classical control and a quantified epistemic-informativeness analysis, not a demonstration of general quantum advantage. The HQCNN reached 96.49±1.96% accuracy and 99.44±0.60% ROC-AUC. A parameter-matched classical multilayer perceptron (441 parameters) reached 95.08±1.81% accuracy; the HQCNN’s +1.41 percentage-point edge at equal capacity was not statistically significant (paired t, p=0.056). Across five shared folds, no HQCNN-versus-classical accuracy difference survived Holm–Bonferroni correction (all adjusted p≥0.625), so we report the HQCNN as competitive with, not superior to, strong tuned classical baselines. A multi-split depth ablation showed that circuit depth L∈{1,2,3} had no statistically detectable effect on accuracy (L=2 vs. L=3: Wilcoxon p=1.00); we therefore adopt two variational layers as a practical default rather than an optimum. Under a low-noise simulator (depolarising and amplitude-damping channels, p=0.01), accuracy was 96.49%, indicating robustness only at modest uniform error rates; realistic hardware noise is higher. We additionally apply Bayesian surprise as an epistemic-informativeness heuristic—not a formal generative model—to rank which findings are most worth building on. The framework offers a reproducible, documented evaluation procedure that can support cumulative comparison of hybrid quantum-classical models in healthcare.

Informatics•Jun 22, 2026•0 citations

Quantum–classical hybrid learning framework for molecular property prediction and molecule optimization in drug discovery

S. Rama Sree, Medepalli Sandhya, A. Jayanthi +3 more

Finding drug-like molecules is a time- and money-consuming task that requires virtual screening techniques capable of accurately representing non-linear intermolecular relationships. Classical ML models usually consider molecular graphs or SMILES sequences, but cannot jointly exploit both structural and sequential information, let alone simultaneously. Of greater importance, numerous deep learning methods are hindered by poor generalisation, black-box predictions, and inadequate interpretability, reducing their feasibility for application in real-life drug discovery pipelines. In this paper, we present QDrugDiscoverAI, a hybrid quantum–classical deep learning framework for predicting molecular properties and optimising molecules to overcome these challenges. We present a framework for multimodal molecular representation learning that combines graph attention networks and transformer-based sequence encoders with variational quantum circuits to increase expressive capacity within a single architecture. It implements a dual-stream representation-learning mechanism with a multimodal feature fusion layer. It includes an explainability module that uses attention weights and SHAP values to identify substructures that contribute to model predictions and enhance interpretability. Moreover, QDrugDiscoverAI also includes a quantum–assisted reinforcement-learning module for a molecule-optimisation workflow, enabling more efficient exploration of the chemical design space while leveraging the controllability of quantum simulation. The experiments on three benchmark datasets, i.e., Lipophilicity, HIV, and BBBP, show improvements of 12.4%, 9.6%, and 11.1% in accuracy, AUC, and F1-score, respectively, over the matched classical and unimodal baselines. Quantitative evaluation of quantum components and fusion strategies is also conducted through ablation studies to demonstrate their roles further. In summary, the framework proposed serves as a systematic integration of interpretable hybrid learning, showing one way it could be organised to become increasingly efficient, and demonstrating the advantage of using quantum-simulated components to enhance classical deep learning models for exploration and predictive performance in drug discovery workflows. The implementation code and supporting scripts for the proposed QDrugDiscoverAI framework are publicly available at: https://github.com/Sripada-RamaSree/QuantumDrugAI

Discover Computing•Jun 21, 2026•0 citations

Hybrid Quantum-Classical Neural Networks for Molecular Property Prediction from SMILES

Sergey M. Gushanskiy, Viktor Potapov, Maxim Polenov

The prediction of molecular properties from SMILES strings is a cornerstone of modern drug discovery and materials science, yet traditional computational methods often face a trade-off between accuracy and speed. This paper presents a comprehensive hybrid quantum-classical architecture that synergistically combines a Bidirectional Long Short-Term Memory (BiLSTM) network with a variational quantum circuit (VQC) to perform multi-task regression on molecular properties. Our system introduces a novel quantum feature layer, implemented in PennyLane and integrated with PyTorch, which employs data reuploading and configurable entanglement patterns (linear, full, pairwise) to generate expressive quantum descriptors. These descriptors are concatenated with classical features and fed into a regression head, enabling the simultaneous prediction of eight key molecular properties. We validate our approach through rigorous experimentation on benchmark datasets (ESOL, FreeSolv, QM9) and demonstrate that the hybrid model consistently outperforms a strong classical BiLSTM baseline, achieving an $\mathbf{R}^{2}$ of up to 0.94 on QM9 and reducing inference time to seconds per molecule. Furthermore, we detail a complete production-ready pipeline, including SMILES tokenization, exploratory data analysis (EDA), handling of invalid inputs, and multiple deployment scenarios such as REST API integration for LIMS/ERP systems, active learning loops, and large-scale batch processing on cloud infrastructure. This work establishes a scalable and robust framework for integrating quantum computing into real-world cheminformatics workflows, offering a significant step toward quantumaccelerated drug design.

