A central question in hybrid quantum–classical learning is whether variational quantum circuits (VQCs) preserve task-relevant information more efficiently than classical nonlinearities of equal output dimension. We study this question for drug–target interaction prediction in Alzheimer’s disease drug-repurposing workflows using a Hybrid Quantum–Classical Graph Neural Network (HQGNN). The model compresses 512-dimensional GNN embeddings into a four-qubit VQC (128 $$\times $$ compression) before a classical prediction head. On the DAVIS kinase benchmark, HQGNN achieves concordance index (CI) $$=0.527$$ and root mean squared error (RMSE) $$=0.850$$ , outperforming a dimension-matched classical bottleneck baseline (CI $$=0.500$$ ; random ranking). Under the same compression, the quantum layer recovers 51% of the ranking signal lost by compression relative to the full classical model and yields a 5.4% relative CI gain over the classical bottleneck. This effect is obtained with 24 trainable quantum parameters (representational yield $$\Delta $$ CI/parameter $$\approx 1.13\times 10^{-3}$$ ). Under depolarizing noise, RMSE degradation remains below 3.3% at realistic noisy intermediate-scale quantum (NISQ) levels ( $$p \le 0.01$$ ). Because the present benchmark is evaluated on a single transductive split, these results are interpreted as controlled proof-of-concept evidence of representational efficiency rather than definitive deployment-level generalization.
A central question in hybrid quantum–classical learning is whether variational quantum circuits (VQCs) preserve task-relevant information more efficiently than classical nonlinearities of equal output dimension. We study this question for drug–target interaction prediction in Alzheimer’s disease drug-repurposing workflows using a Hybrid Quantum–Classical Graph Neural Network (HQGNN). The model compresses 512-dimensional GNN embeddings into a four-qubit VQC (128 × compression) before a classical prediction head. On the DAVIS kinase benchmark, HQGNN achieves concordance index (CI) =0.527 and root mean squared error (RMSE) =0.850 , outperforming a dimension-matched classical bottleneck baseline (CI =0.500 ; random ranking). Under the same compression, the quantum layer recovers 51% of the ranking signal lost by compression relative to the full classical model and yields a 5.4% relative CI gain over the classical bottleneck. This effect is obtained with 24 trainable quantum parameters (representational yield Δ CI/parameter ≈1.13×10−3 ). Under depolarizing noise, RMSE degradation remains below 3.3% at realistic noisy intermediate-scale quantum (NISQ) levels ( p≤0.01 ). Because the present benchmark is evaluated on a single transductive split, these results are interpreted as controlled proof-of-concept evidence of representational efficiency rather than definitive deployment-level generalization.
Advances in classical machine learning and single-cell technologies have paved the way for understanding interactions between disease cells and tumor microenvironments towards accelerating therapeutic discovery. However, challenges in these machine learning methods and NP-hard problems in spatial biology create an opportunity to explore quantum computing algorithms. Here, we present a hybrid quantum-classical graph neural network (GNN) that combines a classical GNN with a type of quantum neural network (QNN) called a variational quantum classifier (VQC) for classifying binary sub-tasks in breast cancer subtyping. We explore two variants of the framework, the first with fixed pretrained GNN parameters and the second with end-to-end training of GNN+VQC. The results demonstrate that the hybrid quantum-classical neural network is at par with the state-of-the-art classical graph neural networks in terms of weighted precision, recall, and F1-score at higher dimensions. We also show that by means of amplitude encoding, we can compress information in logarithmic number of qubits and attain better performance in comparison to classical compression (which leads to information loss), while keeping the number of qubits required constant in both regimes. Finally, we show some results that end-to-end training enables an improvement over fixed GNN parameters and also slightly improves over vanilla GNN with the same number of dimensions.
Large compound libraries are reduced to candidate’s worth testing by computational prediction of drug-target interactions (DTI). We investigate whether this effort is aided by variational quantum circuits appropriate for noisy intermediate-scale quantum (NISQ) devices. Our hybrid model uses classical networks to encode ECFP4 fingerprints and protein sequence descriptors, compresses them to eight rotation angles, and then processes them using a four-layer hardware-efficient circuit that is read out using local Pauli-Z expectations. Realistic noise models are used to simulate the circuits, and it is trained end-to-end using gradients that match the parameter-shift algorithm. The model achieved test AUROCs of 0.896, 0.892, 0.911, and 0.878 on Davis, KIBA, BindingDB, and BIOSNAP. These results outperform a kernel SVM and logistic regression, although they lag behind a graph network on three datasets, a deep network (0.915–0.927), and gradient-boosted trees. Removing entanglement had little effect on the performance of a parameter-matched classical head, and no low-data advantage emerged. Hardware tolerance was demonstrated by the circuit itself. Because ranking is invariant to uniform noise attenuation, local readout avoided barren plateaus, 256 shots were sufficient, and 1% two-qubit error cost only 0.0025 AUROC. Calibration was recovered by recalibrating the reading. Hardware training costs, not noise, are the binding restriction. For drug-screening decisions, these predictions provide an evidence-based ranking of candidate compound–target pairs for experimental follow-up. The comparison with classical methods indicates whether adding a quantum circuit is justified by the resulting predictive performance and computational cost.
