arXiv:2309.03919 · IEEE International Conference on Quantum Computing and Engineering (QCE)
A Hybrid Quantum-classical Fusion Neural Network to Improve Protein-ligand Binding Affinity Predictions for Drug Discovery
Laia Domingo, Mahdi M. Chehimi, S. Banerjee, S. He Yuxun, Subrahmanyam Konakanchi, Lawal Adewale Ogunfowora, Sumantra Dutta Roy, S. Selvarajan, M. Djukic, C. Johnson
Drug discovery hinges on the accurate prediction of binding affinity between prospective drug molecules and target proteins that influence disease progression, which is financially and computationally demanding. Although classical and hybrid quantum machine learning models have been employed in previous studies to aid in binding affinity prediction, they encounter several issues related to convergence stability and prediction accuracy. In this regard, this paper introduces a novel hybrid quantum-classical deep learning model tailored for binding affinity prediction in drug discovery. Specifically, the proposed model synergistically integrates 3D and spatial graph convolutional neural networks within an optimized quantum circuit architecture. Simulation results demonstrate a 6% improvement in prediction accuracy relative to existing classical models, as well as a significantly more stable convergence performance compared to previous classical approaches. Moreover, to scalably deploy the proposed framework over today's noisy intermediate-scale quantum (NISQ) devices, a novel quantum error mitigation algorithm is proposed. This algorithm outperforms existing techniques and is capable of mitigating errors with gate noise probabilities,$p \leq 0.05$, while resulting in no additional overhead during the training and testing phases.
Drug discovery hinges on the accurate prediction of binding affinity between prospective drug molecules and target proteins that influence disease progression, which is financially and computationally demanding. Although classical and hybrid quantum machine learning models have been employed in previous studies to aid in binding affinity prediction, they encounter several issues related to convergence stability and prediction accuracy. In this regard, this paper introduces a novel hybrid quantum-classical deep learning model tailored for binding affinity prediction in drug discovery. Specifically, the proposed model synergistically integrates 3D and spatial graph convolutional neural networks within an optimized quantum circuit architecture. Simulation results demonstrate a 6% improvement in prediction accuracy relative to existing classical models, as well as a significantly more stable convergence performance compared to previous classical approaches. Moreover, to scalably deploy the proposed framework over today's noisy intermediate-scale quantum (NISQ) devices, a novel quantum error mitigation algorithm is proposed. This algorithm outperforms existing techniques and is capable of mitigating errors with gate noise probabilities,p≤0.05, while resulting in no additional overhead during the training and testing phases.
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.
Drug repositioning is a less expensive and time-consuming method than the traditional method of drug discovery. It is a strategy for identifying new uses for approved or investigational drugs that are outside the scope of the original medical indication. A key strategy in repositioning approved or investigational drugs is determining the binding affinity of these drugs to target proteins. The large increase in available experimental data has helped deep learning methods to demonstrate superior performance compared to conventional prediction and other traditional computational methods in precise binding affinity prediction. However, these methods are complex and time-consuming, presenting a significant barrier to their development and practical application. In this context, quantum computing (QC) and quantum machine learning (QML) theoretically offer promising solutions to effectively address these challenges. In this work, we introduce a hybrid quantum–classical framework to predict binding affinity. Our approach involves, initially, the implementation of an efficient classical model using convolutional neural networks (CNNs) for feature extraction and three fully connected layers for prediction. Subsequently, retaining the classical module for feature extraction, we implement various quantum and classical modules for binding affinity prediction, which accept the concatenated features as input. Quantum predicted modules are implemented with Variational Quantum Regressions (VQRs), while classical predicted modules are implemented with various fully connected layers. Our findings clearly show that hybrid quantum–classical models accelerate the training process in terms of epochs and achieve faster stabilization. Also, these models demonstrate quantum superiority in terms of complexity, accuracy, and generalization, thereby indicating a promising direction for QML.
