Skip to content
2000
image of scHDR: A Heterogeneous Network Transfer Learning Model for Predicting Single-Cell Drug Responses

Abstract

Introduction

Single-cell RNA sequencing (scRNA-seq) generates expression data from individual cells, and drug response prediction based on these data can aid in drug therapy at the cell level. Existing methods for predicting single-cell drug responses primarily focus on gene expression, neglecting the complex interactions when drugs act on cells and inadequately integrating cross-domain information. This study proposes scHDR, which integrates multiple types of information based on heterogeneous networks and uses transfer learning to achieve cross-domain prediction of cell drug responses.

Methods

By integrating drug, cell, and gene information from both bulk and single-cell levels into heterogeneous networks, and employing message passing and structure-preserving transfer learning, scHDR predicts single-cell drug responses while maintaining high performance in both domains, with labels in the target domain by default completely unknown during training.

Results

Comparison experiments across six datasets demonstrate that scHDR outperforms other representative models at both the individual cell and cell cluster levels. Ablation and interpretability experiments confirm the critical role of the message passing and transfer learning components, while domain difference analysis and sensitivity experiments examine the effects of domain discrepancy and network size on model performance, respectively. Additionally, scHDR successfully screens drugs for gastric cancer cells, stratifies drug responses in breast cancer cells over time, and captures the overall response of patient cells, identifying corresponding drug response biomarkers and cell response biomarkers. Key chemical structures of drugs and important genes in cells are also calculated based on gradients.

Discussion

This model effectively leverages the strengths of heterogeneous networks and transfer learning to improve the accuracy of single-cell drug response prediction. Its components are well coordinated, enabling cross-domain information transfer. Case study results align with existing evidence, demonstrating excellent performance across multiple tasks.

Conclusion

scHDR provides a novel method for applying complex network modeling to single-cell drug research. Not only does it improve prediction accuracy, but it also offers valuable insights for drug research and precision therapy.

© 2026 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/cbio/10.2174/0115748936401291251010055212
2026-01-08
2026-02-04

