Saved in:
Bibliographic Details
Main Authors: Ito, Takafumi, Artem, Lysenko, Tsunoda, Tatsuhiko
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.10037
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915287988699136
author Ito, Takafumi
Artem, Lysenko
Tsunoda, Tatsuhiko
author_facet Ito, Takafumi
Artem, Lysenko
Tsunoda, Tatsuhiko
contents 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 $\tanh$. 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_10037
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Optimal normalization in quantum-classical hybrid models for anti-cancer drug response prediction
Ito, Takafumi
Artem, Lysenko
Tsunoda, Tatsuhiko
Machine Learning
Artificial Intelligence
Emerging Technologies
Quantum Physics
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 $\tanh$. 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.
title Optimal normalization in quantum-classical hybrid models for anti-cancer drug response prediction
topic Machine Learning
Artificial Intelligence
Emerging Technologies
Quantum Physics
url https://arxiv.org/abs/2505.10037