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

Computational and Structural Biotechnology Journal

Quantum neural networks meet federated learning for DNA mutation prediction

Sotirios Messinis, Ioannis Rallis, Nikolaos Temenos, Dimitris Kalogeras, George Anthony Kastis, Nikolaos Doulamis, Nicholas Ε. Protonotarios

Published Jan 1, 2025• 6 citations
Publisher

Abstract

In this work, we introduce QuanGAT, a hybrid framework integrating quantum neural networks (QNNs), graph attention networks (GATs), and federated learning to tackle DNA mutation prediction in biomedical graphs in a privacy-preserving, noise-aware setting. Motivated by quantum biology’s potential to describe mutation-level mechanisms, our approach is able to simulate decentralized genomic environments in order to protect sensitive data, while capturing complex biological variability. QuanGAT employs a QNN encoder based on parameterized quantum circuits, incorporating quantum noise, via the so-called depolarizing and amplitude damping channels. Furthermore, in order to enforce differential privacy, QuanGAT utilizes an attention-based architecture enhanced with Laplace noise. We evaluated the model on mutation-enriched protein–protein interaction networks, partitioned across simulated clients under centralized, federated, and noisy scenarios. In particular, we employed QuanGAT in three different datasets, namely PPI, STRING, and OBGN-Proteins. Especially in federated learning settings, QuanGAT consistently outperformed certain state-of-the-art graph neural networks up to 4.5 % in terms of accuracy and up to 6.3 % in terms of macro F1 score. Our findings demonstrate that integrating QNN encodings with attention-based graph learning may improve DNA mutation prediction in decentralized, privacy-aware settings.

DOI
10.1016/j.csbj.2025.09.036

Related papers

Hybrid ClassicalQuantum Learning Framework for Genetic Disorder Prediction Using DNA Mutation Data

J. Senthil Kumar, Arockia Jenisha K

Accurate prediction of genetic disorders from DNA mutation data is a critical challenge in computational genomics due to complex mutation patterns and nonlinear genotype–phenotype relationships. This paper proposes a hybrid classical–quantum learning framework that integrates unified sequence graph feature encoding, transformer-based contextual modeling, dual-attention representation refinement, orangutan-based parameter optimization, and a variational quantum classifier for enhanced genetic disorder prediction. The proposed approach leverages hybrid classical–quantum learning to enhance discriminative feature learning in compact latent spaces. Experiments conducted on the Genetic Disorder Prediction Dataset demonstrate that the proposed framework achieves 94.10% accuracy, 93.60% precision, 93.40% F1-score, 92.00% Matthews correlation coefficient, and 96.70% AUC, outperforming existing machine learning and deep learning methods. Ablation studies confirm the contribution of each architectural component, while quantum circuit analysis identifies an optimal configuration of 8 qubits with a circuit depth of 4. Noise sensitivity and inference-time evaluations further indicate that the proposed model remains robust under realistic quantum noise conditions with only a marginal computational overhead. These results validate the effectiveness and practical feasibility of hybrid classical–quantum learning for genomic prediction tasks and highlight its potential for future quantum-assisted bioinformatics and precision medicine applications.

International Conference on Intelligent Systems and Artificial Intelligence Applications (ISAA)•Apr 1, 2026•0 citations

Hybrid ClassicalQuantum Learning Framework for Genetic Disorder Prediction Using DNA Mutation Data

J. Senthil Kumar, Arockia Jenisha K

Accurate prediction of genetic disorders from DNA mutation data is a critical challenge in computational genomics due to complex mutation patterns and nonlinear genotype-phenotype relationships. This paper proposes a hybrid classical-quantum learning framework that integrates unified sequence graph feature encoding, transformer-based contextual modeling, dual-attention representation refinement, orangutan-based parameter optimization, and a variational quantum classifier for enhanced genetic disorder prediction. The proposed approach leverages hybrid classical-quantum learning to enhance discriminative feature learning in compact latent spaces. Experiments conducted on the Genetic Disorder Prediction Dataset demonstrate that the proposed framework achieves 94.10% accuracy, 93.60% precision, 93.40% F1-score, 92.00% Matthews correlation coefficient, and 96.70% AUC, outperforming existing machine learning and deep learning methods. Ablation studies confirm the contribution of each architectural component, while quantum circuit analysis identifies an optimal configuration of 8 qubits with a circuit depth of 4. Noise sensitivity and inference-time evaluations further indicate that the proposed model remains robust under realistic quantum noise conditions with only a marginal computational overhead. These results validate the effectiveness and practical feasibility of hybrid classical-quantum learning for genomic prediction tasks and highlight its potential for future quantum-assisted bioinformatics and precision medicine applications.