  • From This Site

    /content/journals/cbio/10.2174/0115748936401291251010055212
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Lawson D.A. Kessenbrock K. Davis R.T. Pervolarakis N. Werb Z. Tumour heterogeneity and metastasis at single-cell resolution. Nat. Cell Biol. 2018 20 12 1349 1360 10.1038/s41556‑018‑0236‑7 30482943
    [Google Scholar]
  2. Gambardella G. Viscido G. Tumaini B. Isacchi A. Bosotti R. di Bernardo D. A single-cell analysis of breast cancer cell lines to study tumour heterogeneity and drug response. Nat. Commun. 2022 13 1 1714 10.1038/s41467‑022‑29358‑6 35361816
    [Google Scholar]
  3. Zhu Y. Bai L. Ning Z. Deep learning for clustering single-cell RNA-seq data. Curr. Bioinform. 2024 19 3 193 210 10.2174/1574893618666221130094050
    [Google Scholar]
  4. Lim Z.F. Ma P.C. Emerging insights of tumor heterogeneity and drug resistance mechanisms in lung cancer targeted therapy. J. Hematol. Oncol. 2019 12 1 134 10.1186/s13045‑019‑0818‑2 31815659
    [Google Scholar]
  5. Chen J. Wang X. Ma A. Deep transfer learning of cancer drug responses by integrating bulk and single-cell RNA-seq data. Nat. Commun. 2022 13 1 6494 10.1038/s41467‑022‑34277‑7 36310235
    [Google Scholar]
  6. Zheng Z. Chen J. Chen X. Enabling single-cell drug response annotations from bulk RNA-seq using SCAD. Adv. Sci. 2023 10 11 2204113 10.1002/advs.202204113 36762572
    [Google Scholar]
  7. Fustero-Torre C. Jiménez-Santos M.J. García-Martín S. Beyondcell: Targeting cancer therapeutic heterogeneity in single-cell RNA-seq data. Genome Med. 2021 13 1 187 10.1186/s13073‑021‑01001‑x 34911571
    [Google Scholar]
  8. Li L. Zhao T. Hu Y. Ren S. Tian T. Mathematical modelling and bioinformatics analyses of drug resistance for cancer treatment. Curr. Bioinform. 2024 19 3 211 221 10.2174/1574893618666230512141427
    [Google Scholar]
  9. Baptista D. Ferreira P.G. Rocha M. Deep learning for drug response prediction in cancer. Brief. Bioinform. 2021 22 1 360 379 10.1093/bib/bbz171 31950132
    [Google Scholar]
  10. Suphavilai C. Chia S. Sharma A. Predicting heterogeneity in clone-specific therapeutic vulnerabilities using single-cell transcriptomic signatures. Genome Med. 2021 13 1 189 10.1186/s13073‑021‑01000‑y 34915921
    [Google Scholar]
  11. Wu Z. Lawrence P.J. Ma A. Zhu J. Xu D. Ma Q. Single-cell techniques and deep learning in predicting drug response. Trends Pharmacol. Sci. 2020 41 12 1050 1065 10.1016/j.tips.2020.10.004 33153777
    [Google Scholar]
  12. Cao X. Xing L. Ding H. Novel machine learning model for predicting cancer drugs’ susceptibilities and discovering novel treatments. J. Biomed. Inform. 2025 161 104762 10.1016/j.jbi.2024.104762 39674292
    [Google Scholar]
  13. Gerdes H. Casado P. Dokal A. Drug ranking using machine learning systematically predicts the efficacy of anti-cancer drugs. Nat. Commun. 2021 12 1 1850 10.1038/s41467‑021‑22170‑8 33767176
    [Google Scholar]
  14. Ho Y.J. Anaparthy N. Molik D. Single-cell RNA-seq analysis identifies markers of resistance to targeted BRAF inhibitors in melanoma cell populations. Genome Res. 2018 28 9 1353 1363 10.1101/gr.234062.117 30061114
    [Google Scholar]
  15. Sharma A. Cao E.Y. Kumar V. Longitudinal single-cell RNA sequencing of patient-derived primary cells reveals drug-induced infidelity in stem cell hierarchy. Nat. Commun. 2018 9 1 4931 10.1038/s41467‑018‑07261‑3 30467425
    [Google Scholar]
  16. Krivtsov A.V. Evans K. Gadrey J.Y. A Menin-MLL inhibitor induces specific chromatin changes and eradicates disease in models of MLL-rearranged leukemia. Cancer Cell 2019 36 6 660 673.e11 10.1016/j.ccell.2019.11.001 31821784
    [Google Scholar]
  17. Schnepp P.M. Shelley G. Dai J. Single-cell transcriptomics analysis identifies nuclear protein 1 as a regulator of docetaxel resistance in prostate cancer cells. Mol. Cancer Res. 2020 18 9 1290 1301 10.1158/1541‑7786.MCR‑20‑0051 32513898
    [Google Scholar]
  18. Aissa A.F. Islam A.B.M.M.K. Ariss M.M. Single-cell transcriptional changes associated with drug tolerance and response to combination therapies in cancer. Nat. Commun. 2021 12 1 1628 10.1038/s41467‑021‑21884‑z 33712615
    [Google Scholar]
  19. Kuwahara H. Gao X. Analysis of the effects of related fingerprints on molecular similarity using an eigenvalue entropy approach. J. Cheminform. 2021 13 1 27 10.1186/s13321‑021‑00506‑2 33757582
