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

IEEE International Conference on Intelligent Computer Communication and Processing (ICCP)

Predicting Drug Sensitivity in TP53-Mutated Cancer via Quantum Boltzman Machines

Vasile Vancea

Published Oct 16, 2025• 0 citations
Publisher

Abstract

Mutations in the TP53 gene are among the most prevalent alterations in human cancers and are known to influence therapeutic responses. Accurate prediction of drug sensitivity based on TP53 mutation profiles remains a major challenge in precision oncology. In this study, we propose a quantum-enhanced framework for genomic classification using Quantum Boltzmann Machines (QBMs) applied to quantum-encoded DNA sequences. Exon 5–8 fragments of TP53 containing both wild-type and clinically relevant mutations were encoded using angle-based quantum rotations and input into a QBM architecture trained to predict binary drug response (sensitive vs resistant) based on half-maximal inhibitory concentration (IC50) thresholds. Simulated results demonstrate that the QBM achieved over $\mathbf{9 1 \%}$ accuracy in classifying drug sensitivity, outperforming classical Boltzmann models and revealing interpretable latent features. This work showcases the potential of QBMs in modeling sequence-driven phenotypes and supports their application in biomarker discovery, drug response prediction, and quantum-enabled precision medicine.

DOI
10.1109/iccp68926.2025.11427125

Related papers

Hybrid Quantum Neural Network for Drug Response Prediction

Asel Sagingalieva, Mohammad Kordzanganeh, N. R. Kenbaev +3 more

Cancer is one of the leading causes of death worldwide. It is caused by various genetic mutations, which makes every instance of the disease unique. Since chemotherapy can have extremely severe side effects, each patient requires a personalized treatment plan. Finding the dosages that maximize the beneficial effects of the drugs and minimize their adverse side effects is vital. Deep neural networks automate and improve drug selection. However, they require a lot of data to be trained on. Therefore, there is a need for machine-learning approaches that require less data. Hybrid quantum neural networks were shown to provide a potential advantage in problems where training data availability is limited. We propose a novel hybrid quantum neural network for drug response prediction based on a combination of convolutional, graph convolutional, and deep quantum neural layers of 8 qubits with 363 layers. We test our model on the reduced Genomics of Drug Sensitivity in Cancer dataset and show that the hybrid quantum model outperforms its classical analog by 15% in predicting IC50 drug effectiveness values. The proposed hybrid quantum machine learning model is a step towards deep quantum data-efficient algorithms with thousands of quantum gates for solving problems in personalized medicine, where data collection is a challenge.

arXiv:2211.05777•Cancers•May 10, 2023•110 citations

246 Feasibility of quantum computing and quantum boltzmann machines for glioblastoma classification

Joseph Davids, Andrew Folusho Alalade, Hutan Ashrafian

a:2:{s:4:"lang";s:2:"en";s:7:"content";s:1284:" Glioblastoma, one of the most aggressive forms of brain cancer affecting the elderly and children indescriminately requires advanced computational techniques to achieve accurate and efficient classification for improved patient outcomes. This study explores the application of Quantum Boltzmann Machines (QBMs), a quantum-enhanced variant of classical Boltzmann Machines, to classify glioblastoma from multimodal datasets including imaging, spectroscopy, and molecular profiles. QBMs leverage quantum computing’s ability to represent and sample from complex probability distributions, offering a computational advantage in optimizing high-dimensional data. This study demonstrates and presents QBMs and how they may outperform classical models in accuracy and training efficiency, particularly useful for distinguishing glioblastoma from normal and marginal tissues. Preliminary results highlight the potential of quantum-enhanced machine learning to revolutionize cancer diagnostics by enabling faster and more precise classifications. Our future work will involve scaling QBMs to larger datasets, integrating multimodal inputs, and validating performance in clinical workflows, paving the way for quantum technologies in precision oncology. jdavids{at}ic.ac.uk ";}

Journal of Neurology Neurosurgery & Psychiatry•Nov 26, 2025•0 citations

Quantum Interaction Manifolds for Cancer Genomics: A Theoretical Framework and Proof-of-Concept Quantum Machine Learning for Early Diagnosis and Drug Response Modeling

