Exploring the Effects of Entanglement on Quantum Machine Learning of Pathogen Epitope-Receptor Binding

2026-06-26

AI Summary

This study addresses overfitting and optimization challenges in classifying epitope–receptor binding affinities on noisy intermediate-scale quantum devices by systematically investigating the impact of two-qubit entangling gate count and topology within the feature-mapping stage of parameterized quantum circuits on Embedding-QNN performance. Comparing various feature maps—including non-entangling Z, fully connected ZZ, and nearest-neighbor alternating low- and high-depth ZZ structures—against a classical CNN baseline, the work demonstrates that highly entangling ZZ mappings substantially mitigate overfitting, achieving the lowest training AUAC and the highest test-to-training AUAC ratio while maintaining high test accuracy. These findings highlight entanglement topology as a critical design variable for sparse biological screening tasks.

Abstract

Parameterized quantum circuits (PQCs) provide a flexible substrate for hybrid quantum machine learning (QML), but their practical value on Noisy Intermediate-Scale Quantum (NISQ) devices remains an empirical question, especially because training depth and scale can introduce optimization challenges such as barren plateaus. Here we study how the number and topology of two-qubit entangling gates in the feature-map stage influence a fixed hybrid QNN workflow for classifying strong versus weak epitope-receptor binding in Porcine Reproductive and Respiratory Syndrome (PRRS) vaccine design. The dataset consists of docking-derived binding affinities for N=80 9-mer epitopes, labeled as Strong or Weak binding, and partitioned into training, validation, and test subsets using a 40:30:30 split. We compare a classical CNN benchmark with a hybrid Embedding-QNN architecture under four feature-map configurations: a non-entangling Z feature map, an all-to-all high-entanglement ZZ feature map, and two interleaved nearest-neighbour entanglement patterns of low and high depth. Among the configurations tested, the high-entanglement ZZ feature map is seen to provide the strongest evidence of reduced training-set overfit, with a lower training area under the accuracy curve (AUAC) and the highest test/training AUAC ratio, while preserving competitive test-set accuracy. These results do not establish a general QML advantage, but they suggest that feature-map entanglement topology is a meaningful design variable for sparse biological screening tasks and warrants further evaluation with additional metrics, larger datasets, and noise-aware or hardware-based experiments.

Problem

• Quantum Machine Learning
• Entanglement
• Epitope-Receptor Binding
• Feature Map
• NISQ

Innovation

• entanglement topology
• parameterized quantum circuits
• quantum machine learning
• feature map
• epitope-receptor binding