Exploring Strategies for Personalized Radiation Therapy: Part III Identifying genetic determinants for Radiation Response with Meta Learning

TL;DR

This paper presents a meta learning approach for predicting tumor radiosensitivity from gene expression data, enabling personalized radiation therapy by adapting to individual tumor biology and outperforming static models.

Contribution

It introduces a novel meta learning framework that allows gene importance to vary per sample, addressing limitations of existing static models like RSI.

Findings

Meta learning improves prediction accuracy on unseen samples.

The approach performs well across diverse tumor subtypes.

It uncovers context-dependent gene influence patterns.

Abstract

Radiation response in cancer is shaped by complex, patient specific biology, yet current treatment strategies often rely on uniform dose prescriptions without accounting for tumor heterogeneity. In this study, we introduce a meta learning framework for one-shot prediction of radiosensitivity measured by SF2 using cell line level gene expression data. Unlike the widely used Radiosensitivity Index RSI a rank-based linear model trained on a fixed 10-gene signature, our proposed meta-learned model allows the importance of each gene to vary by sample through fine tuning. This flexibility addresses key limitations of static models like RSI, which assume uniform gene contributions across tumor types and discard expression magnitude and gene gene interactions. Our results show that meta learning offers robust generalization to unseen samples and performs well in tumor subgroups with high radiosensitivity variability, such as adenocarcinoma and large cell carcinoma. By learning transferable structure across tasks while preserving sample specific adaptability, our approach enables rapid adaptation to individual samples, improving predictive accuracy across diverse tumor subtypes while uncovering context dependent patterns of gene influence that may inform personalized therapy.