{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T19:10:59Z","timestamp":1789672259166,"version":"4.0.1"},"reference-count":52,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T00:00:00Z","timestamp":1755734400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Accurately predicting tumor cell line responses to therapeutic drugs is essential for personalized cancer treatment. Current methods using bulk cell data fail to fully capture tumor heterogeneity and the complex mechanisms underlying treatment responses.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>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 pre-training on bulk cell gene expression data. A multi-head attention mechanism is incorporated to enhance the model's expressive power and prediction accuracy by identifying gene expression patterns linked to drug reactions.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>ATSDP-NET outperforms existing methods in drug response prediction, as demonstrated on four single-cell RNA sequencing datasets. The model showed superior performance across multiple metrics, including recall, ROC, and average precision (AP). It accurately predicted 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 revealed a high correlation between predicted sensitivity gene scores and actual values (R = 0.888, <jats:italic>p<\/jats:italic> &amp;lt; 0.001), while resistance gene scores also showed a significant correlation (R = 0.788, <jats:italic>p<\/jats:italic> &amp;lt; 0.001). The dynamic process of cells transitioning from sensitive to resistant states was visualized using uniform manifold approximation and projection (UMAP).<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>ATSDP-NET identifies critical genes linked to drug responses, confirming 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.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fmed.2025.1631898","type":"journal-article","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T05:29:00Z","timestamp":1755754140000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["A drug response prediction method for single-cell tumors combining attention networks and transfer learning"],"prefix":"10.3389","volume":"12","author":[{"given":"BingWei","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"SiLin","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"ShengZheng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"HaiXia","family":"Long","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"YuChun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,8,21]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"106830","DOI":"10.1016\/j.phrs.2023.106830","article-title":"Machine learning model for anti-cancer drug combinations: analysis, prediction, and validation","volume":"194","author":"Zhou","year":"2023","journal-title":"Pharmacol Res"},{"key":"B2","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1016\/B978-0-443-15336-5.00001-4","article-title":"Pharmacogenomics in cancer","author":"Bhat","year":"2023"},{"key":"B3","doi-asserted-by":"publisher","first-page":"102745","DOI":"10.1016\/j.sbi.2023.102745","article-title":"A review of computational methods for predicting cancer drug response at the single-cell level through integration with bulk RNAseq data","volume":"84","author":"Maeser","year":"2024","journal-title":"Curr Opin Struct Biol"},{"key":"B4","doi-asserted-by":"publisher","first-page":"5378","DOI":"10.1038\/s41467-024-49620-3","article-title":"Deep representation learning of chemical-induced transcriptional profile for phenotype-based drug discovery","volume":"15","author":"Tong","year":"2024","journal-title":"Nat Commun"},{"key":"B5","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1186\/s12929-024-00994-y","article-title":"Scaffold-based 3D cell culture models in cancer research","volume":"31","author":"Abuwatfa","year":"2024","journal-title":"J Biomed Sci"},{"key":"B6","doi-asserted-by":"publisher","first-page":"2209529","DOI":"10.1002\/adma.202209529","article-title":"In response to precision medicine: current subcellular targeting strategies for cancer therapy","volume":"35","author":"Li","year":"2023","journal-title":"Adv Mater"},{"key":"B7","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1016\/j.gendis.2022.11.025","article-title":"Cancer cell cycle heterogeneity as a critical determinant of therapeutic resistance","volume":"11","author":"Maleki","year":"2024","journal-title":"Genes