QBioFusion-QSAR: Morgan-Anchored Quantum Multiple Kernel Learning for Small-Data Ligand Classification

2026-06-19

AI Summary

This work addresses the challenge of activity cliffs in few-shot quantitative structure–activity relationship (QSAR) modeling by proposing QBiolFusion-QSAR, an auditable quantum multiple kernel learning framework. The method integrates Morgan/Tanimoto fingerprints with quantum fidelity kernels derived from RDKit, Mordred, and Deep-PK, combined with support vector machines and classical descriptor kernels. A match-regularized auditing mechanism is introduced within five-fold cross-validation to identify critical molecular contributions. Evaluated on the PsychLight-A dataset, the approach improves overall accuracy from 0.815 to 0.833 and Matthews correlation coefficient (MCC) from 0.613 to 0.645. Notably, on the activity cliff subset, MCC increases markedly to 0.22, and compounds such as N-Me-5-HT are correctly reclassified from false negatives to true positives, revealing for the first time the corrective role of localized quantum kernels in mitigating activity cliff effects.

Abstract

Small quantitative structure-activity relationship (QSAR) studies are difficult when close molecular analogues have different activity labels. This paper asks whether a quantum kernel can add similarity information to a Morgan/Tanimoto fingerprint model, and which molecules account for the change. QBioFusion-QSAR uses quantum multiple kernel learning (QMKL): a support vector machine combines a Morgan/Tanimoto kernel with a quantum fidelity kernel constructed from fold-local components derived from RDKit and Mordred descriptors and Deep-PK features. Linear and radial basis function descriptor kernels are included as classical controls. On the 54-molecule PsychLight-A benchmark, Morgan/Tanimoto was the strongest single representation. In the primary stratified five-fold evaluation, QMKL increased accuracy from 0.815 to 0.833 and Matthews correlation coefficient (MCC) from 0.613 to 0.645. Matched-regularization auditing attributed the change to N-Me-5-HT and N-Me-tryptamine changing from false-negative to true-positive predictions; activity-cliff subset MCC increased from 0.07 to 0.22. Repeating the five-fold protocol over ten random partitionings showed that learned QMKL did not exceed Morgan/Tanimoto on mean MCC; paired held-out bootstrap intervals for the matched comparison also span zero. These results support QBioFusion-QSAR as an auditable QMKL framework for identifying localized residual quantum-kernel contributions in small-data, activity-cliff-aware ligand classification.

Problem

• QSAR
• activity cliff
• small-data
• ligand classification
• quantum kernel

Innovation

• Quantum Multiple Kernel Learning
• Activity Cliff
• Morgan Fingerprint
• Quantum Fidelity Kernel
• Auditable QSAR