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

Journal of the American Society for Mass Spectrometry

Quantum Kernel Regression and Variational Quantum Regression for the CCS Prediction of Dissolved Organic Matter: A Comparative Benchmarking Study

Sadollah Ebrahimi, Armand Soldera, Céline Guéguen

Published Sep 10, 2026• 0 citations
Publisher

Abstract

Recent advances in quantum machine learning (QML) offer new opportunities for chemical property prediction, yet their practical performance relative to established classical models remains poorly characterized on real-world datasets. Building on our previous benchmark of classical and deep learning models for collision cross-section (CCS) predictions, we present an empirical comparison of quantum kernel regression (QKR) and a variational quantum regressor (VQR) against classical machine learning (CML) techniques, including Random Forest (RF), support vector regression (SVR), Lasso, and a Voting Regressor (VR) ensemble. Using an aquatic dissolved organic matter (DOM) dataset with five molecular descriptors and five chemical classes, we systematically investigate QKR feature map repetitions and classical readout kernels, as well as VQR circuit depths and optimizer choices, to identify performance-optimal QML configurations. Regression performance is evaluated using the mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R2) across training-set sizes up to 600 molecules per class. Overall, RF and Lasso deliver the most robust CCS predictions, achieving R2 ≥ 0.9 for lignins, carbohydrates, lipids, and proteins. Meanwhile, the optimized QKR architecture exhibits substantial gains as data increase and achieves competitive performance on chemically homogeneous subsets such as carbohydrates and lipids. In contrast, the VQR ansatz remains consistently weaker than both QKR and the classical baselines across all classes and data sizes. The results highlight the strong influence of dataset size, feature representation, and molecular heterogeneity on QML performance while also identifying conditions under which quantum methods may become competitive in future studies.

DOI
10.1021/jasms.6c00135

Related papers

Adapting Quantum Machine Learning for Energy Dissociation of Bonds

Swathi Chandrasekhar, Shiva Raj Pokhrel, Navneet Singh

Accurate prediction of bond dissociation energies (BDEs) underpins mechanistic insight and the rational design of molecules and materials. We present a systematic, reproducible benchmark comparing quantum and classical machine learning models for BDE prediction using a chemically curated feature set encompassing atomic properties (atomic numbers, hybridization), bond characteristics (bond order, type), and local environmental descriptors. Our quantum framework, implemented in Qiskit Aer on six qubits, employs ZZFeatureMap encodings with variational ansätz (RealAmplitudes) across multiple architectures Variational Quantum Regressors (VQR), Quantum Support Vector Regressors (QSVR), Quantum Neural Networks (QNN), Quantum Convolutional Neural Networks (QCNN), and Quantum Random Forests (QRF). These are rigorously benchmarked against strong classical baselines, including Support Vector Regression (SVR), Random Forests (RF), and Multi-Layer Perceptrons (MLP). Comprehensive evaluation spanning absolute and relative error metrics, threshold accuracies, and error distributions shows that top-performing quantum models (QCNN, QRF) match the predictive accuracy and robustness of classical ensembles and deep networks, particularly within the chemically prevalent mid-range BDE regime. These findings establish a transparent baseline for quantum-enhanced molecular property prediction and outline a practical foundation for advancing quantum computational chemistry toward near-chemical accuracy.

arXiv:2510.06563•Sep 25, 2025•4 citations

Beyond Accuracy: A Statistical Benchmarking of Variational Quantum Circuits and Classical Regressors for Molecular Atomization Energy Prediction

