🤖 AI Summary
Current single-cell drug response prediction models exhibit poor generalizability across heterogeneous domains—including cell lines, patient-derived xenografts (PDXs), and clinical cohorts—and inadequately jointly model responses at both single-cell and patient levels. To address these limitations, we propose scAdaDrug—the first multi-source domain adaptation framework explicitly designed for dual-level (single-cell and patient) drug response prediction. scAdaDrug introduces an importance-aware sample-weighting mechanism and integrates a shared encoder, adversarial domain alignment, and a plug-and-play weight generation module to jointly optimize representation importance and domain invariance. Evaluated on multiple independent single-cell and clinical datasets, scAdaDrug achieves state-of-the-art performance. Ablation studies confirm its ability to capture domain-invariant, biologically meaningful drug response patterns, significantly enhancing cross-domain generalization and biological interpretability.
📝 Abstract
The advancement of single-cell sequencing technology has promoted the generation of a large amount of single-cell transcriptional profiles, providing unprecedented opportunities to identify drug-resistant cell subpopulations within a tumor. However, few studies have focused on drug response prediction at single-cell level, and their performance remains suboptimal. This paper proposed scAdaDrug, a novel multi-source domain adaptation model powered by adaptive importance-aware representation learning to predict drug response of individual cells. We used a shared encoder to extract domain-invariant features related to drug response from multiple source domains by utilizing adversarial domain adaptation. Particularly, we introduced a plug-and-play module to generate importance-aware and mutually independent weights, which could adaptively modulate the latent representation of each sample in element-wise manner between source and target domains. Extensive experimental results showed that our model achieved state-of-the-art performance in predicting drug response on multiple independent datasets, including single-cell datasets derived from both cell lines and patient-derived xenografts (PDX) models, as well as clinical tumor patient cohorts. Moreover, the ablation experiments demonstrated our model effectively captured the underlying patterns determining drug response from multiple source domains.