Dis"},{"key":"B8","doi-asserted-by":"publisher","first-page":"115077","DOI":"10.1016\/j.biopha.2023.115077","article-title":"Deep learning applications in single-cell genomics and transcriptomics data analysis","volume":"165","author":"Erfanian","year":"2023","journal-title":"Biomed Pharmacother"},{"key":"B9","doi-asserted-by":"publisher","first-page":"0050","DOI":"10.34133\/research.0050","article-title":"Trends and potential of machine learning and deep learning in drug study at single-cell level","volume":"6","author":"Qi","year":"2023","journal-title":"Research"},{"key":"B10","doi-asserted-by":"publisher","first-page":"106939","DOI":"10.1016\/j.compbiomed.2023.106939","article-title":"Clustering ensemble in scRNA-seq data analysis: methods, applications and challenges","volume":"159","author":"Nie","year":"2023","journal-title":"Comput Biol Med"},{"key":"B11","doi-asserted-by":"publisher","first-page":"8110486","DOI":"10.1016\/j.isci.2024.110486","article-title":"Applications of single-cell technologies in drug discovery for tumor treatment","volume":"27","author":"Liu","year":"2024","journal-title":"iScience"},{"key":"B12","doi-asserted-by":"publisher","first-page":"353","DOI":"10.3324\/haematol.2022.280800","article-title":"Leukemic stem cells and therapy resistance in acute myeloid leukemia","volume":"108","author":"Stelmach","year":"2023","journal-title":"Haematologica"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1970","DOI":"10.3390\/cells12151970","article-title":"A review of single-cell RNA-Seq annotation, integration, and cell-cell communication","volume":"12","author":"Cheng","year":"2023","journal-title":"Cells"},{"key":"B14","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1186\/s40779-024-00526-7","article-title":"The implications of single-cell RNA-seq analysis in prostate cancer: unraveling tumor heterogeneity, therapeutic implications and pathways towards personalized therapy","volume":"11","author":"Feng","year":"2024","journal-title":"Mil Med Res"},{"key":"B15","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1186\/s13073-023-01256-6","article-title":"Personalized tumor combination therapy optimization using the single-cell transcriptome","volume":"15","author":"Tang","year":"2023","journal-title":"Genome Med"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1086097","DOI":"10.3389\/fmed.2023.1086097","article-title":"Deep learning methods for drug response prediction in cancer: predominant and emerging trends","volume":"10","author":"Partin","year":"2023","journal-title":"Front Med"},{"key":"B17","doi-asserted-by":"publisher","first-page":"2524","DOI":"10.1021\/acs.molpharmaceut.6b00248","article-title":"Deep learning applications for predicting pharmacological properties of drugs and drug repurposing using transcriptomic data","volume":"13","author":"Aliper","year":"2016","journal-title":"Mol Pharm"},{"key":"B18","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1186\/s12859-018-2509-3","article-title":"Predicting tumor cell line response to drug pairs with deep learning","volume":"19","author":"Xia","year":"2018","journal-title":"BMC Bioinformatics"},{"key":"B19","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1186\/s12920-018-0460-9","article-title":"Predicting drug response of tumors from integrated genomic profiles by deep neural networks","volume":"12","author":"Chiu","year":"2019","journal-title":"BMC Med Genomics"},{"key":"B20","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1002\/ijc.34671","article-title":"Age at diagnosis for lung, colon, breast and prostate cancers: an international comparative study","volume":"154","author":"Zahed","year":"2024","journal-title":"Int J Cancer"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on transfer learning","volume":"22","author":"Pan","year":"2009","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"B22","first-page":"270","article-title":"A survey on deep transfer learning","volume-title":"Proceedings of the International Conference on Artificial Neural Networks (ICANN 2018). vol. 11141 of Lecture Notes in Computer Science","author":"Tan","year":"2018"},{"key":"B23","doi-asserted-by":"publisher","first-page":"18040","DOI":"10.1038\/s41598-020-74921-0","article-title":"Ensemble transfer learning for the prediction of anti-cancer drug response","volume":"10","author":"Zhu","year":"2020","journal-title":"Sci