Q-Score: A Quantum-Native Scoring Function for Molecular Docking
Abstract
Molecular docking predicts how a small molecule binds to a protein and is a key bottleneck in drug discovery. Classical scoring functions sum empirical pairwise contacts, blind to quantum-mechanical effects like orbital charge transfer that govern binding specificity. We introduce Q-Score, encoding GNN-predicted orbital donor-acceptor energies into a weighted graph and scoring binding by solving a maximum-weight vertex clique problem via Digitized-Counterdiabatic QAOA. Each interaction anchor maps to one qubit and compatibility constraints become edges. Across 11 protein targets, DC-QAOA recovers the exact optimum on 8 at 10 qubits. On 1000 AI-generated molecules, Q-Score is orthogonal to classical scoring with Spearman rho of 0.05, driven by orbital quality with rho of 0.90, and free of molecular-weight bias, enriching for strong orbital interactions at twice the random rate. DC-QAOA achieves a mean approximation ratio of 0.94 with 52 percent exact. Execution of 1000 circuits on IBM Eagle confirms 6-qubit solvability on NISQ hardware.
Related
- A Machine Learning Approach to logBB Prediction Combining Molecular Docking and Quantum-Chemical Descriptors
- Structure–function relationships in a square-planar Cu(ii) hybrid halometalate: experimental, DFT, molecular docking, optical, and biological studies
- In silico evaluation of novel isosteres against PTPN1 and estrogen receptor alpha: molecular docking, ADMET profiling, and quantum chemical analysis
- Chilean Papaya Bioprospecting for Human α-Glucosidase: Near-Native Pose Recovery in CtMGAM Docking
- PARAM-DOCK: An Integrated Framework for Parallel Multi-Protein–Multi-Ligand Docking and Scoring for Scalable Structure-Based Drug Discovery
BibTeX
@misc{zheng2026qscore,
title = {{Q-Score: A Quantum-Native Scoring Function for Molecular Docking}},
author = {Kangyu Zheng and Yidong Zhou and Ruihao Li and Zixin Ding and Zhiding Liang and Shaohua Li},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2607.09737},
eprint = {2607.09737},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2607.09737},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Q-Score: A Quantum-Native Scoring Function for Molecular Docking
AU - Kangyu Zheng
AU - Yidong Zhou
AU - Ruihao Li
AU - Zixin Ding
AU - Zhiding Liang
AU - Shaohua Li
PY - 2026
DA - 2026/11/03
PB - arXiv
DO - 10.48550/arxiv.2607.09737
UR - https://arxiv.org/abs/2607.09737
AB - Molecular docking predicts how a small molecule binds to a protein and is a key bottleneck in drug discovery. Classical scoring functions sum empirical pairwise contacts, blind to quantum-mechanical effects like orbital charge transfer that govern binding specificity. We introduce Q-Score, encoding GNN-predicted orbital donor-acceptor energies into a weighted graph and scoring binding by solving a maximum-weight vertex clique problem via Digitized-Counterdiabatic QAOA. Each interaction anchor maps to one qubit and compatibility constraints become edges. Across 11 protein targets, DC-QAOA recovers the exact optimum on 8 at 10 qubits. On 1000 AI-generated molecules, Q-Score is orthogonal to classical scoring with Spearman rho of 0.05, driven by orbital quality with rho of 0.90, and free of molecular-weight bias, enriching for strong orbital interactions at twice the random rate. DC-QAOA achieves a mean approximation ratio of 0.94 with 52 percent exact. Execution of 1000 circuits on IBM Eagle confirms 6-qubit solvability on NISQ hardware.
ER -