Amrita Kundu, Souvik Ghosh, Vegi Fernando A +1 more

The use of quantum machine learning (QML) in computational chemistry has received significant attention as a potential substitute to classical approaches for molecular property prediction. The following paper presents a comparative study of the performance of different quantum circuits and classical techniques for predicting atomization energies based on the QM7 dataset. The molecular structure is mapped to Coulomb matrices, which are then transformed into a flattened vector and truncated into 10 principal components based on Principal Component Analysis (PCA). Three quantum circuit designs have been considered; VQC-1 based on RY gates and ladder entanglement using CNOT gate, VQC-2 based on rotation RX & RZ gates and CNOT gate entanglement, and VQC-3 based on seven layers of strongly entangled gates on ten qubits. The four classical model-based baseline approaches tested are Linear Regression, Support Vector Regression (SVR), Gradient Boosting, and Random Forest. The measures used for performance analysis are MAE, RMSE, and$\mathbf{R}^{\mathbf{2}}$. From the experimental analysis, SVR outperforms the other algorithms and gets an$\mathbf{R}^{\mathbf{2}}$of 0.2208, followed by Gradient Boosting and Random Forest, and the quantum-based models perform poorly with near-zero or negative values of$\mathbf{R}^{\mathbf{2}}$. VQC-3 performs best among the quantum models, yielding an$\mathbf{R}^{\mathbf{2}}$value of 0.0380 and demonstrating the advantages of deep entanglement architectures. An analysis of statistical significance using independent t-tests reveals no significant difference between the distributions of errors in VQC-3 and those of the other classical models, reflecting the current shortcomings of variational quantum circuits in solving structured regression problems.

International Conference on Computing, Intelligence, and Application (CIACON)•Jul 1, 2026•0 citations

Variational Quantum Regression for Binding Affinity Prediction: A Hybrid Quantum-Classical Framework with Explainable Molecular Descriptors

Volkan Erol

Predicting drug-target binding affinity with limited training data remains a central challenge in computational drug discovery. We introduce a hybrid quantum-classical framework combining molecular descriptors with variational quantum circuits for interpretable binding affinity prediction. Seven physicochemical descriptors (MW, logP, TPSA, HBD/HBA, rotatable bonds, aromatic rings) were encoded into 6-qubit variational circuits using parameterized rotations and controlled-Z entanglement. Quantum kernels were extracted and used for regression on 1,200 BindingDB molecules across kinase, GPCR, and protease targets, with external validation on 300 ChEMBL compounds. Performance was compared against SVR, random forest, gradient boosting, and neural network baselines using 100-fold bootstrap validation. Variational quantum regression achieved MSE = 0.056 ± 0.009, outperforming SVR by 32% (0.082 ± 0.013), RF by 28%, and GBM by 24%. Quantum advantage was most significant in low-data regimes (n < 500), where VQR maintained R2 > 0.85 versus R2 < 0.72 for classical methods. External validation confirmed generalization (R2 = 0.83). Our Explainable Quantum Pharmacology framework revealed TPSA and logP as dominant predictive features through gradientbased sensitivity analysis, aligning with established medicinal chemistry principles. Quantum kernels provide measurable, chemically interpretable improvements for molecular property prediction in data-limited scenarios. This work demonstrates practical quantum advantage for early-stage drug discovery applications on near-term quantum hardware.

•Oct 20, 2025•1 citation

Predicting Molecular Properties With Quantum Kernels: a Study on the Qm9 Dataset

Sonam Khattar, Harshit Kumawat, Aryan

Predicting molecular properties is a cornerstone of drug discovery, materials science, and quantum chemistry, where accuracy and speed are critical. Classical machine learning mod- els offer rapid predictions but often fail to capture the intricate quantum interactions governing molecular behavior. Our team investigated quantum kernel methods to predict properties of the QM9 dataset, a widely recognized benchmark containing$\mathbf{1 3 4, 0 0 0}$organic molecules with diverse chemical structures. By encoding molecular features into quantum circuits, we mapped classical data into highdimensional Hilbert spaces to enhance prediction accuracy. Our pipeline encompasses data preprocessing, quantum circuit design, model training with support vector regression, and evaluation of ten key molecular properties. The quantum kernel approach delivered promising results, achieving mean absolute errors of 0.13 Debye for dipole moment and 0.08 eV for HOMOLUMO gap, even when executed on noisy quantum devices. This work provides a comprehensive, reproducible pipeline, benchmarks quantum and classical models, and discusses practical challenges, contributing significantly to the field of quantumenhanced computational chemistry.