    [Google Scholar]
  20. Govindan G. Nair A.S. Composition, Transition and Distribution (CTD)—a dynamic feature for predictions based on hierarchical structure of cellular sorting. 2011 Annual IEEE India Conference Hyderabad, India 2011 1 6 10.1109/INDCON.2011.6139332
    [Google Scholar]
  21. Davis A.P. Wiegers T.C. Wiegers J. CTD tetramers: a new online tool that computationally links curated chemicals, genes, phenotypes, and diseases to inform molecular mechanisms for environmental health. Toxicol. Sci. 2023 195 2 155 168 10.1093/toxsci/kfad069 37486259
    [Google Scholar]
  22. Kim S. Thiessen P.A. Bolton E.E. PubChem substance and compound databases. Nucleic Acids Res. 2016 44 D1 D1202 D1213 10.1093/nar/gkv951 26400175
    [Google Scholar]
  23. Kosoglu K. Aydin Z. Tuncbag N. Gursoy A. Keskin O. Structural coverage of the human interactome. Brief. Bioinform. 2023 25 1 bbad496 10.1093/bib/bbad496 38180828
    [Google Scholar]
  24. Raimundo F. Vallot C. Vert J.P. Tuning parameters of dimensionality reduction methods for single-cell RNA-seq analysis. Genome Biol. 2020 21 1 212 10.1186/s13059‑020‑02128‑7 32831127
    [Google Scholar]
  25. Paszke A. Gross S. Chintala S. Automatic differentiation in pytorch. 31st Conference on Neural Information Processing Systems. (NIPS 2017), Long Beach, CA, USA.
    [Google Scholar]
  26. Xu Y. Baumgart S.J. Stegmann C.M. Hayat S. MACA: Marker-based automatic cell-type annotation for single-cell expression data. Bioinformatics 2022 38 6 1756 1760 10.1093/bioinformatics/btab840 34935911
    [Google Scholar]
  27. Barretina J. Caponigro G. Stransky N. The cancer cell line encyclopedia enables predictive modelling of anticancer drug sensitivity. Nature 2012 483 7391 603 607 10.1038/nature11003 22460905
    [Google Scholar]
  28. Zhao R. He B. Bie Q. AQP5 complements LGR5 to determine the fates of gastric cancer stem cells through regulating ULK1 ubiquitination. J. Exp. Clin. Cancer Res. 2022 41 1 322 10.1186/s13046‑022‑02532‑w 36372898
    [Google Scholar]
  29. Ben-David U. Siranosian B. Ha G. Genetic and transcriptional evolution alters cancer cell line drug response. Nature 2018 560 7718 325 330 10.1038/s41586‑018‑0409‑3 30089904
    [Google Scholar]
  30. Becht E. McInnes L. Healy J. Dimensionality reduction for visualizing single-cell data using UMAP. Nat. Biotechnol. 2018 10.1038/nbt.4314 30531897
    [Google Scholar]
  31. Opthof T. Comparison of the impact factors of the most-cited cardiovascular journals. Circ. Res. 2019 124 12 1718 1724 10.1161/CIRCRESAHA.119.315249 31170041
    [Google Scholar]
  32. Morrow E.S. Roseweir A. Edwards J. The role of gamma delta T lymphocytes in breast cancer: A review. Transl. Res. 2019 203 88 96 10.1016/j.trsl.2018.08.005 30194922
    [Google Scholar]
  33. Li J. Cao Y. Liu Y. Multiomics profiling reveals the benefits of gamma-delta (γδ) T lymphocytes for improving the tumor microenvironment, immunotherapy efficacy and prognosis in cervical cancer. J. Immunother. Cancer 2024 12 1 e008355 10.1136/jitc‑2023‑008355 38199610
    [Google Scholar]
  34. Knox C. Wilson M. Klinger C.M. DrugBank 6.0: The drugbank knowledgebase for 2024. Nucleic Acids Res. 2024 52 D1 D1265 D1275 10.1093/nar/gkad976 37953279
    [Google Scholar]
  35. Wishart D.S. Guo A. Oler E. HMDB 5.0: The human metabolome database for 2022. Nucleic Acids Res. 2022 50 D1 D622 D631 10.1093/nar/gkab1062 34986597
    [Google Scholar]
  36. Cannon M. Stevenson J. Stahl K. DGIdb 5.0: Rebuilding the drug–gene interaction database for precision medicine and drug discovery platforms. Nucleic Acids Res. 2024 52 D1 D1227 D1235 10.1093/nar/gkad1040 37953380
    [Google Scholar]
  37. Lin H. Liu S. Gao W. Liu H. DDIT3 modulates cancer stemness in gastric cancer by directly regulating CEBPβ. J. Pharm. Pharmacol. 2020 72 6 807 815 10.1111/jphp.13243 32189359
    [Google Scholar]
  38. Okazaki K. Anzawa H. Katsuoka F. Kinoshita K. Sekine H. Motohashi H. CEBPB is required for NRF2-mediated drug resistance in NRF2-activated non-small cell lung cancer cells. J. Biochem. 2022 171 5 567 578 10.1093/jb/mvac013 35137113
    [Google Scholar]
  39. Haghverdi L. Büttner M. Wolf F.A. Buettner F. Theis F.J. Diffusion pseudotime robustly reconstructs lineage branching. Nat. Methods 2016 13 10 845 848 10.1038/nmeth.3971 27571553