Parham Ghayour

Abstract Understanding and predicting cancer phenotypes from genomic data requires models capableof capturing high-order interactions among genes and biological pathways. We introduce Quantum Interaction Manifolds (QIMs), a theoretical framework that represents gene expression profiles as quantumstates evolved under biologically informed Hamiltonians. We show that QIM embeddings induce hypothesisclasses that cannot be efficiently approximated by classical learners under standard complexity assumptions,providing a principled quantum advantage in representing nonlinear genomic dependencies. Using noisysimulations on reduced-dimensional datasets, we demonstrate that QIM-based quantum kernels achievecompetitive accuracy in cancer classification tasks, while variational quantum models trained on QIMrepresentations learn continuous drug response signals with stable convergence. Together, these results establish QIMs as a quantum-native approach for modeling genomic interactions and highlight the potentialof structured quantum machine learning to support future developments in computational oncology

•Dec 31, 2025•0 citations

Quantum-Enhanced AI for Genomic Medicine

Shakila Basheer

By facilitating quicker and more precise analysis of intricate biological data, the union of quantum computing and Artificial Intelligence (AI) may transform genomic medicine and drug discovery altogether. The study suggests a model for artificial intelligence with quantum-enhanced acceleration based on hybrid quantum-classical models in order to speed up drug discovery and customize therapies. It utilizes deep learning models and Quantum Machine Learning (QML) techniques to analyze patient-specific data, protein structures, and genetic sequences. Large genomic and clinical data sets are processed by conventional deep learning models, while the quantum component carries out efficient data encoding and optimization processes. As compared to other traditional AI-based approaches, the proposed model performs a 30% improved drug target identification when evaluated against more than 1,000 genetic sequences and related clinical outcomes. The hybrid model was as accurate as 98.4% in its prediction and was more accurate than the conventional AI techniques including random forests (accuracy: 91.3%) and gradient boosting machines (accuracy: 93.7%). The methodology also produced an F1-score of 0.95 with accuracy and recall scores of 96.1% and 94.7%, respectively. These results demonstrate how quantum-enhanced AI can reduce the time for computation and improve the accuracy of genomic data analysis, driving significant progress toward personalized therapy and drug development.

CRC Press eBooks•Jun 2, 2026•0 citations

Quantum network-based prediction of cancer driver genes

Patrícia Marques, Andreas Wichert, Duarte Magano +1 more

Identification of cancer driver genes is fundamental for the development of targeted therapeutic interventions. The integration of mutational profiles with protein-protein-interaction (PPI) networks offers a promising avenue for their detection [Horn , ; Nourbakhsh , ], but scaling to large network datasets is computationally demanding. Quantum computing offers compact representations and potential complexity reductions. Motivated by the classical method of Gumpinger [], in this work we introduce a supervised quantum framework that combines mutation scores with network topology via a state-preparation scheme we call quantum multiorder moment embedding (QMME). QMME encodes low-order statistical moments over the mutation scores of a node's immediate and second-order neighbors and encodes this information into quantum states. These states are used as inputs to a kernel-based quantum binary classifier that discriminates known driver genes from others. Simulations on an empirical PPI network demonstrate competitive performance, with a 12.6% recall gain over a classical baseline. The pipeline performs explicit quantum state preparation and requires no classical training, enabling an efficient, nearly end-to-end quantum workflow. A brief complexity analysis suggests the approach could achieve a quantum speedup in network-based cancer-gene prediction. This work underscores the potential of supervised quantum-graph-learning frameworks to advance biological discovery.

arXiv:2510.12628•Physical Review A•Apr 20, 2026•1 citation

Application of Quantum Machine Learning in Genomic Data Analysis Using Quantum Support Vector Machines (QSVM)

