Quantum Machine Learning for Drug–Target Interaction Prediction: A Hybrid Variational Circuit Approach on NISQ Hardware
Computer and Decision Making: An International Journal · 04.11.2026 · 3 (6S) · 1468-1489
DOI: 10.1922/comdem.v3i6s.18924 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer and Decision Making: An International Journal, online erschienen am 04.11.2026. Verfasst von Cherukuri Anusha und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Large compound libraries are reduced to candidate’s worth testing by computational prediction of drug-target interactions (DTI). We investigate whether this effort is aided by variational quantum circuits appropriate for noisy intermediate-scale quantum (NISQ) devices. Our hybrid model uses classical networks to encode ECFP4 fingerprints and protein sequence descriptors, compresses them to eight rotation angles, and then processes them using a four-layer hardware-efficient circuit that is read out using local Pauli-Z expectations. Realistic noise models are used to simulate the circuits, and it is trained end-to-end using gradients that match the parameter-shift algorithm. The model achieved test AUROCs of 0.896, 0.892, 0.911, and 0.878 on Davis, KIBA, BindingDB, and BIOSNAP. These results outperform a kernel SVM and logistic regression, although they lag behind a graph network on three datasets, a deep network (0.915–0.927), and gradient-boosted trees. Removing entanglement had little effect on the performance of a parameter-matched classical head, and no low-data advantage emerged. Hardware tolerance was demonstrated by the circuit itself. Because ranking is invariant to uniform noise attenuation, local readout avoided barren plateaus, 256 shots were sufficient, and 1% two-qubit error cost only 0.0025 AUROC. Calibration was recovered by recalibrating the reading. Hardware training costs, not noise, are the binding restriction. For drug-screening decisions, these predictions provide an evidence-based ranking of candidate compound–target pairs for experimental follow-up. The comparison with classical methods indicates whether adding a quantum circuit is justified by the resulting predictive performance and computational cost.
Zitieren
APA
Anusha, C., Radha, D. D., Sailaja, M., Ratnamala, B., & B.Giridhar (2026). Quantum Machine Learning for Drug–Target Interaction Prediction: A Hybrid Variational Circuit Approach on NISQ Hardware. Computer and Decision Making: An International Journal, 3(6S), 1468-1489. https://doi.org/10.1922/comdem.v3i6s.18924
Vancouver
Anusha C, Radha DD, Sailaja M, Ratnamala B, B.Giridhar. Quantum Machine Learning for Drug–Target Interaction Prediction: A Hybrid Variational Circuit Approach on NISQ Hardware. Computer and Decision Making: An International Journal. 2026;3(6S):1468-1489. doi:10.1922/comdem.v3i6s.18924
BibTeX
@article{Anusha2026,
author = {Anusha, Cherukuri and Radha, Dr. D. and Sailaja, Mattaparthi and Ratnamala, B. and B.Giridhar},
title = {Quantum Machine Learning for Drug–Target Interaction Prediction: A Hybrid Variational Circuit Approach on NISQ Hardware},
journal = {Computer and Decision Making: An International Journal},
year = {2026},
volume = {3},
number = {6S},
pages = {1468--1489},
doi = {10.1922/comdem.v3i6s.18924}
}
EUVIMED