    [Google Scholar]
  40. Kozak E.L. Palit S. Miranda-Rodríguez J.R. Epithelial planar bipolarity emerges from notch-mediated asymmetric inhibition of Emx2. Curr. Biol. 2020 30 6 1142 1151.e6 10.1016/j.cub.2020.01.027 32109392
    [Google Scholar]
  41. Wolf F.A. Angerer P. Theis F.J. SCANPY: large-scale single-cell gene expression data analysis. Genome Biol. 2018 19 1 15 10.1186/s13059‑017‑1382‑0 29409532
    [Google Scholar]
  42. Kanehisa M. Furumichi M. Sato Y. Kawashima M. Ishiguro-Watanabe M. KEGG for taxonomy-based analysis of pathways and genomes. Nucleic Acids Res. 2023 51 D1 D587 D592 10.1093/nar/gkac963 36300620
    [Google Scholar]
  43. Lin W. Noel P. Borazanci E.H. Single-cell transcriptome analysis of tumor and stromal compartments of pancreatic ductal adenocarcinoma primary tumors and metastatic lesions. Genome Med. 2020 12 1 80 10.1186/s13073‑020‑00776‑9 32988401
    [Google Scholar]
  44. Qi R Zou Q Trends and potential of machine learning and deep learning in drug study at single-cell level. Research (Wash D C) 2023 6 0050 10.34133/research.0050 36930772
    [Google Scholar]
  45. Ma Q. Xu D. Deep learning shapes single-cell data analysis. Nat. Rev. Mol. Cell Biol. 2022 23 5 303 304 10.1038/s41580‑022‑00466‑x 35197610
    [Google Scholar]
  46. Van de Sande B. Lee J.S. Mutasa-Gottgens E. Applications of single-cell RNA sequencing in drug discovery and development. Nat. Rev. Drug Discov. 2023 22 6 496 520 10.1038/s41573‑023‑00688‑4 37117846
    [Google Scholar]
  47. Ni F. Tang H. Wang C. Berzosertib (VE-822) inhibits gastric cancer cell proliferation via base excision repair system. Cancer Manag. Res. 2019 11 8391 8405 10.2147/CMAR.S217375 31571995
    [Google Scholar]
  48. Kumanishi R. Kadowaki S. Mitani S. Nivolumab versus irinotecan as third- or later-line treatment for advanced gastric cancer: A multi-center retrospective study. Int. J. Clin. Oncol. 2023 28 6 756 763 10.1007/s10147‑023‑02330‑0 36943545
    [Google Scholar]
  49. Pavurala R.B. Heflin A. Suimin Q. Cohn S.M. Leflunomide induced lymphocytic gastritis. Am. J. Gastroenterol. 2021 116 1 S1309 S09 10.14309/01.ajg.0000786248.06214.5b
    [Google Scholar]
  50. Kang H.G. Kim W.J. Kang H.G. Chun K.H. Kim S.J. Galectin-3 Interacts with C/EBPβ and upregulates hyaluronan-mediated motility receptor expression in gastric cancer. Mol. Cancer Res. 2020 18 3 403 413 10.1158/1541‑7786.MCR‑19‑0811 31822520
    [Google Scholar]
  51. Zhang X. Ren D. Guo L. Thymosin beta 10 is a key regulator of tumorigenesis and metastasis and a novel serum marker in breast cancer. Breast Cancer Res. 2017 19 1 15 10.1186/s13058‑016‑0785‑2 28179017
    [Google Scholar]
  52. Niu M. Zhang B. Li L. Targeting HSP90 Inhibits proliferation and induces apoptosis through AKT1/ERK pathway in lung cancer. Front. Pharmacol. 2022 12 724192 10.3389/fphar.2021.724192 35095481
    [Google Scholar]
  53. Liu H. Zhang Z. Huang Y. Plasma HSP90AA1 predicts the risk of breast cancer onset and distant metastasis. Front. Cell Dev. Biol. 2021 9 639596 10.3389/fcell.2021.639596 34109171
    [Google Scholar]
  54. Milani M. Rzymski T. Mellor H.R. The role of ATF4 stabilization and autophagy in resistance of breast cancer cells treated with bortezomib. Cancer Res. 2009 69 10 4415 4423 10.1158/0008‑5472.CAN‑08‑2839 19417138
    [Google Scholar]
  55. Tsai J. Lee J.T. Wang W. Discovery of a selective inhibitor of oncogenic B-Raf kinase with potent antimelanoma activity. Proc. Natl. Acad. Sci. USA 2008 105 8 3041 3046 10.1073/pnas.0711741105 18287029
    [Google Scholar]
/content/journals/cbio/10.2174/0115748936401291251010055212
Loading
scHDR: A Heterogeneous Network Transfer Learning Model for Predicting Single-Cell Drug Responses
Bentham Science Publishers ; https://doi.org/10.2174/0115748936401291251010055212
/content/journals/cbio/10.2174/0115748936401291251010055212
/content/journals/cbio/10.2174/0115748936401291251010055212
Loading

Data & Media loading...

Supplements

Supplementary material is available on the publisher’s website along with the published article.

file format download Download

  • Article Type:     Research Article
Keywords: biomarker ; single-cell ; drug response ; tumor ; Heterogeneous network ; transfer learning ; heterogeneity

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test