Anoop Kumar, Wakeel Ahmed, Muzaffar Matchanov +3 more

Quantum computing has reintroduced itself as a breakthrough technology for machine learning, especially in the analysis of massive datasets, especially the genomic ones. The present research focuses on using QML, namely QSVM, to parse sequences, discover features relating to multiple genetic alterations, biomarkers, and gene expression patterns. The data type under consideration, namely genomic data, is high-dimensional and complex, which presents some problems to the computational methods originating from traditional mathematics. QSVM is designed to work with the mathematical foundations of quantum mechanics including superposition and entanglement and for this reason, it solves problems associated with large scale genomic data more efficiently and accurately. The application of QSVM in MEPs confirms its superiority over classical counterparts in classifying gene mutations, clustering of expression profiles or prediction of disease susceptibility. In addition, through feature mapping, QSVM offers better insights into biological information contained on genomic data, as compared to linear correlations. Furthermore, the ability of QML frameworks to expand to fit the increasing amount of data produced by next-generation sequencing technologies is assessed. Leveraging on this research QSVM has been recognised to redefine precision medicine by rapidly diagnosing diseases and providing unique therapeutic options. The results re-echo the potential of QML in transforming CG and promoting future innovations in biomedicine and health.

International Conference on Networks and Cryptology (NETCRYPT)•May 29, 2025•2 citations
Mutations in the TP53 gene are among the most prevalent alterations in human cancers and are known to influence therapeutic responses. Accurate prediction of drug sensitivity based on TP53 mutation profiles remains a major challenge in precision oncology. In this study, we propose a quantum-enhanced framework for genomic classification using Quantum Boltzmann Machines (QBMs) applied to quantum-encoded DNA sequences. Exon 5–8 fragments of TP53 containing both wild-type and clinically relevant mutations were encoded using angle-based quantum rotations and input into a QBM architecture trained to predict binary drug response (sensitive vs resistant) based on half-maximal inhibitory concentration (IC50) thresholds. Simulated results demonstrate that the QBM achieved over 91%\mathbf{9 1 \%}91% accuracy in classifying drug sensitivity, outperforming classical Boltzmann models and revealing interpretable latent features. This work showcases the potential of QBMs in modeling sequence-driven phenotypes and supports their application in biomarker discovery, drug response prediction, and quantum-enabled precision medicine.
Cancer is one of the leading causes of death worldwide. It is caused by various genetic mutations, which makes every instance of the disease unique. Since chemotherapy can have extremely severe side effects, each patient requires a personalized treatment plan. Finding the dosages that maximize the beneficial effects of the drugs and minimize their adverse side effects is vital. Deep neural networks automate and improve drug selection. However, they require a lot of data to be trained on. Therefore, there is a need for machine-learning approaches that require less data. Hybrid quantum neural networks were shown to provide a potential advantage in problems where training data availability is limited. We propose a novel hybrid quantum neural network for drug response prediction based on a combination of convolutional, graph convolutional, and deep quantum neural layers of 8 qubits with 363 layers. We test our model on the reduced Genomics of Drug Sensitivity in Cancer dataset and show that the hybrid quantum model outperforms its classical analog by 15% in predicting IC50 drug effectiveness values. The proposed hybrid quantum machine learning model is a step towards deep quantum data-efficient algorithms with thousands of quantum gates for solving problems in personalized medicine, where data collection is a challenge.
a:2:{s:4:"lang";s:2:"en";s:7:"content";s:1284:" Glioblastoma, one of the most aggressive forms of brain cancer affecting the elderly and children indescriminately requires advanced computational techniques to achieve accurate and efficient classification for improved patient outcomes. This study explores the application of Quantum Boltzmann Machines (QBMs), a quantum-enhanced variant of classical Boltzmann Machines, to classify glioblastoma from multimodal datasets including imaging, spectroscopy, and molecular profiles. QBMs leverage quantum computing’s ability to represent and sample from complex probability distributions, offering a computational advantage in optimizing high-dimensional data. This study demonstrates and presents QBMs and how they may outperform classical models in accuracy and training efficiency, particularly useful for distinguishing glioblastoma from normal and marginal tissues. Preliminary results highlight the potential of quantum-enhanced machine learning to revolutionize cancer diagnostics by enabling faster and more precise classifications. Our future work will involve scaling QBMs to larger datasets, integrating multimodal inputs, and validating performance in clinical workflows, paving the way for quantum technologies in precision oncology. jdavids{at}ic.ac.uk ";}