International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM)•May 18, 2026•0 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

HQCNN: A Hybrid Quantum-Classical Neural Network for Medical Image Classification

Shahjalal, Jahid Karim Fahim, Pintu Chandra Paul +3 more

Classification of medical images plays a vital role in medical image analysis; however, it remains challenging due to the limited availability of labeled data, class imbalances, and the complexity of medical patterns. To overcome these challenges, we propose a novel Hybrid Quantum-Classical Neural Network (HQCNN) for both binary and multi-class classification. The architecture of HQCNN integrates a five-layer classical convolutional backbone with a 4-qubit variational quantum circuit that incorporates quantum state encoding, superpositional entanglement, and a Fourier-inspired quantum attention mechanism. We evaluate the model on six MedMNIST v2 benchmark datasets. The HQCNN consistently outperforms classical and quantum baselines, achieving up to 99.91% accuracy and 100.00% AUC on PathMNIST (binary) and 99.95% accuracy on OrganAMNIST (multi-class) with strong robustness on noisy datasets like BreastMNIST (87.18% accuracy). The model demonstrates superior generalization capability and computational efficiency, accomplished with significantly fewer trainable parameters, making it suitable for data-scarce scenarios. Our findings provide strong empirical evidence that hybrid quantum-classical models can advance medical imaging tasks.