IEEE International Conference for Women in Innovation, Technology & Entrepreneurship (ICWITE)•Sep 26, 2025•0 citations

Quantum Kernel Learning for Drug Discovery: A Hybrid QSVR and Quantum Kernel-Based Random Forest Approach for Molecular Screening

Rakshath Raj Y, Chelvachezhiyan S N, Praveen S +2 more

Drug discovery requires efficient screening of large molecular libraries to identify promising therapeutic candidates. This work presents a hybrid quantum–classical framework for DPP-4 inhibitor screening using a curated ChEMBL dataset of 3972 molecules. Classical SVR and Random Forest models are first used for broad candidate screening, from which the top 50 molecules are selected for quantum refinement using Quantum Support Vector Regression (QSVR) and a Quantum Kernel Ensemble (QKE). PCA-reduced molecular descriptors are encoded into a quantum feature space and evaluated using fidelity-based quantum kernels, while XGBoost, LightGBM, and MLP Regression are included as additional comparative baselines. Experimental results show that Random Forest achieves the best classical baseline performance with MAE = 0.7735, RMSE = 1.0655, and R2= 0.3625, while QKE achieves MAE = 0.5642, RMSE = 0.7494, and R2= 0.5369 during quantum refinement. The QSVR-selected molecule CHEMBL2063040 exhibits IC50= 0.3 nM with docking affinity of −4.258 kcal/mol, whereas the QKE-selected molecule CHEMBL2069852 exhibits IC50= 91.5 nM and stronger docking affinity of −11.68 kcal/mol. These results support quantum-kernel learning as a focused refinement mechanism in hybrid molecular screening.

IEEE Region 10 Symposium (TENSYMP)•Jun 1, 2026•0 citations

Why Classical-Quantum Machine Learning Works Better Than Classical Machine Learning

Abdullah Md Raihan Chy, Md. Farhan Shahriyar

Quantum machine learning has emerged as a promising paradigm that leverages quantum computational principles to potentially outperform classical approaches on specific learning tasks. This paper presents a comprehensive empirical investigation comparing Quantum Machine Learning (QML), specifically Quantum Support Vector Machines (QSVM) against Classical Machine Learning (CML) baselines including Logistic Regression, K Nearest Neighbors and classical SVMs. We implement quantum kernel methods using variational quantum circuits with angle embedding, IQP and ZZ feature maps on datasets exhibiting varying structural complexity. Our experiments on synthetic quantum generated datasets (Quantum Parity, Quantum Entanglement, Quantum Interference) demonstrate that QSVM achieves superior classification accuracy with improvements ranging from 2.9 % to 60 % over the best classical baselines achieving a 55.6 % overall win rate. Notably, on the Quantum Parity dataset, QSVM consistently outperformed all classical models across multiple configurations. On real-world benchmark datasets (Breast Cancer, Iris, Wine), QSVM Angle achieved 88% accuracy on Breast Cancer compared to 76% for classical SVM Linear a 15.8 % relative improvement while matching the best classical performance on Iris$(100 \%)$and Wine$(92 \%)$. All experiments were conducted using quantum circuit simulation on classical hardware. These results provide empirical evidence that quantum kernel methods offer meaningful advantages over classical approaches on datasets with complex feature interactions. We discuss the theoretical foundations of these improvements including quantum feature space expressivity and kernel alignment.

