Optimal normalization in quantum-classical hybrid models for anti-cancer drug response prediction

2025-05-15

AI Summary

Quantum–hybrid machine learning (QHML) models for few-shot anticancer drug response prediction suffer from training instability due to suboptimal classical-to-quantum data encoding at the interface. Method: We propose a moderated gradient tanh normalization technique that mitigates neural network output saturation and enhances both the quality and distributional robustness of input data fed into quantum circuits. Contribution/Results: This work is the first to systematically identify and address QHML’s high sensitivity to input distribution characteristics—particularly in gene expression data encoding. Experiments across multi-cancer cell line drug response datasets demonstrate that the normalized QHML model significantly outperforms purely classical deep learning baselines in prediction accuracy, convergence stability, and few-shot generalization capability, thereby validating its efficacy and practical utility in biomedical prediction tasks.

Technology Category

• Machine Learning: Quantum Machine Learning
• Humans and AI: Human-in-the-loop Machine Learning
• Search and Optimization: Learning to Search

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• User Modeling, Personalization and Recommendation: ML for personalized search and recommendations
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Quantum-classical Hybrid Machine Learning (QHML) models are recognized for their robust performance and high generalization ability even for relatively small datasets. These qualities offer unique advantages for anti-cancer drug response prediction, where the number of available samples is typically small. However, such hybrid models appear to be very sensitive to the data encoding used at the interface of a neural network and a quantum circuit, with suboptimal choices leading to stability issues. To address this problem, we propose a novel strategy that uses a normalization function based on a moderated gradient version of the $ anh$. This method transforms the outputs of the neural networks without concentrating them at the extreme value ranges. Our idea was evaluated on a dataset of gene expression and drug response measurements for various cancer cell lines, where we compared the prediction performance of a classical deep learning model and several QHML models. These results confirmed that QHML performed better than the classical models when data was optimally normalized. This study opens up new possibilities for biomedical data analysis using quantum computers.

Problem

• Optimizing data encoding in quantum-classical hybrid models
• Improving anti-cancer drug response prediction accuracy
• Addressing sensitivity issues in hybrid model normalization

Innovation

• Uses quantum-classical hybrid machine learning models
• Implements moderated gradient tanh normalization
• Optimizes data encoding for quantum circuits