MOTIVATION: While many quantum computing (QC) methods promise theoretical advantages over classical counterparts, quantum hardware remains limited. Exploiting near-term QC in computer-aided drug design (CADD) thus requires judicious partitioning between classical and quantum calculations. RESULTS: We present HypaCADD, a hybrid classical-quantum workflow for finding ligands binding to proteins, while accounting for genetic mutations. We explicitly identify modules of our drug-design workflow currently amenable to replacement by QC: non-intuitively, we identify the mutation-impact predictor as the best candidate. HypaCADD thus combines classical docking and molecular dynamics with quantum machine learning (QML) to infer the impact of mutations. We present a case study with the coronavirus (SARS-CoV-2) protease and associated mutants. We map a classical machine-learning module onto QC, using a neural network constructed from qubit-rotation gates. We have implemented this in simulation and on two commercial quantum computers. We find that the QML models can perform on par with, if not better than, classical baselines. In summary, HypaCADD offers a successful strategy for leveraging QC for CADD. AVAILABILITY AND IMPLEMENTATION: Jupyter Notebooks with Python code are freely available for academic use on GitHub: https://www.github.com/hypahub/hypacadd_notebook. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
MOTIVATION: While many quantum computing (QC) methods promise theoretical advantages over classical counterparts, quantum hardware remains limited. Exploiting near-term QC in computer-aided drug design (CADD) thus requires judicious partitioning between classical and quantum calculations. RESULTS: We present HypaCADD, a hybrid classical-quantum workflow for finding ligands binding to proteins, while accounting for genetic mutations. We explicitly identify modules of our drug-design workflow currently amenable to replacement by QC: non-intuitively, we identify the mutation-impact predictor as the best candidate. HypaCADD thus combines classical docking and molecular dynamics with quantum machine learning (QML) to infer the impact of mutations. We present a case study with the coronavirus (SARS-CoV-2) protease and associated mutants. We map a classical machine-learning module onto QC, using a neural network constructed from qubit-rotation gates. We have implemented this in simulation and on two commercial quantum computers. We find that the QML models can perform on par with, if not better than, classical baselines. In summary, HypaCADD offers a successful strategy for leveraging QC for CADD. AVAILABILITY AND IMPLEMENTATION: Jupyter Notebooks with Python code are freely available for academic use on GitHub: https://www.github.com/hypahub/hypacadd_notebook. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
Quantum machine learning (QML) has become a key research field on the interface between quantum computing, artificial intelligence, chemistry and pharmaceutical science. By enhancing the molecular representation, predictive modeling, generative chemistry, and quantum-assisted simulations workflows, researchers are increasingly arguing that QML can aid work in molecular design and drug discovery. Meanwhile, this field is still in its new frontiers with much of the published literature only comprising reviews, simulations, proof-of-concept applications, and hybrid quantum-classical demonstrations as opposed to large-scale pharmaceutical application. In this qualitative study, the literature emerging is reviewed to determine how QML is being conceptualized, areas of application seem the most promising, and what obstacles remain that hamper its practical implementation in actual drug discovery pipelines. The paper presents five large themes segmented into a thematic analysis of recent reviews and representative studies and includes relevant themes as QML as a representational innovation, QML in predictive tasks, e.g., drug-target interaction and ADMET modeling, QML in generative molecular design, hybrid quantum-classical workflows as the most plausible approach in the near term, and the continuation of restrictions in terms of hardware, trainability, data This research paper concludes that the idea of QML must be seen at present as a field not as an alternative to the classical machine learning in drug discovery, but it is an opportunity with strategic and scientific potential whose future realization may be found in the subproblems carefully chosen where the influence of molecular quantum effects, the complexity of learning, and the hybrid implementations converge. Keywords: quantum machine learning, molecular design, drug discovery, qualitative study, quantum computing, generative chemistry, ADMET, drug-target interaction
A study published in the Journal of Computer-Aided Molecular Design presents the first innovative quantum algorithm for identifying the optimal docking sites where proteins and ligands bind during the drug design process. It expands the existing protein lattice model to fully include hydrogen bonding and hydrophobic interactions, introducing quantum state labelling for interaction sites and applying an extended and modified Grover quantum search algorithm. The algorithm was successfully verified on IBM's real 127-qubit quantum computers by applying error mitigation techniques (such as M3 and Pauli twirling), and it is expected to exponentially accelerate drug candidate screening for large proteins as hardware scales up in the future. [Quantum Biology Society] Even after the introduction of High-Performance Computers (HPC) into drug development, protein-ligand docking has faced fundamental computational limits with classical computing methods because it is inherently a complex quantum mechanical interaction process. In response to the question, "Can quantum computers be used in drug design and how?" raised alongside the rapid advancement of quantum computers today, a study titled "Quantum algorithm for protein-ligand docking sites identification in the interaction space," recently published in the international journal Journal of Computer-Aided Molecular Design, has provided a clear answer. An industry-academia joint research team consisting of Professor Ioannis G. Karafyllidis from the Democritus University of Thrace in Greece and researchers from the multinational pharmaceutical company Pfizer conducted this innovative study. ■ Combination of an Extended Lattice Model and Grover's Quantum Search Algorithm The researchers significantly expanded the previously used protein lattice model to fully encompass hydrogen bonding and hydrophobic interactions, which are key interactions