Accurate amine property prediction is essential for optimizing CO2 capture efficiency in post-combustion processes. Quantum machine learning (QML) can enhance predictive modeling by leveraging superposition, entanglement, and interference to capture complex correlations. In this study, we developed hybrid quantum neural networks (HQNN) to improve quantitative structure-property relationship (QSPR) modeling for CO2-capturing amines. By integrating variational quantum regressors with classical multi-layer perceptrons and graph neural networks, quantum-enhanced performance was explored in physicochemical property prediction under noiseless conditions and robustness was evaluated against quantum hardware noise using IBM quantum systems. Our results showed that HQNNs improve predictive accuracy for key solvent properties, including basicity, viscosity, boiling point, melting point, and vapor pressure. The fine-tuned and frozen pre-trained HQNN models with 9 qubits consistently achieved the highest rankings, highlighting the benefits of integrating quantum layers with pre-trained classical models. Furthermore, simulations under hardware noise confirmed the robustness of HQNNs, maintaining predictive performance. Overall, these findings emphasize the potential of hybrid quantum-classical architectures in molecular modeling. As quantum hardware and QML algorithms continue to advance, practical quantum benefits in QSPR modeling and materials discovery are expected to become increasingly attainable, driven by improvements in quantum circuit design, noise mitigation, and scalable architectures.
Accurate amine property prediction is essential for optimizing CO2 capture efficiency in post-combustion processes. Quantum machine learning (QML) can enhance predictive modeling by leveraging superposition, entanglement, and interference to capture complex correlations. In this study, we developed hybrid quantum neural networks (HQNN) to improve quantitative structure-property relationship (QSPR) modeling for CO2-capturing amines. By integrating variational quantum regressors with classical multi-layer perceptrons and graph neural networks, quantum-enhanced performance was explored in physicochemical property prediction under noiseless conditions and robustness was evaluated against quantum hardware noise using IBM quantum systems. Our results showed that HQNNs improve predictive accuracy for key solvent properties, including basicity, viscosity, boiling point, melting point, and vapor pressure. The fine-tuned and frozen pre-trained HQNN models with 9 qubits consistently achieved the highest rankings, highlighting the benefits of integrating quantum layers with pre-trained classical models. Furthermore, simulations under hardware noise confirmed the robustness of HQNNs, maintaining predictive performance. Overall, these findings emphasize the potential of hybrid quantum-classical architectures in molecular modeling. As quantum hardware and QML algorithms continue to advance, practical quantum benefits in QSPR modeling and materials discovery are expected to become increasingly attainable, driven by improvements in quantum circuit design, noise mitigation, and scalable architectures.
Corrosion inhibition efficiency (IE%) prediction plays a central role in the computational discovery of high-performance organic inhibitors. Classical machine learning has shown promising results; however, its performance often deteriorates when learning non-linear interactions between quantum chemical descriptors. Meanwhile, quantum machine learning (QML) provides enhanced expressivity through quantum feature mapping but remains limited by NISQ-era hardware. In this study, we propose a Hybrid Quantum Neural Network (HQNN) integrating classical dense layers with variational quantum circuits (VQC) to predict the inhibition efficiency of organic corrosion inhibitors. Using a curated dataset of 660 molecules with DFT descriptors, the HQNN achieves an RMSE of 3.41 and R² of 0.958, outperforming classical regressors and pure VQC. The results demonstrate that hybrid quantum models offer a balanced trade-off between quantum advantage and practical feasibility in materials informatics.
Accurate prediction of molecular structures and properties is vital for chemistry; materials science, and drug discovery, yet classical electronic-structure methods often fail for strongly correlated systems, large basis sets, and complex potential-energy landscapes. Quantum technology encompassing quantum computing, quantum machine learning, and hybrid quantum classical strategies offers a fundamentally new paradigm by encoding many-electron wave functions directly on qubits and exploiting superposition and entanglement to explore exponentially large Hilbert spaces. This review synthesizes recent algorithmic and hardware advances relevant to molecular modelling, including the Variational Quantum Eigensolver (VQE), Quantum Phase Estimation (QPE), quantum unitary coupled-cluster (q-UCC) families, equation-of-motion and subspace methods for excited states, tensor-network hybrids, and quantum kernel and variational QML approaches. We examine noise-aware hybrid workflows, error-mitigation techniques, symmetry-preserving ansätze, and operator-factorization methods that reduce measurement and gate overhead. Representative applications are discussed: ground- and excited-state energy prediction, potential-energy surface mapping, geometry and transition-state optimization, spectroscopic property estimation (IR, UV–Vis, NMR, EPR), and reaction-dynamics scenarios where non-adiabatic effects and conical intersections dominate. Resource estimates and scaling analyses clarify current NISQ limitations qubit counts, circuit depth, shot complexity and delineate the roadmap to fault-tolerant QPE for chemical accuracy. We compare quantum approaches with classical baselines (DFT, CCSD (T), multireference methods), identifying domains where quantum methods already show promise (strong correlation, multi-reference dissociation, spin-state ordering) and where classical methods remain competitive. Finally, we highlight near-term industrial opportunities in drug design, catalysis, CO2 capture, and energy materials, and outline critical research directions: algorithmic reductions in measurement/precision cost, hardware improvements in fidelity and connectivity, scalable ansatz design, and integrated software stacks for reproducible hybrid simulations. Together, these developments indicate that while practical, large-scale quantum advantage for general chemistry remains future work, quantum technologies are rapidly maturing into powerful tools for targeted molecular problems that are intractable with existing classical techniques.