One of the main challenges in drug discovery is to find molecules that bind specifically and strongly to their target protein while having minimal binding to other proteins. By predicting binding affinity, it is possible to identify the most promising candidates from a large pool of potential compounds, reducing the number of compounds that need to be tested experimentally. Recently, deep learning methods have shown superior performance than traditional computational methods for making accurate predictions on large datasets. However, the complexity and time-consuming nature of these methods have limited their usage and development. Quantum machine learning is an emerging technology that has the potential to improve many classical machine learning algorithms. In this work we present a hybrid quantum-classical convolutional neural network, which is able to reduce by 20% the complexity of the classical network while maintaining optimal performance in the predictions. Additionally, it results in a significant time savings of up to 40% in the training process, which means a meaningful speed up of the drug discovery process.
Quantum machine learning (QML) has attracted significant interest in drug discovery due to its potential to model complex molecular interactions and improve prediction accuracy for protein-ligand binding affinity. However, most existing hybrid quantum-classical approaches rely on static architectures that apply quantum computation uniformly across all samples, regardless of molecular complexity or prediction confidence. Such static execution strategies lead to inefficient quantum resource utilization and limit scalability on near-term noisy intermediatescale quantum (NISQ) devices. In this paper, we propose an uncertainty-aware adaptive hybrid quantum-classical learning framework for protein-ligand binding affinity prediction that treats quantum computation as a selectively invoked resource rather than a constant component of the learning pipeline. The proposed framework first employs a classical ensemble-based regression model to generate binding affinity predictions along with an associated uncertainty estimate derived from ensemble variance. This uncertainty information is then used by a decision mechanism to dynamically select between classical-only inference, shallow quantum circuit execution, or deep quantum circuit execution. By adapting the quantum circuit depth and invocation frequency to the predicted uncertainty, the framework enables decision-centric allocation of quantum resources. Experimental evaluation of binding affinity data demonstrates that the recommended adaptive framework utilizes around 76 % less quantum resources than static hybrid quantum learning methods that use fixed-depth quantum circuits for all samples. The framework also preserves decision-level functionality and a steady inference workflow. These findings highlight the effectiveness of uncertainty-guided adaptivity as a practical strategy and offer a scalable foundation for future quantum-enhanced molecular learning.method for incorporating QML into drug development pipelines while taking hardware constraints into consideration.
Central in drug design is the identification of biomolecules that uniquely and robustly bind to a target protein, while minimizing their interactions with others. Accordingly, precise binding affinity prediction, enabling the accurate selection of suitable candidates from an extensive pool of potential compounds, can greatly reduce the expenses associated to practical experimental protocols. In this respect, recent advances revealed that deep learning methods show superior performance compared to other traditional computational methods, especially with the advent of large datasets. These methods, however, are complex and very time-intensive, thus representing an important clear bottleneck for their development and practical application. In this context, the emerging realm of quantum machine learning holds promise for enhancing numerous classical machine learning algorithms. In this work, we take one step forward and present a hybrid quantum-classical convolutional neural network, which is able to reduce by 20% the complexity of the classical counterpart while still maintaining optimal performance in the predictions. Additionally, this results in a significant cost and time savings of up to 40% in the training stage, which means a substantial speed-up of the drug design process.
Accurate prediction of binding affinities and efficient lead optimization remain central challenges in computational drug discovery, particularly for complex biological targets characterized by rugged energy landscapes, conformational heterogeneity, and high-dimensional interaction spaces. Classical computational methods—such as molecular docking, force-field–based simulations, and deep learning models—have made substantial progress, yet they often struggle to capture quantum-mechanical effects and long-range correlations critical to molecular recognition. This study explores a quantum-enhanced framework that integrates Variational Quantum Algorithms (VQAs), quantum-inspired Hamiltonian modeling, and hybrid quantum–classical optimization workflows to improve the fidelity and scalability of drug discovery pipelines. By encoding molecular interactions into parameterized quantum circuits, the framework leverages quantum superposition and entanglement to explore complex chemical space more efficiently, enabling refined estimation of binding energies and accelerated identification of high-quality leads. Preliminary simulations indicate that VQA-based estimators outperform classical baselines for challenging protein–ligand systems, reducing prediction error while maintaining computational tractability. These findings highlight the emerging potential of quantum technologies to enable more accurate, data-efficient, and mechanistically grounded drug discovery for next-generation therapeutics.