Abstract Understanding and predicting cancer phenotypes from genomic data requires models capableof capturing high-order interactions among genes and biological pathways. We introduce Quantum Interaction Manifolds (QIMs), a theoretical framework that represents gene expression profiles as quantumstates evolved under biologically informed Hamiltonians. We show that QIM embeddings induce hypothesisclasses that cannot be efficiently approximated by classical learners under standard complexity assumptions,providing a principled quantum advantage in representing nonlinear genomic dependencies. Using noisysimulations on reduced-dimensional datasets, we demonstrate that QIM-based quantum kernels achievecompetitive accuracy in cancer classification tasks, while variational quantum models trained on QIMrepresentations learn continuous drug response signals with stable convergence. Together, these results establish QIMs as a quantum-native approach for modeling genomic interactions and highlight the potentialof structured quantum machine learning to support future developments in computational oncology
By facilitating quicker and more precise analysis of intricate biological data, the union of quantum computing and Artificial Intelligence (AI) may transform genomic medicine and drug discovery altogether. The study suggests a model for artificial intelligence with quantum-enhanced acceleration based on hybrid quantum-classical models in order to speed up drug discovery and customize therapies. It utilizes deep learning models and Quantum Machine Learning (QML) techniques to analyze patient-specific data, protein structures, and genetic sequences. Large genomic and clinical data sets are processed by conventional deep learning models, while the quantum component carries out efficient data encoding and optimization processes. As compared to other traditional AI-based approaches, the proposed model performs a 30% improved drug target identification when evaluated against more than 1,000 genetic sequences and related clinical outcomes. The hybrid model was as accurate as 98.4% in its prediction and was more accurate than the conventional AI techniques including random forests (accuracy: 91.3%) and gradient boosting machines (accuracy: 93.7%). The methodology also produced an F1-score of 0.95 with accuracy and recall scores of 96.1% and 94.7%, respectively. These results demonstrate how quantum-enhanced AI can reduce the time for computation and improve the accuracy of genomic data analysis, driving significant progress toward personalized therapy and drug development.
Identification of cancer driver genes is fundamental for the development of targeted therapeutic interventions. The integration of mutational profiles with protein-protein-interaction (PPI) networks offers a promising avenue for their detection [Horn , ; Nourbakhsh , ], but scaling to large network datasets is computationally demanding. Quantum computing offers compact representations and potential complexity reductions. Motivated by the classical method of Gumpinger [], in this work we introduce a supervised quantum framework that combines mutation scores with network topology via a state-preparation scheme we call quantum multiorder moment embedding (QMME). QMME encodes low-order statistical moments over the mutation scores of a node's immediate and second-order neighbors and encodes this information into quantum states. These states are used as inputs to a kernel-based quantum binary classifier that discriminates known driver genes from others. Simulations on an empirical PPI network demonstrate competitive performance, with a 12.6% recall gain over a classical baseline. The pipeline performs explicit quantum state preparation and requires no classical training, enabling an efficient, nearly end-to-end quantum workflow. A brief complexity analysis suggests the approach could achieve a quantum speedup in network-based cancer-gene prediction. This work underscores the potential of supervised quantum-graph-learning frameworks to advance biological discovery.
Quantum computing has reintroduced itself as a breakthrough technology for machine learning, especially in the analysis of massive datasets, especially the genomic ones. The present research focuses on using QML, namely QSVM, to parse sequences, discover features relating to multiple genetic alterations, biomarkers, and gene expression patterns. The data type under consideration, namely genomic data, is high-dimensional and complex, which presents some problems to the computational methods originating from traditional mathematics. QSVM is designed to work with the mathematical foundations of quantum mechanics including superposition and entanglement and for this reason, it solves problems associated with large scale genomic data more efficiently and accurately. The application of QSVM in MEPs confirms its superiority over classical counterparts in classifying gene mutations, clustering of expression profiles or prediction of disease susceptibility. In addition, through feature mapping, QSVM offers better insights into biological information contained on genomic data, as compared to linear correlations. Furthermore, the ability of QML frameworks to expand to fit the increasing amount of data produced by next-generation sequencing technologies is assessed. Leveraging on this research QSVM has been recognised to redefine precision medicine by rapidly diagnosing diseases and providing unique therapeutic options. The results re-echo the potential of QML in transforming CG and promoting future innovations in biomedicine and health.