International Conference on Trends in Quantum Computing and Emerging Business Technologies (TQCEBT)•Apr 1, 2026•0 citations

Federated Quantum Machine Learning for Secure Multi-Party Genomic Data Analysis: A Hybrid Architecture with Differential Privacy

David Jumpa Malem Sembiring, Sinek Mehuli Br Perangin Angin

The exponential growth of genomic data has created opportunities for collaborative biomedical research while posing significant privacy and security challenges. Traditional centralized machine learning approaches risk data breaches and regulatory non-compliance. This study proposes a novel hybrid architecture combining Federated Quantum Machine Learning (FQML) with Differential Privacy (DP) for secure multi-party genomic data analysis. Our simulated framework enables institutions to collaboratively train quantum machine learning models on distributed genomic datasets without exposing sensitive data. Using variational quantum circuits within a federated learning framework, we implement privacy-preserving models across three simulated genomic data silos. Gaussian noise injection via DP mechanisms during gradient updates ensures formal privacy guarantees (ε = 0.85). Experimental results on synthetic datasets demonstrate that FQML achieves 93.4% predictive accuracy in genome-wide association studies simulation, outperforming classical federated models in convergence speed by 27% and reducing communication overhead by 19%. These findings suggest FQML with DP provides a promising foundation for future secure genomic collaboration, though real-world validation remains necessary.

Journal of Novel Engineering Science and Technology•May 4, 2026•0 citations

Quantum Graph Attention Networks: Trainable Quantum Encoders for Inductive Graph Learning

Arthur Mendonça Faria, Mehdi Djellabi, Igor O. Sokolov +1 more

We introduce Quantum Graph Attention Networks (QGATs) as trainable quantum encoders for inductive learning on graphs, extending the Quantum Graph Neural Networks (QGNN) framework. QGATs leverage parameterized quantum circuits to encode node features and neighborhood structures, with quantum attention mechanisms modulating the contribution of each neighbor via dynamically learned unitaries. This allows for expressive, locality-aware quantum representations that can generalize across unseen graph instances. We evaluate our approach on the QM9 dataset, targeting the prediction of various chemical properties. Our experiments compare classical and quantum graph neural networks-with and without attention layers-demonstrating that attention consistently improves performance in both paradigms. Notably, we observe that quantum attention yields increasing benefits as graph size grows, with QGATs significantly outperforming their non-attentive quantum counterparts on larger molecular graphs. Furthermore, for smaller graphs, QGATs achieve predictive accuracy comparable to classical GAT models, highlighting their viability as expressive quantum encoders. These results show the potential of quantum attention mechanisms to enhance the inductive capacity of QGNN in chemistry and beyond.

arXiv:2509.11390•Sep 14, 2025•2 citations

Federated Variational Quantum Neural Networks for Privacy-Preserving Anomaly Detection in IoT

Radhakrishnan Delhibabu, Manuel Mazzara, Salvatore Distefano

In this paper, we propose a Federated Variational Quantum Machine Learning (F-VQML) framework tailored for anomaly detection in smart IoT infrastructures. First, we introduce a localized quantum feature embedding strategy that mitigates the dimensionality bottleneck, allowing resource-constrained edge nodes to efficiently encode time-series data into Hilbert space. Second, we integrate a federated learning architecture where nodes collaboratively train Variational Quantum Circuits (VQCs) by exchanging only parameterized quantum gradients, thereby ensuring strict data privacy and bypassing the need for raw data transmission. Finally, we evaluate the robustness of the F-VQML framework against realistic hardware noise models, specifically depolarizing and Pauli noise channels. Comprehensive simulations on network intrusion datasets reveal that our approach achieves a 94.2% anomaly detection accuracy. Furthermore, it reduces communication overhead by 98% compared to classical deep federated architectures, all while maintaining resilience to NISQ-era depolarizing noise.