Protein-ligand binding affinity is critical in drug discovery, but experimentally determining it is time-consuming and expensive. Artificial intelligence (AI) has been used to predict binding affinity, significantly accelerating this process. However, the high-performance requirements and vast datasets involved in affinity prediction demand increasingly large AI models, requiring substantial computational resources and training time. Quantum machine learning has emerged as a promising solution to these challenges. In particular, hybrid quantum-classical models can reduce the number of parameters while maintaining or improving performance compared to classical counterparts. Despite these advantages, challenges persist: why hybrid quantum models achieve these benefits, whether quantum neural networks (QNNs) can replace classical neural networks, and whether such models are feasible on noisy intermediate-scale quantum (NISQ) devices. This study addresses these challenges by proposing a hybrid quantum neural network (HQNN) that empirically demonstrates the capability to approximate non-linear functions in the latent feature space derived from classical embedding. The primary goal of this study is to achieve a parameter-efficient model in binding affinity prediction while ensuring feasibility on NISQ devices. Numerical results indicate that HQNN achieves comparable or superior performance and parameter efficiency compared to classical neural networks, underscoring its potential as a viable replacement. This study highlights the potential of hybrid QML in computational drug discovery, offering insights into its applicability and advantages in addressing the computational challenges of protein-ligand binding affinity prediction.
This paper proposes and evaluate Hybrid Quantum Convolutional Neural Networks (HQCNNs) that integrate Structured Variational Quantum Circuits (SVQCs) into classical convolutional networks for image classification. Prior quanvolutional architectures often rely on unstructured variational circuits, leading to barren-plateau training landscapes, unpredictable convergence, and poor scaling of expressivity as qubit count grows. Moreover, simplistic data-encoding schemes can either fail to capture spatial correlations or demand impractically deep circuits, while arbitrary entanglement patterns obscure the relationship between circuit design and learning capacity. To address these challenges, we design four HQCNN architectures with progressively increased quantum encoding precision, entanglement topology, and classical post-processing depth. Each HQCNN replaces the convolutional layer with a quanvolutional layer: local image patches are encoded into small qubit registers via an Enhanced Novel Enhanced Quantum Representation (ENEQR), then processed by the SVQCs, and then measured to produce quantum feature maps. The four versions vary in quantum structure: Version 1 uses a simple linear 5-qubit chain (q=2), Version 2 adds wrap-around entanglement (closed-loop topology), Version 3 augments the classical head with a deeper batch-normalized multilayer perceptron, and Version 4 increases encoding fidelity to q=4 (7 qubits per patch). All models end-to-end using the Adam optimizer and cross-entropy loss on the MNIST dataset for 10 epochs using a PennyLane simulator. Version 4 achieves the best test accuracy (96% on MNIST). Fourier spectrum analysis reveals that richer entanglement and higher-fidelity encoding broaden the circuits’ harmonic spectrum, correlating with enhanced representational capacity and improved classification performance. These results confirm that carefully structured quantum layers and enhanced encoding can enrich feature representations and boost accuracy, albeit with increased simulation overhead and training complexity.
To accelerate the process of materials design, materials science has increasingly used data driven techniques to extract information from collected data. Specially, machine learning (ML) algorithms, which span the ML discipline, have demonstrated ability to predict various properties of materials with the level of accuracy similar to explicit calculation of quantum mechanical theories, but with significantly reduced run time and computational resources. Within ML, graph neural networks have emerged as an important algorithm within the field of machine learning, since they are capable of predicting accurately a wide range of important physical, chemical and electronic properties due to their higher learning ability based on the graph representation of material and molecular descriptors through the aggregation of information embedded within the graph. In parallel with the development of state of the art classical machine learning applications, the fusion of quantum computing and machine learning have created a new paradigm where classical machine learning model can be augmented with quantum layers which are able to encode high dimensional data more efficiently. Leveraging the structure of existing algorithms, we developed a unique and novel gradient free hybrid quantum classical convoluted graph neural network (HyQCGNN) to predict formation energies of perovskite materials. The performance of our hybrid statistical model is competitive with the results obtained purely from a classical convoluted graph neural network, and other classical machine learning algorithms, such as XGBoost. Consequently, our study suggests a new pathway to explore how quantum feature encoding and parametric quantum circuits can yield drastic improvements of complex ML algorithm like graph neural network.
The study explores the integration of quantum-enhanced feature mapping and optimization within Graph Neural Networks (GNNs) for molecular classification tasks. Utilizing IBM's Qiskit platform, we implement Variational Quantum Circuits (VQCs) to transform classical molecular features into quantum states, capturing complex correlations through quantum entanglement. Additionally, the Quantum Approximate Optimization Algorithm (QAOA) is employed for hyperparameter tuning to enhance model convergence and performance. Comparative analyses against traditional machine learning models demonstrate the superiority of the quantum-enhanced GNN, highlighting the potential of quantum computing in advancing molecular property prediction.