ORIGINAL RESEARCH article
Front. Med.
Sec. Precision Medicine
Volume 12 - 2025 | doi: 10.3389/fmed.2025.1631898
A drug response prediction method for single-cell tumors combining attention networks and transfer learning
Provisionally accepted
- Hainan Normal University, Haikou, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Accurately predicting tumor cell line responses to therapeutic drugs is essential for personalized cancer treatment. Current approaches using bulk cell data fail to fully capture tumor heterogeneity and the complex mechanisms underlying treatment responses.This study introduces a novel method, ATSDP-NET (Attention-based Transfer Learning for Enhanced Single-cell Drug Response Prediction), which combines bulk and single-cell data. The model utilizes transfer learning and attention networks to predict drug responses in single-cell tumor data, after pretraining on bulk cell gene expression data. A multi-head attention mechanism enhances the model's expressive power and prediction accuracy by identifying gene expression patterns linked to drug reactions.ATSDP-NET outperforms existing methods in drug response prediction, as demonstrated on four single-cell RNA sequencing datasets. The model achieved superior performance across multiple metrics, including recall, ROC, and average precision (AP). It accurately predicted both the sensitivity and resistance of mouse acute myeloid leukemia cells to I-BET-762 and the sensitivity and resistance of human oral squamous cell carcinoma cells to cisplatin. Correlation analysis showed a high correlation between predicted sensitivity gene scores and actual values (R = 0.888, p < 0.001), while resistance gene scores also showed a significant correlation (R = 0.788, p < 0.001). Additionally, ATSDP-NET visualized the dynamic process of cells transitioning from sensitive to resistant states using uniform manifold approximation and projection (UMAP).ATSDP-NET identifies critical genes linked to drug responses and confirms the correctness of its predictions through differential gene expression scores and gene expression patterns. This method provides valuable insights into the mechanisms of drug resistance and offers potential for developing personalized treatment strategies.
Keywords: tumor drug response prediction, attention mechanism, Transfer Learning, Bulk RNA sequencing, single-cell RNA sequencing
Received: 20 May 2025; Accepted: 22 Jul 2025.
Copyright: © 2025 Zhou, Sun, Liu, Long and Li. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
HaiXia Long, Hainan Normal University, Haikou, China
YuChun Li, Hainan Normal University, Haikou, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.