Rep"},{"key":"B24","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/JPROC.2020.3004555","article-title":"A comprehensive survey on transfer learning","volume":"109","author":"Zhuang","year":"2020","journal-title":"Proc IEEE"},{"key":"B25","doi-asserted-by":"publisher","first-page":"6494","DOI":"10.1038\/s41467-022-34277-7","article-title":"Deep transfer learning of cancer drug responses by integrating bulk and single-cell RNA-seq data","volume":"13","author":"Chen","year":"2022","journal-title":"Nat Commun"},{"key":"B26","doi-asserted-by":"publisher","first-page":"i130","DOI":"10.1093\/bioinformatics\/btae249","article-title":"Transfer learning of condition-specific perturbation in gene interactions improves drug response prediction","volume":"40","author":"Bang","year":"2024","journal-title":"Bioinformatics"},{"key":"B27","unstructured":"Transferring preclinical drug response to patient via tumor heterogeneity-aware alignment and perturbation modeling\n          \n          \n            \n              Sung\n              I\n            \n            \n              Bang\n              D\n            \n            \n              Kim\n              S\n            \n            \n              Lee\n              S\n            \n          \n          Proceedings of the ICLR 2025 Workshop on Machine Learning for Genomics Explorations (TinyPapers Track)\n          \n          2025"},{"key":"B28","doi-asserted-by":"publisher","first-page":"100949","DOI":"10.1016\/j.patter.2024.100949","article-title":"Predicting drug response through tumor deconvolution by cancer cell lines","volume":"5","author":"Hsu","year":"2024","journal-title":"Patterns"},{"key":"B29","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J Artif Intell Res"},{"key":"B30","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1007\/s12539-023-00593-9","article-title":"Drug repositioning based on deep sparse autoencoder and drug-disease similarity","volume":"16","author":"Lei","year":"2024","journal-title":"Interdiscip Sci Comput Life Sci"},{"key":"B31","doi-asserted-by":"publisher","first-page":"bbab503","DOI":"10.1093\/bib\/bbab503","article-title":"ResNet18DNN: prediction approach of drug-induced liver injury by deep neural network with ResNet18","volume":"23","author":"Chen","year":"2022","journal-title":"Brief Bioinform"},{"key":"B32","doi-asserted-by":"publisher","first-page":"bbac100","DOI":"10.1093\/bib\/bbac100","article-title":"DeepTTA: a transformer-based model for predicting cancer drug response","volume":"23","author":"Jiang","year":"2022","journal-title":"Brief Bioinform"},{"key":"B33","doi-asserted-by":"publisher","first-page":"102805","DOI":"10.1016\/j.artmed.2024.102805","article-title":"Drug-disease association prediction based on graph convolution neural network and graph attention network","volume":"150","author":"Yang","year":"2024","journal-title":"Artif Intell Med"},{"key":"B34","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1038\/s41392-023-01480-x","article-title":"Epigenetic regulation in the tumor microenvironment: molecular mechanisms and therapeutic targets","volume":"8","author":"Yang","year":"2023","journal-title":"Signal Transduct Target Ther"},{"key":"B35","doi-asserted-by":"publisher","first-page":"117362","DOI":"10.1016\/j.envres.2023.117362","article-title":"The diverse effects of cisplatin on tumor microenvironment: insights and challenges for the delivery of cisplatin by nanoparticles","volume":"240","author":"Meng","year":"2024","journal-title":"Environ Res"},{"key":"B36","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1038\/s41420-024-01872-0","article-title":"The interplay of mitophagy, autophagy, and apoptosis in cisplatin-induced kidney injury: involvement of ERK signaling pathway","volume":"10","author":"Suman","year":"2024","journal-title":"Cell Death Discov"},{"key":"B37","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1038\/s41419-024-06891-4","article-title":"The eEF2 kinase coordinates the DNA damage response to cisplatin by supporting p53 activation","volume":"15","author":"Lim","year":"2024","journal-title":"Cell Death Dis"},{"key":"B38","doi-asserted-by":"publisher","first-page":"1666","DOI":"10.1158\/0008-5472.CAN-22-2233","article-title":"NAT10 drives cisplatin chemoresistance by enhancing ac4C-associated DNA repair in bladder cancer","volume":"83","author":"Xie","year":"2023","journal-title":"Cancer Res"},{"key":"B39","doi-asserted-by":"publisher","first-page":"2230","DOI":"10.1038\/s41401-023-01122-6","article-title":"Inhibition