IEEE International Conference on Smart Computing Workshops and Other Affiliated Events (SMARTCOMP Companion)•Jun 1, 2026•0 citations

FedVQC for Genomic Data: A Quantum-Enhanced Privacy Approach

Vaidehi Gawande, Jayesh V. Hire, Sagar Dhande

Abstract This study presents a Federated Quantum Variational Quantum Classifier (FedVQC) framework designed to address critical challenges in healthcare data privacy and computational efficiency, particularly in the domain of genomic analysis. Conventional machine learning approaches in healthcare often face obstacles stemming from privacy concerns, regulatory constraints, and the fragmented nature of medical data across different institutions. The proposed FedVQC framework leverages the principles of federated learning and quantum machine learning to enable secure, decentralized training of predictive models without requiring the sharing of sensitive patient data. Extensive experimentation on multiple genomic datasets reveals a strong correlation between the number of participating institutions and the model's accuracy, with performance consistently improving as more clients contribute to the training process. The framework demonstrates high accuracy levels, ranging from 70% to 96%, across diverse datasets, highlighting its robustness and applicability in healthcare analytics. By harnessing the computational power of quantum computing and the collaborative nature of federated learning, the FedVQC framework provides a scalable and secure solution for genomic research. This study underscores the potential of quantum federated learning in advancing privacy-preserving precision medicine, large-scale genomic collaboration, and broader applications in bioinformatics, drug discovery, and personalized healthcare analytics