between proteins and ligands. Within this expanded model, they introduced quantum state labelling for each interaction site and implemented an extended and modified form of Grover's quantum search algorithm. Simulation of the algorithm demonstrated that it can identify potential docking sites inside the target protein even within a massive interaction space, and evaluate the optimal binding positions much more efficiently and rapidly than classical computing tools through Euclidean distance calculations based on the quantum SWAP test. ■ Real Quantum Hardware Verification and Infinite Scalability Notably, this study did not stop at simulators but verified the algorithm's accuracy by running it directly on IBM's real 127-qubit quantum computers (such as ibm_brisbane). To overcome the hardware noise generated during this process, they successfully applied state-of-the-art quantum error mitigation techniques such as M3 (Matrix-free Measurement Mitigation), Pauli twirling, and dynamical decoupling. The most powerful asset of the newly developed quantum algorithm is its exceptional scalability. Thanks to this characteristic, the algorithm is perfectly suited for exploring binding sites within complex target proteins with massive molecular weights. By breaking the bottleneck of traditional drug discovery pipelines that required heavy computations, it is expected to serve as a revolutionary milestone that will exponentially explode the potential of drug candidate screening and molecular design as the number of available qubits increases with future hardware advancements. #QuantumAlgorithm #DrugScreening #ProteinLigandDocking #GroverAlgorithm #QuantumComputing #DrugDevelopment #MolecularDocking #QuantumBiology #Biophysics #KoreanQuantumBiologySociety https://www.researchgate.net/publication/393436574_Quantum_algorithm_for_protein-ligand_docking_sites_identification_in_the_interaction_space
Early-stage decisions in the pharmaceutical development process carry outsized consequences for eventual clinical success, yet the computational tools underpinning these decisions remain fundamentally constrained. Computer-aided drug design (CADD) has transformed how researchers navigate chemical space and predict ligand–target interactions, but classical implementations rely on mechanical force-field approximations that fail to capture polarisation, charge transfer, and electron correlation effects central to molecular recognition and reactivity. Quantum-mechanical treatments that correctly describe these phenomena scale exponentially with system size on classical hardware, rendering them impractical for drug-relevant biomolecules. Quantum computing offers a physically motivated path beyond this scaling barrier: by exploiting superposition, entanglement, and interference, quantum algorithms can in principle simulate electronic structure with polynomial resource requirements for targeted problem classes. This article provides a theoretical review of how quantum computation integrates throughout the drug discovery pipeline, from target identification to lead optimisation. Its primary contribution is a pipeline-level mapping of quantum methods—including the Variational Quantum Eigensolver (VQE), quantum machine learning, and quantum-enhanced optimisation—to specific drug development stages. The review critically distinguishes near-term NISQ (Noisy Intermediate-Scale Quantum: current devices with 50–1,000 noisy qubits operating without full error correction) capabilities from fault-tolerant quantum computing (FTQC) requirements, quantifies current resource gaps through a worked CYP3A4 case study, and identifies algorithmic limitations (barren plateaus, ansatz expressibility, measurement overhead), hardware scalability, and error correction overhead as the principal barriers to practical deployment.
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.
The Epidermal Growth Factor Receptor (EGFR) is a transmembrane protein in the Receptor Tyrosine Kinases (RTKs) family, playing a central role in cell growth, motility, and differentiation. Mutations in EGFR are associated with various cancers, notably Non-Small Cell Lung Cancer (NSCLC), due to overexpression and dysregulated signaling. To support early-stage drug discovery targeting EGFR, this work introduces Q-CaDD (Quantum-enhanced Computer-aided Drug Design), a hybrid quantum–classical computational framework. Q-CaDD integrates quantum machine learning (QML), classical models, molecular docking, and multi-stage ligand filtering. Over 200,000 ligands were generated using STONED-SELFIES and filtered using Ghose and Quantitative Estimate of Drug-Likeness (QED) criteria. Docking simulations were performed using AutoDock Vina, and toxicity prediction employed an ensemble of machine learning models including a Quantum Support Vector Machine (QSVM). Model evaluation was conducted on the Tox21 dataset using the NR-AR (Androgen Receptor) pathway as a proof-of-concept toxicity endpoint. The hybrid ensemble achieved an AUC-ROC of ~ 0.76, demonstrating improved generalisation relative to standalone classical models under the same evaluation setting and competitive performance with respect to reported benchmark results. Several compounds exhibited favourable predicted affinity and toxicity profiles and are identified as preliminary candidate molecules pending further experimental validation. Overall, this study demonstrates that quantum-enhanced components can contribute complementary predictive signals within hybrid drug discovery workflows, even under the constraints of current Noisy Intermediate-Scale Quantum (NISQ) hardware.
Using quantum computing for drug design is among the most promising applications in quantum technologies. Genetic algorithms with their evolutionary iterations make it a propitious approach in various tasks, including drug discovery, gene prediction, docking of ligands to receptors, and the design to combinatorial libraries. As its computational power and methods limits classical computing, quantum computing intends to break these limits with exponential computing capabilities. This application complements both quantum theory and genetic programming as we use true randomness with mutation and fitness function based on information encoded onto qubits storing quantum data. In this article, we present the results of encoding quantum data to our quantum genetic algorithm, which predicts the best possible drug structure to bind onto the target protein. The qubits hold the genome structure to perform bit string mutation over quantum gates. These results are later than compared to classical computing with various approaches in the evolutionary algorithm's parameters.