IEEE International Conference on Quantum Photonics, Artificial Intelligence & Networking (QPAIN)•Apr 16, 2026•1 citation
Recent advances in quantum machine learning (QML) offer new opportunities for chemical property prediction, yet their practical performance relative to established classical models remains poorly characterized on real-world datasets. Building on our previous benchmark of classical and deep learning models for collision cross-section (CCS) predictions, we present an empirical comparison of quantum kernel regression (QKR) and a variational quantum regressor (VQR) against classical machine learning (CML) techniques, including Random Forest (RF), support vector regression (SVR), Lasso, and a Voting Regressor (VR) ensemble. Using an aquatic dissolved organic matter (DOM) dataset with five molecular descriptors and five chemical classes, we systematically investigate QKR feature map repetitions and classical readout kernels, as well as VQR circuit depths and optimizer choices, to identify performance-optimal QML configurations. Regression performance is evaluated using the mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R2) across training-set sizes up to 600 molecules per class. Overall, RF and Lasso deliver the most robust CCS predictions, achieving R2 ≥ 0.9 for lignins, carbohydrates, lipids, and proteins. Meanwhile, the optimized QKR architecture exhibits substantial gains as data increase and achieves competitive performance on chemically homogeneous subsets such as carbohydrates and lipids. In contrast, the VQR ansatz remains consistently weaker than both QKR and the classical baselines across all classes and data sizes. The results highlight the strong influence of dataset size, feature representation, and molecular heterogeneity on QML performance while also identifying conditions under which quantum methods may become competitive in future studies.
Accurate prediction of bond dissociation energies (BDEs) underpins mechanistic insight and the rational design of molecules and materials. We present a systematic, reproducible benchmark comparing quantum and classical machine learning models for BDE prediction using a chemically curated feature set encompassing atomic properties (atomic numbers, hybridization), bond characteristics (bond order, type), and local environmental descriptors. Our quantum framework, implemented in Qiskit Aer on six qubits, employs ZZFeatureMap encodings with variational ansätz (RealAmplitudes) across multiple architectures Variational Quantum Regressors (VQR), Quantum Support Vector Regressors (QSVR), Quantum Neural Networks (QNN), Quantum Convolutional Neural Networks (QCNN), and Quantum Random Forests (QRF). These are rigorously benchmarked against strong classical baselines, including Support Vector Regression (SVR), Random Forests (RF), and Multi-Layer Perceptrons (MLP). Comprehensive evaluation spanning absolute and relative error metrics, threshold accuracies, and error distributions shows that top-performing quantum models (QCNN, QRF) match the predictive accuracy and robustness of classical ensembles and deep networks, particularly within the chemically prevalent mid-range BDE regime. These findings establish a transparent baseline for quantum-enhanced molecular property prediction and outline a practical foundation for advancing quantum computational chemistry toward near-chemical accuracy.
The use of quantum machine learning (QML) in computational chemistry has received significant attention as a potential substitute to classical approaches for molecular property prediction. The following paper presents a comparative study of the performance of different quantum circuits and classical techniques for predicting atomization energies based on the QM7 dataset. The molecular structure is mapped to Coulomb matrices, which are then transformed into a flattened vector and truncated into 10 principal components based on Principal Component Analysis (PCA). Three quantum circuit designs have been considered; VQC-1 based on RY gates and ladder entanglement using CNOT gate, VQC-2 based on rotation RX & RZ gates and CNOT gate entanglement, and VQC-3 based on seven layers of strongly entangled gates on ten qubits. The four classical model-based baseline approaches tested are Linear Regression, Support Vector Regression (SVR), Gradient Boosting, and Random Forest. The measures used for performance analysis are MAE, RMSE, andR2\mathbf{R}^{\mathbf{2}}R2. From the experimental analysis, SVR outperforms the other algorithms and gets anR2\mathbf{R}^{\mathbf{2}}R2of 0.2208, followed by Gradient Boosting and Random Forest, and the quantum-based models perform poorly with near-zero or negative values ofR2\mathbf{R}^{\mathbf{2}}R2. VQC-3 performs best among the quantum models, yielding anR2\mathbf{R}^{\mathbf{2}}R2value of 0.0380 and demonstrating the advantages of deep entanglement architectures. An analysis of statistical significance using independent t-tests reveals no significant difference between the distributions of errors in VQC-3 and those of the other classical models, reflecting the current shortcomings of variational quantum circuits in solving structured regression problems.