Drug discovery depends heavily on predicting molecular toxicity early and classical ML still struggles here, because the interactions that make a molecule toxic are fundamentally quantum-mechanical. This paper builds a Hybrid Quantum Graph Neural Network (QGNN) that feeds GCN-learned molecular embeddings into a Variational Quantum Circuit (VQC). A 3-layer GCN produces graphlevel embeddings, which are angle-encoded into 4-8 qubit quantum states, and Pauli-Z expectations are concatenated with classical features before the final classifier. A quantum edge embedding is also introduced, encoding bondtype information directly into entangling gate parameters. On MoleculeNet's Tox21 (7,831 compounds, 12 endpoints) and ClinTox (1,478 compounds), 5-fold cross-validation shows the hybrid 4-qubit model with edge embedding achieves 0.762 ROC-AUC on Tox21 (+3.1% over 0.739 classical baseline), while the 8-qubit hybrid model reaches 0.741 on ClinTox (+6.3% over 0.697 baseline), both with batch size 64. Smaller batches (64) consistently outperform larger batches (256) at3−17×computational cost. Quantum edge embedding yields its largest improvement with only 15 additional parameters: +16.4% on ClinTox (batch 64). Quantum-only models achieve 83.7% parameter reduction while landing consistently just below the classical baseline. Across five folds, however, every one of these differences falls inside overlapping 95% confidence intervals(p>0.05), so the gains reported here are consistent in direction but not individually significant at this sample size. Total overhead for hybrid models is 10-13% extra parameters with training time ranging from 1.2 to 54.6 seconds per epoch. External validation on the held-out BBBP benchmark (2,039 compounds), performed with the same architecture and no retuning, confirms that the gain transfers: the hybrid 4-qubit model reaches 0.702 ROC-AUC against 0.649 for the classical baseline (+8.2%), the largest relative gain across the three datasets. A mechanistic interpretability analysis attributes the edge-embedding effect to bond order reaching the model only through the entangling gates, where a learnable convex combination of perbond-type angles tunes entanglement continuously instead of pinning it at the CNOT maximum; the effect is positive on reactivity-driven toxicity endpoints and negative on passive permeability, matching the chemistry of each target.
Graph Neural Networks (GNNs) are now one of the key tools to model relational and non-Euclidean data in multiagent systems, infrastructure networks and even molecular modeling applications. Nevertheless, in very dense or noisy graph topologies, classical message-passing architectures may experience scalability and representational degeneration, especially due to over-smoothing and insufficient higher-order dependency information. The recent developments in quantum machine learning indicate that hybrid quantum-classical models can also provide an alternative feature representation by projecting relational data to parameterized quantum circuits. This article presents a Quantum-Enhanced Graph Neural Network (QGNN) architecture that extends variational quantum circuits with graph learning pipelines, based on classical learning. Parameters are represented as parameterized qubits, and relational dependencies are represented as structured entanglement mappings. We benchmark the regimes where quantum-enhanced relational encoding proves to be more robust and stable through the swarm coordination, molecular property prediction, and financial transaction network. We also elaborate on the issue of scalability, hardware issues, and practical aspects of near-term hybrid implementations and give a critical view of the changing role of quantum methods in computational intelligence systems.
Graph Neural Networks (GNNs) are now one of the key tools to model relational and non-Euclidean data in multiagent systems, infrastructure networks and even molecular modeling applications. Nevertheless, in very dense or noisy graph topologies, classical message-passing architectures may experience scalability and representational degeneration, especially due to over-smoothing and insufficient higher-order dependency information. The recent developments in quantum machine learning indicate that hybrid quantum-classical models can also provide an alternative feature representation by projecting relational data to parameterized quantum circuits. This article presents a Quantum-Enhanced Graph Neural Network (QGNN) architecture that extends variational quantum circuits with graph learning pipelines, based on classical learning. Parameters are represented as parameterized qubits, and relational dependencies are represented as structured entanglement mappings. We benchmark the regimes where quantum-enhanced relational encoding proves to be more robust and stable through the swarm coordination, molecular property prediction, and financial transaction network. We also elaborate on the issue of scalability, hardware issues, and practical aspects of near-term hybrid implementations and give a critical view of the changing role of quantum methods in computational intelligence systems.
Large language and sentence-embedding models provide rich semantic representations, but their high dimensionality poses a challenge for near-term quantum machine learning (QML), where quantum circuits can process only a limited number of input features. We investigate a hybrid quantum-classical pipeline that transforms high-dimensional sentence embeddings into compact representations for variational quantum classification. The workflow combines a pretrained sentence-embedding model, dimensionality reduction, angle encoding, a variational quantum circuit (VQC), and a classical decision layer. We systematically compare principal component analysis (PCA), neighborhood components analysis (NCA), and linear discriminant analysis (LDA), covering both unsupervised and supervised dimensionality reduction. Using the TREC question-classification dataset, we study the relationship between representation dimensionality, information retention, qubit count, and classification performance. Preliminary PCA experiments reveal a strong information bottleneck: reducing 768-dimensional embeddings to 3, 4, 5, and 8 dimensions retains about 8.2%, 10.2%, 11.9%, and 16.4% of the variance, with corresponding classification accuracies of 50.3%, 51.2%, 57.9%, and 63.4%. In contrast, supervised reduction is substantially more efficient. LDA reaches 85.3% accuracy and NCA reaches 83.1% using only 5 dimensions, under a leakage-free cross-validation protocol, compared with 85.1% for a full 384-dimensional classical baseline. These results indicate that supervised dimensionality reduction can preserve task-relevant information far more effectively than variance-based compression, making compact representations a promising route toward practical hybrid quantum-classical NLP models.