Sample-Efficient Adaptation of Drug-Response Models to Patient Tumors under Strong Biological Domain Shift

TL;DR

This paper introduces a staged transfer-learning framework that leverages unsupervised representation learning to improve sample-efficient adaptation of drug-response models from cell lines to patient tumors, addressing the challenge of biological domain shift in precision oncology.

Contribution

It proposes a novel staged transfer-learning approach that separates representation learning from task supervision, enabling more effective adaptation to patient data with limited labeled samples.

Findings

Unsupervised pretraining benefits are significant when adapting to patient tumors with few labels.

The framework achieves faster performance gains during few-shot adaptation.

It maintains comparable accuracy on cell-line benchmarks while improving clinical data adaptation.

Abstract

Predicting drug response in patients from preclinical data remains a major challenge in precision oncology due to the substantial biological gap between in vitro cell lines and patient tumors. Rather than aiming to improve absolute in vitro prediction accuracy, this work examines whether explicitly separating representation learning from task supervision enables more sample-efficient adaptation of drug-response models to patient data under strong biological domain shift. We propose a staged transfer-learning framework in which cellular and drug representations are first learned independently from large collections of unlabeled pharmacogenomic data using autoencoder-based representation learning. These representations are then aligned with drug-response labels on cell-line data and subsequently adapted to patient tumors using few-shot supervision. Through a systematic evaluation spanning in-domain, cross-dataset, and patient-level settings, we show that unsupervised pretraining provides limited benefit when source and target domains overlap substantially, but yields clear gains when adapting to patient tumors with very limited labeled data. In particular, the proposed framework achieves faster performance improvements during few-shot patient-level adaptation while maintaining comparable accuracy to single-phase baselines on standard cell-line benchmarks. Overall, these results demonstrate that learning structured and transferable representations from unlabeled molecular profiles can substantially reduce the amount of clinical supervision required for effective drug-response prediction, offering a practical pathway toward data-efficient preclinical-to-clinical translation.