•Jan 30, 2026•0 citations
In this work, we introduce QuanGAT, a hybrid framework integrating quantum neural networks (QNNs), graph attention networks (GATs), and federated learning to tackle DNA mutation prediction in biomedical graphs in a privacy-preserving, noise-aware setting. Motivated by quantum biology’s potential to describe mutation-level mechanisms, our approach is able to simulate decentralized genomic environments in order to protect sensitive data, while capturing complex biological variability. QuanGAT employs a QNN encoder based on parameterized quantum circuits, incorporating quantum noise, via the so-called depolarizing and amplitude damping channels. Furthermore, in order to enforce differential privacy, QuanGAT utilizes an attention-based architecture enhanced with Laplace noise. We evaluated the model on mutation-enriched protein–protein interaction networks, partitioned across simulated clients under centralized, federated, and noisy scenarios. In particular, we employed QuanGAT in three different datasets, namely PPI, STRING, and OBGN-Proteins. Especially in federated learning settings, QuanGAT consistently outperformed certain state-of-the-art graph neural networks up to 4.5 % in terms of accuracy and up to 6.3 % in terms of macro F1 score. Our findings demonstrate that integrating QNN encodings with attention-based graph learning may improve DNA mutation prediction in decentralized, privacy-aware settings.
Accurate prediction of genetic disorders from DNA mutation data is a critical challenge in computational genomics due to complex mutation patterns and nonlinear genotype–phenotype relationships. This paper proposes a hybrid classical–quantum learning framework that integrates unified sequence graph feature encoding, transformer-based contextual modeling, dual-attention representation refinement, orangutan-based parameter optimization, and a variational quantum classifier for enhanced genetic disorder prediction. The proposed approach leverages hybrid classical–quantum learning to enhance discriminative feature learning in compact latent spaces. Experiments conducted on the Genetic Disorder Prediction Dataset demonstrate that the proposed framework achieves 94.10% accuracy, 93.60% precision, 93.40% F1-score, 92.00% Matthews correlation coefficient, and 96.70% AUC, outperforming existing machine learning and deep learning methods. Ablation studies confirm the contribution of each architectural component, while quantum circuit analysis identifies an optimal configuration of 8 qubits with a circuit depth of 4. Noise sensitivity and inference-time evaluations further indicate that the proposed model remains robust under realistic quantum noise conditions with only a marginal computational overhead. These results validate the effectiveness and practical feasibility of hybrid classical–quantum learning for genomic prediction tasks and highlight its potential for future quantum-assisted bioinformatics and precision medicine applications.
Accurate prediction of genetic disorders from DNA mutation data is a critical challenge in computational genomics due to complex mutation patterns and nonlinear genotype-phenotype relationships. This paper proposes a hybrid classical-quantum learning framework that integrates unified sequence graph feature encoding, transformer-based contextual modeling, dual-attention representation refinement, orangutan-based parameter optimization, and a variational quantum classifier for enhanced genetic disorder prediction. The proposed approach leverages hybrid classical-quantum learning to enhance discriminative feature learning in compact latent spaces. Experiments conducted on the Genetic Disorder Prediction Dataset demonstrate that the proposed framework achieves 94.10% accuracy, 93.60% precision, 93.40% F1-score, 92.00% Matthews correlation coefficient, and 96.70% AUC, outperforming existing machine learning and deep learning methods. Ablation studies confirm the contribution of each architectural component, while quantum circuit analysis identifies an optimal configuration of 8 qubits with a circuit depth of 4. Noise sensitivity and inference-time evaluations further indicate that the proposed model remains robust under realistic quantum noise conditions with only a marginal computational overhead. These results validate the effectiveness and practical feasibility of hybrid classical-quantum learning for genomic prediction tasks and highlight its potential for future quantum-assisted bioinformatics and precision medicine applications.
The exponential growth of genomic data has created opportunities for collaborative biomedical research while posing significant privacy and security challenges. Traditional centralized machine learning approaches risk data breaches and regulatory non-compliance. This study proposes a novel hybrid architecture combining Federated Quantum Machine Learning (FQML) with Differential Privacy (DP) for secure multi-party genomic data analysis. Our simulated framework enables institutions to collaboratively train quantum machine learning models on distributed genomic datasets without exposing sensitive data. Using variational quantum circuits within a federated learning framework, we implement privacy-preserving models across three simulated genomic data silos. Gaussian noise injection via DP mechanisms during gradient updates ensures formal privacy guarantees (ε = 0.85). Experimental results on synthetic datasets demonstrate that FQML achieves 93.4% predictive accuracy in genome-wide association studies simulation, outperforming classical federated models in convergence speed by 27% and reducing communication overhead by 19%. These findings suggest FQML with DP provides a promising foundation for future secure genomic collaboration, though real-world validation remains necessary.
We introduce Quantum Graph Attention Networks (QGATs) as trainable quantum encoders for inductive learning on graphs, extending the Quantum Graph Neural Networks (QGNN) framework. QGATs leverage parameterized quantum circuits to encode node features and neighborhood structures, with quantum attention mechanisms modulating the contribution of each neighbor via dynamically learned unitaries. This allows for expressive, locality-aware quantum representations that can generalize across unseen graph instances. We evaluate our approach on the QM9 dataset, targeting the prediction of various chemical properties. Our experiments compare classical and quantum graph neural networks-with and without attention layers-demonstrating that attention consistently improves performance in both paradigms. Notably, we observe that quantum attention yields increasing benefits as graph size grows, with QGATs significantly outperforming their non-attentive quantum counterparts on larger molecular graphs. Furthermore, for smaller graphs, QGATs achieve predictive accuracy comparable to classical GAT models, highlighting their viability as expressive quantum encoders. These results show the potential of quantum attention mechanisms to enhance the inductive capacity of QGNN in chemistry and beyond.
In this paper, we propose a Federated Variational Quantum Machine Learning (F-VQML) framework tailored for anomaly detection in smart IoT infrastructures. First, we introduce a localized quantum feature embedding strategy that mitigates the dimensionality bottleneck, allowing resource-constrained edge nodes to efficiently encode time-series data into Hilbert space. Second, we integrate a federated learning architecture where nodes collaboratively train Variational Quantum Circuits (VQCs) by exchanging only parameterized quantum gradients, thereby ensuring strict data privacy and bypassing the need for raw data transmission. Finally, we evaluate the robustness of the F-VQML framework against realistic hardware noise models, specifically depolarizing and Pauli noise channels. Comprehensive simulations on network intrusion datasets reveal that our approach achieves a 94.2% anomaly detection accuracy. Furthermore, it reduces communication overhead by 98% compared to classical deep federated architectures, all while maintaining resilience to NISQ-era depolarizing noise.
Abstract This study presents a Federated Quantum Variational Quantum Classifier (FedVQC) framework designed to address critical challenges in healthcare data privacy and computational efficiency, particularly in the domain of genomic analysis. Conventional machine learning approaches in healthcare often face obstacles stemming from privacy concerns, regulatory constraints, and the fragmented nature of medical data across different institutions. The proposed FedVQC framework leverages the principles of federated learning and quantum machine learning to enable secure, decentralized training of predictive models without requiring the sharing of sensitive patient data. Extensive experimentation on multiple genomic datasets reveals a strong correlation between the number of participating institutions and the model's accuracy, with performance consistently improving as more clients contribute to the training process. The framework demonstrates high accuracy levels, ranging from 70% to 96%, across diverse datasets, highlighting its robustness and applicability in healthcare analytics. By harnessing the computational power of quantum computing and the collaborative nature of federated learning, the FedVQC framework provides a scalable and secure solution for genomic research. This study underscores the potential of quantum federated learning in advancing privacy-preserving precision medicine, large-scale genomic collaboration, and broader applications in bioinformatics, drug discovery, and personalized healthcare analytics