of TMEM16A improves cisplatin-induced acute kidney injury via preventing DRP1-mediated mitochondrial fission","volume":"44","author":"Li","year":"2023","journal-title":"Acta Pharmacologica Sinica"},{"key":"B40","doi-asserted-by":"publisher","first-page":"847","DOI":"10.1080\/10643389.2022.2094693","article-title":"Antibiotics and antibiotic resistance genes in agricultural soils: a systematic analysis","volume":"53","author":"Wu","year":"2023","journal-title":"Crit Rev Environ Sci Technol"},{"key":"B41","doi-asserted-by":"publisher","first-page":"10","DOI":"10.21203\/rs.3.rs-2695265\/v1","article-title":"Identification of key genes associated with breast cancer radiotherapy sensitivity based on the stromal-immune score and analysis of the WGCNA and ceRNA network","author":"Sun","year":"2023"},{"key":"B42","doi-asserted-by":"publisher","first-page":"6236","DOI":"10.1038\/s44318-024-00306-y","article-title":"ZBTB48 is a priming factor regulating B-cell-specific CIITA expression","volume":"43","author":"Rane","year":"2024","journal-title":"EMBO J"},{"key":"B43","doi-asserted-by":"publisher","first-page":"256","DOI":"10.3390\/cells12020256","article-title":"NEK6 regulates redox balance and DNA damage response in DU-145 prostate cancer cells","volume":"12","author":"Pavan","year":"2023","journal-title":"Cells"},{"key":"B44","doi-asserted-by":"publisher","first-page":"2496","DOI":"10.1016\/j.jid.2020.04.003","article-title":"FBXO25 promotes cutaneous squamous cell carcinoma growth and metastasis through cyclin D1","volume":"140","author":"Kuzmanov","year":"2020","journal-title":"J Invest Dermatol"},{"key":"B45","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1038\/s41416-021-01516-5","article-title":"UCHL1 as a novel target in breast cancer: emerging insights from cell and chemical biology","volume":"126","author":"Mondal","year":"2022","journal-title":"Br J Cancer"},{"key":"B46","doi-asserted-by":"publisher","first-page":"6696198","DOI":"10.1155\/2021\/6696198","article-title":"Identified GNGT1 and NMU as combined diagnosis biomarker of non-small-cell lung cancer utilizing bioinformatics and logistic regression","volume":"2021","author":"Zhang","year":"2021","journal-title":"Dis Markers"},{"key":"B47","doi-asserted-by":"publisher","first-page":"1493","DOI":"10.1158\/2326-6066.CIR-23-0171","article-title":"EDIL3 as an angiogenic target of immune exclusion following checkpoint blockade","volume":"11","author":"Tabasum","year":"2023","journal-title":"Cancer Immunol Res"},{"key":"B48","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1186\/s13059-019-1663-x","article-title":"PAGA: graph abstraction reconciles clustering with trajectory inference through a topology preserving map of single cells","volume":"20","author":"Wolf","year":"2019","journal-title":"Genome Biol"},{"key":"B49","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1038\/nature22794","article-title":"Rare cell variability and drug-induced reprogramming as a mode of cancer drug resistance","volume":"546","author":"Shaffer","year":"2017","journal-title":"Nature"},{"key":"B50","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.cell.2010.02.027","article-title":"A chromatin-mediated reversible drug-tolerant state in cancer cell subpopulations","volume":"141","author":"Sharma","year":"2010","journal-title":"Cell"},{"key":"B51","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1186\/s13073-021-01001-x","article-title":"Beyondcell: targeting cancer therapeutic heterogeneity in single-cell RNA-seq data","volume":"13","author":"Fustero-Torre","year":"2021","journal-title":"Genome Med"},{"key":"B52","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1186\/s13073-021-01000-y","article-title":"Predicting heterogeneity in clone-specific therapeutic vulnerabilities using single-cell transcriptomic signatures","volume":"13","author":"Suphavilai","year":"2021","journal-title":"Genome Med"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1631898\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T05:29:01Z","timestamp":1755754141000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1631898\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,21]]},"references-count":52,"alternative-id":["10.3389\/fmed.2025.1631898"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2025.1631898","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,21]]},"article-number":"1631898"}}