利用混合量子-经典神经网络提高肽-HLA结合预测的样本效率
Improving Sample Efficiency in Peptide-HLA Binding Prediction with Hybrid Quantum-Classical Neural Networks
- Shenzhen SpinQ Technology Co., Ltd.（深圳_spinq科技有限公司）
- Shenzhen AIage Puhui Longevity Technology Corporation, Ltd.（深圳爱佳普慧长寿科技有限公司）
- Shien-Ming Wu School of Intelligent Engineering, South China University of Technology（华南理工大学智能工程学院）
- Guangxi Key Laboratory of Longevity Science and Technology, AIage Life Science Corparation Ltd.（广西长寿科学与技术重点实验室，爱佳生命科学公司）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出混合量子-经典神经网络HQNN用于肽-HLA结合预测，通过量子特征提取和分类器在低数据下超越经典CNN，提升样本效率。
AI中文摘要：
肽-HLA结合预测是个性化癌症免疫治疗中新抗原识别的关键步骤，具有重要的临床价值。然而，许多HLA等位基因可用的训练数据极为有限，这严重制约了传统方法在该任务上的性能。参数化量子电路被假设能诱导有利于从小数据集学习的归纳偏置，但其在生物序列预测中的应用仍未得到充分探索。为解决这一问题，我们提出了一种专门用于肽-HLA结合预测的混合量子-经典神经网络（HQNN）。HQNN将多源生物特征编码与并行量子特征提取器及量子增强分类器相结合。在两个HLA等位基因（A*02:01和B*07:02）上，HQNN在所有训练规模下均优于参数匹配的经典CNN基线，且随着训练数据的减少，性能差距逐渐扩大。消融研究证实了量子特征提取模块和量子分类器各自的贡献。在噪声感知模拟中，性能仅轻微下降，且这种下降在现实量子硬件噪声水平下是合理且可接受的。这些结果表明，混合量子-经典架构可以在低数据场景下为免疫信息学任务提供实际的样本效率提升。
英文摘要：
Peptide-HLA binding prediction is a critical step in neoantigen identification for personalized cancer immunotherapy and holds significant clinical value. However, the training data available for many HLA alleles are extremely limited, which severely constrains the performance of conventional methods on this task. Parameterized quantum circuits are hypothesized to induce inductive biases beneficial for learning from small datasets, yet their application to biological sequence prediction remains underexplored. To address this, we propose a hybrid quantum-classical neural network (HQNN) specifically designed for peptide-HLA binding prediction. HQNN integrates multi-source biological feature encoding with parallel quantum feature extractors and a quantum-enhanced classifier. On two HLA alleles (A*02:01 and B*07:02), HQNN outperforms a parameter-matched classical CNN baseline across all training sizes, with the performance gap widening as training data decreases. Ablation studies confirm the respective contributions of the quantum feature extraction module and the quantum classifier. In noise-aware simulations, performance degrades only mildly, and such degradation is reasonable and acceptable under realistic quantum hardware noise levels. These results suggest that hybrid quantum-classical architectures can provide practical sample-efficiency gains for immunoinformatics tasks in low-data regimes.