arXiv:2509.14277•Sep 16, 2025•5 citations
Hybrid quantum-classical neural networks (HQCNNs) represent a promising but largely unproven paradigm for enhancing molecular property prediction in drug discovery. Despite growing interest and optimistic claims in recent literature, rigorous benchmarks comparing these hybrid architectures against strong classical baselines remain scarce. This work implements and systematically evaluates a representative HQCNN architecture against its classical equivalent using standardized molecular datasets (QM9 and ZINC-250K) within a reproducible, multi-seed experimental framework. Contrary to optimistic expectations, our results reveal that the hybrid model consistently underperforms the classical baseline, showing a 49% increase in MAE on QM9 (1.0834 vs 0.7256) and a devastating 107% degradation on ZINC (1.4006 vs 0.6755), with R2values dropping by over 80% on both datasets. Through detailed analysis, we identify fundamental challenges including information bottlenecks during quantum encoding and difficult optimization landscapes in variational quantum circuits as primary causes of performance degradation. This work provides a crucial, datadriven reality check for the field, demonstrating that current “plug-and-play” quantum layer approaches may be insufficient for practical quantum advantages. All experimental code and data are publicly released to enable community replication and investigation of more sophisticated quantum-native architectures.
Accurate prediction of molecular properties is crucial for accelerating the development of new drugs, and quantum machine learning (QML) holds great promise in this domain. A typical QML pipeline comprises two core stages: encoding classical data into quantum representations followed by training and prediction using quantum computing-based machine learning (ML) models. In this article, we focus on the initial encoding stage and propose an effective quantum feature extraction approach for molecular graph data, introducing quantum node embedding and quantum edge embedding methods. We developed a hybrid quantum-classical ML framework and implemented several quantum-embedded graph neural network (QEGNN) models to evaluate the proposed method. Experiments conducted on three benchmark data sets with diverse molecular property prediction tasks demonstrate that QEGNN models consistently achieve higher accuracy, improved stability, and significantly reduced parameter complexity─hallmarks of quantum advantage. Furthermore, we validate the reliability of the quantum embedding approach on the superconducting quantum processor "Wukong," showing that the models retain stable performance even under the constraints of current noisy quantum hardware. This work highlights the potential of QML and paves the way for the development of universal QML models.
This study presents a reproducible evaluation framework for hybrid quantum-classical neural networks (HQCNNs) in healthcare classification, rather than a new architecture. We assess a four-qubit HQCNN combining a compact classical encoder, a two-layer parameterized quantum circuit (PQC), and a classical readout (441 trainable parameters) against carefully tuned classical baselines on the Wisconsin Diagnostic Breast Cancer (WDBC) dataset under identical five-fold cross-validation. The work is framed as a single-dataset proof-of-concept: the contribution is a documented, shared-fold evaluation protocol with a parameter-matched classical control and a quantified epistemic-informativeness analysis, not a demonstration of general quantum advantage. The HQCNN reached 96.49±1.96% accuracy and 99.44±0.60% ROC-AUC. A parameter-matched classical multilayer perceptron (441 parameters) reached 95.08±1.81% accuracy; the HQCNN’s +1.41 percentage-point edge at equal capacity was not statistically significant (paired t, p=0.056). Across five shared folds, no HQCNN-versus-classical accuracy difference survived Holm–Bonferroni correction (all adjusted p≥0.625), so we report the HQCNN as competitive with, not superior to, strong tuned classical baselines. A multi-split depth ablation showed that circuit depth L∈{1,2,3} had no statistically detectable effect on accuracy (L=2 vs. L=3: Wilcoxon p=1.00); we therefore adopt two variational layers as a practical default rather than an optimum. Under a low-noise simulator (depolarising and amplitude-damping channels, p=0.01), accuracy was 96.49%, indicating robustness only at modest uniform error rates; realistic hardware noise is higher. We additionally apply Bayesian surprise as an epistemic-informativeness heuristic—not a formal generative model—to rank which findings are most worth building on. The framework offers a reproducible, documented evaluation procedure that can support cumulative comparison of hybrid quantum-classical models in healthcare.
Finding drug-like molecules is a time- and money-consuming task that requires virtual screening techniques capable of accurately representing non-linear intermolecular relationships. Classical ML models usually consider molecular graphs or SMILES sequences, but cannot jointly exploit both structural and sequential information, let alone simultaneously. Of greater importance, numerous deep learning methods are hindered by poor generalisation, black-box predictions, and inadequate interpretability, reducing their feasibility for application in real-life drug discovery pipelines. In this paper, we present QDrugDiscoverAI, a hybrid quantum–classical deep learning framework for predicting molecular properties and optimising molecules to overcome these challenges. We present a framework for multimodal molecular representation learning that combines graph attention networks and transformer-based sequence encoders with variational quantum circuits to increase expressive capacity within a single architecture. It implements a dual-stream representation-learning mechanism with a multimodal feature fusion layer. It includes an explainability module that uses attention weights and SHAP values to identify substructures that contribute to model predictions and enhance interpretability. Moreover, QDrugDiscoverAI also includes a quantum–assisted reinforcement-learning module for a molecule-optimisation workflow, enabling more efficient exploration of the chemical design space while leveraging the controllability of quantum simulation. The experiments on three benchmark datasets, i.e., Lipophilicity, HIV, and BBBP, show improvements of 12.4%, 9.6%, and 11.1% in accuracy, AUC, and F1-score, respectively, over the matched classical and unimodal baselines. Quantitative evaluation of quantum components and fusion strategies is also conducted through ablation studies to demonstrate their roles further. In summary, the framework proposed serves as a systematic integration of interpretable hybrid learning, showing one way it could be organised to become increasingly efficient, and demonstrating the advantage of using quantum-simulated components to enhance classical deep learning models for exploration and predictive performance in drug discovery workflows. The implementation code and supporting scripts for the proposed QDrugDiscoverAI framework are publicly available at: https://github.com/Sripada-RamaSree/QuantumDrugAI
The prediction of molecular properties from SMILES strings is a cornerstone of modern drug discovery and materials science, yet traditional computational methods often face a trade-off between accuracy and speed. This paper presents a comprehensive hybrid quantum-classical architecture that synergistically combines a Bidirectional Long Short-Term Memory (BiLSTM) network with a variational quantum circuit (VQC) to perform multi-task regression on molecular properties. Our system introduces a novel quantum feature layer, implemented in PennyLane and integrated with PyTorch, which employs data reuploading and configurable entanglement patterns (linear, full, pairwise) to generate expressive quantum descriptors. These descriptors are concatenated with classical features and fed into a regression head, enabling the simultaneous prediction of eight key molecular properties. We validate our approach through rigorous experimentation on benchmark datasets (ESOL, FreeSolv, QM9) and demonstrate that the hybrid model consistently outperforms a strong classical BiLSTM baseline, achieving an R2\mathbf{R}^{2}R2 of up to 0.94 on QM9 and reducing inference time to seconds per molecule. Furthermore, we detail a complete production-ready pipeline, including SMILES tokenization, exploratory data analysis (EDA), handling of invalid inputs, and multiple deployment scenarios such as REST API integration for LIMS/ERP systems, active learning loops, and large-scale batch processing on cloud infrastructure. This work establishes a scalable and robust framework for integrating quantum computing into real-world cheminformatics workflows, offering a significant step toward quantumaccelerated drug design.
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.
Classification of medical images plays a vital role in medical image analysis; however, it remains challenging due to the limited availability of labeled data, class imbalances, and the complexity of medical patterns. To overcome these challenges, we propose a novel Hybrid Quantum-Classical Neural Network (HQCNN) for both binary and multi-class classification. The architecture of HQCNN integrates a five-layer classical convolutional backbone with a 4-qubit variational quantum circuit that incorporates quantum state encoding, superpositional entanglement, and a Fourier-inspired quantum attention mechanism. We evaluate the model on six MedMNIST v2 benchmark datasets. The HQCNN consistently outperforms classical and quantum baselines, achieving up to 99.91% accuracy and 100.00% AUC on PathMNIST (binary) and 99.95% accuracy on OrganAMNIST (multi-class) with strong robustness on noisy datasets like BreastMNIST (87.18% accuracy). The model demonstrates superior generalization capability and computational efficiency, accomplished with significantly fewer trainable parameters, making it suitable for data-scarce scenarios. Our findings provide strong empirical evidence that hybrid quantum-classical models can advance medical imaging tasks.