Predicting drug-target binding affinity with limited training data remains a central challenge in computational drug discovery. We introduce a hybrid quantum-classical framework combining molecular descriptors with variational quantum circuits for interpretable binding affinity prediction. Seven physicochemical descriptors (MW, logP, TPSA, HBD/HBA, rotatable bonds, aromatic rings) were encoded into 6-qubit variational circuits using parameterized rotations and controlled-Z entanglement. Quantum kernels were extracted and used for regression on 1,200 BindingDB molecules across kinase, GPCR, and protease targets, with external validation on 300 ChEMBL compounds. Performance was compared against SVR, random forest, gradient boosting, and neural network baselines using 100-fold bootstrap validation. Variational quantum regression achieved MSE = 0.056 ± 0.009, outperforming SVR by 32% (0.082 ± 0.013), RF by 28%, and GBM by 24%. Quantum advantage was most significant in low-data regimes (n < 500), where VQR maintained R2 > 0.85 versus R2 < 0.72 for classical methods. External validation confirmed generalization (R2 = 0.83). Our Explainable Quantum Pharmacology framework revealed TPSA and logP as dominant predictive features through gradientbased sensitivity analysis, aligning with established medicinal chemistry principles. Quantum kernels provide measurable, chemically interpretable improvements for molecular property prediction in data-limited scenarios. This work demonstrates practical quantum advantage for early-stage drug discovery applications on near-term quantum hardware.
Predicting molecular properties is a cornerstone of drug discovery, materials science, and quantum chemistry, where accuracy and speed are critical. Classical machine learning mod- els offer rapid predictions but often fail to capture the intricate quantum interactions governing molecular behavior. Our team investigated quantum kernel methods to predict properties of the QM9 dataset, a widely recognized benchmark containing134,000\mathbf{1 3 4, 0 0 0}134,000organic molecules with diverse chemical structures. By encoding molecular features into quantum circuits, we mapped classical data into highdimensional Hilbert spaces to enhance prediction accuracy. Our pipeline encompasses data preprocessing, quantum circuit design, model training with support vector regression, and evaluation of ten key molecular properties. The quantum kernel approach delivered promising results, achieving mean absolute errors of 0.13 Debye for dipole moment and 0.08 eV for HOMOLUMO gap, even when executed on noisy quantum devices. This work provides a comprehensive, reproducible pipeline, benchmarks quantum and classical models, and discusses practical challenges, contributing significantly to the field of quantumenhanced computational chemistry.
Drug discovery requires efficient screening of large molecular libraries to identify promising therapeutic candidates. This work presents a hybrid quantum–classical framework for DPP-4 inhibitor screening using a curated ChEMBL dataset of 3972 molecules. Classical SVR and Random Forest models are first used for broad candidate screening, from which the top 50 molecules are selected for quantum refinement using Quantum Support Vector Regression (QSVR) and a Quantum Kernel Ensemble (QKE). PCA-reduced molecular descriptors are encoded into a quantum feature space and evaluated using fidelity-based quantum kernels, while XGBoost, LightGBM, and MLP Regression are included as additional comparative baselines. Experimental results show that Random Forest achieves the best classical baseline performance with MAE = 0.7735, RMSE = 1.0655, and R2= 0.3625, while QKE achieves MAE = 0.5642, RMSE = 0.7494, and R2= 0.5369 during quantum refinement. The QSVR-selected molecule CHEMBL2063040 exhibits IC50= 0.3 nM with docking affinity of −4.258 kcal/mol, whereas the QKE-selected molecule CHEMBL2069852 exhibits IC50= 91.5 nM and stronger docking affinity of −11.68 kcal/mol. These results support quantum-kernel learning as a focused refinement mechanism in hybrid molecular screening.
Quantum machine learning has emerged as a promising paradigm that leverages quantum computational principles to potentially outperform classical approaches on specific learning tasks. This paper presents a comprehensive empirical investigation comparing Quantum Machine Learning (QML), specifically Quantum Support Vector Machines (QSVM) against Classical Machine Learning (CML) baselines including Logistic Regression, K Nearest Neighbors and classical SVMs. We implement quantum kernel methods using variational quantum circuits with angle embedding, IQP and ZZ feature maps on datasets exhibiting varying structural complexity. Our experiments on synthetic quantum generated datasets (Quantum Parity, Quantum Entanglement, Quantum Interference) demonstrate that QSVM achieves superior classification accuracy with improvements ranging from 2.9 % to 60 % over the best classical baselines achieving a 55.6 % overall win rate. Notably, on the Quantum Parity dataset, QSVM consistently outperformed all classical models across multiple configurations. On real-world benchmark datasets (Breast Cancer, Iris, Wine), QSVM Angle achieved 88% accuracy on Breast Cancer compared to 76% for classical SVM Linear a 15.8 % relative improvement while matching the best classical performance on Iris(100%)(100 \%)(100%)and Wine(92%)(92 \%)(92%). All experiments were conducted using quantum circuit simulation on classical hardware. These results provide empirical evidence that quantum kernel methods offer meaningful advantages over classical approaches on datasets with complex feature interactions. We discuss the theoretical foundations of these improvements including quantum feature space expressivity and kernel alignment.