Drug Response Prediction using Deep Learning Models and Single-Cell Perturbation Data across Pan Cancer Cell Lines
DOI:
https://doi.org/10.54097/rj7r3r25Keywords:
Drugs repurpose, machine learning, transcriptomics, cancer.Abstract
Cancer remains a leading cause of death. Effective treatments remain limited, because of complications during therapies that contribute to poor survival outcomes. Developing new drugs can be expensive and time-consuming. One promising approach is drug repurposing by identifying potent treatments from existing drugs. This study aims at developing an efficient and effective framework for drug efficacy prediction. To achieve this goal, this study first processed publicly available drug perturbation cancer cell line datasets to enhance their usefulness for drug repurposing to cancer, in which this paper integrated perturbed pan cancer cell line gene expression data with their drug responses. This study integrated 10 selected cancer cell line data covering 8 cancers from public databases including CMAP, CTRP, CCLE, and GDSC. Secondly, this study applied advanced machine learning methods, particularly deep learning to learn useful features from these data, and transfer learning to make the predictive models generalized and interpretable. With deep learning and these datasets, this study developed a highly accurate deep neural network framework (DeepDrugCancer) that combines the drug molecular structures and gene expression data of cancer cell lines to predict the drug responsiveness. DeepDrugCancer achieved excellent performance with over 90% AUC test score across multiple cell lines. By integration with scRNA-seq data of breast cancer, predicted drugs such as aminocaproic acid, pancuronium bromide, and pseudopelletierine showed high cell-type specificity. Finally, this study conducted in-vitro (wet lab) experiments to validate the viability of DeepDrugCancer. The model predicted Mifanertinib to be sensitive on breast cancer cell lines and the in-vitro experiments confirmed the trend of such effects. The experiments have demonstrated that this framework efficiently utilizes drug-induced molecular signatures to predict therapeutic responses across certain cancers. By linking transcriptomic perturbations to drug responses, this study advances drug repurposing to expanded therapeutic options for cancer treatments as well as to precision oncology.
Downloads
References
[1] Ahmad, F. B.; Anderson, R. N. The Leading Causes of Death in the US for 2020. JAMA 2021, 325 (18), 1829. https://doi.org/10.1001/jama.2021.5469.
[2] Jaehde, U.; Liekweg, A.; Simons, S.; Westfeld, M. Minimising Treatment-Associated Risks in Systemic Cancer Therapy. Pharm. World Sci. 2008, 30 (2), 161–168. https://doi.org/10.1007/s11096-007-9157-4.
[3] Tanoli, Z.; Vähä-Koskela, M.; Aittokallio, T. Artificial Intelligence, Machine Learning, and Drug Repurposing in Cancer. Expert Opin. Drug Discov. 2021, 16 (9), 977–989. https://doi.org/10.1080/17460441.2021.1883585.
[4] Saranraj, K.; Kiran, P. U. Drug Repurposing: Clinical Practices and Regulatory Pathways. Perspect. Clin. Res. 2025, 16 (2), 61–68. https://doi.org/10.4103/picr.picr_70_24.
[5] Failli, M.; Demir, S.; Del Río-Álvarez, Á.; Carrillo-Reixach, J.; Royo, L.; Domingo-Sàbat, M.; Childs, M.; Maibach, R.; Alaggio, R.; Czauderna, P.; Morland, B.; Branchereau, S.; Cairo, S.; Kappler, R.; Armengol, C.; Di Bernardo, D. Computational Drug Prediction in Hepatoblastoma by Integrating Pan-Cancer Transcriptomics with Pharmacological Response. Hepatology 2024, 80 (1), 55–68. https://doi.org/10.1097/HEP.0000000000000601.
[6] Issa, N. T.; Stathias, V.; Schürer, S.; Dakshanamurthy, S. Machine and Deep Learning Approaches for Cancer Drug Repurposing. Semin. Cancer Biol. 2021, 68, 132–142. https://doi.org/10.1016/j.semcancer.2019.12.011.
[7] Al Khzem, A. H.; Gomaa, M. S.; Alturki, M. S.; Tawfeeq, N.; Sarafroz, M.; Alonaizi, S. M.; Al Faran, A.; Alrumaihi, L. A.; Alansari, F. A.; Alghamdi, A. A. Drug Repurposing for Cancer Treatment: A Comprehensive Review. Int. J. Mol. Sci. 2024, 25 (22), 12441. https://doi.org/10.3390/ijms252212441.
[8] Baptista, D.; Ferreira, P. G.; Rocha, M. Deep Learning for Drug Response Prediction in Cancer. Brief. Bioinform. 2021, 22 (1), 360–379. https://doi.org/10.1093/bib/bbz171.
[9] Yang, W.; Soares, J.; Greninger, P.; Edelman, E. J.; Lightfoot, H.; Forbes, S.; Bindal, N.; Beare, D.; Smith, J. A.; Thompson, I. R.; Ramaswamy, S.; Futreal, P. A.; Haber, D. A.; Stratton, M. R.; Benes, C.; McDermott, U.; Garnett, M. J. Genomics of Drug Sensitivity in Cancer (GDSC): A Resource for Therapeutic Biomarker Discovery in Cancer Cells. Nucleic Acids Res. 2012, 41 (D1), D955–D961. https://doi.org/10.1093/nar/gks1111.
[10] Lamb, J.; Crawford, E. D.; Peck, D.; Modell, J. W.; Blat, I. C.; Wrobel, M. J.; Lerner, J.; Brunet, J.-P.; Subramanian, A.; Ross, K. N.; Reich, M.; Hieronymus, H.; Wei, G.; Armstrong, S. A.; Haggarty, S. J.; Clemons, P. A.; Wei, R.; Carr, S. A.; Lander, E. S.; Golub, T. R. The Connectivity Map: Using Gene-Expression Signatures to Connect Small Molecules, Genes, and Disease. Science 2006, 313 (5795), 1929–1935. https://doi.org/10.1126/science.1132939.
[11] Musa, A.; Ghoraie, L. S.; Zhang, S.-D.; Galzko, G.; Yli-Harja, O.; Dehmer, M.; Haibe-Kains, B.; Emmert-Streib, F. A Review of Connectivity Map and Computational Approaches in Pharmacogenomics. Brief. Bioinform. 2017, bbw112. https://doi.org/10.1093/bib/bbw112.
[12] Barretina, J.; Caponigro, G.; Stransky, N.; Venkatesan, K.; Margolin, A. A.; Kim, S.; J.Wilson, C.; Lehár, J.; Kryukov, G. V.; Sonkin, D.; Reddy, A.; Liu, M.; Murray, L.; Berger, M. F.; Monahan, J. E.; Morais, P.; Meltzer, J.; Korejwa, A.; Jané-Valbuena, J.; Mapa, F. A.; Thibault, J.; Bric-Furlong, E.; Raman, P.; Shipway, A.; Engels, I. H.; Cheng, J.; Yu, G. K.; Yu, J.; Aspesi, P.; De Silva, M.; Jagtap, K.; Jones, M. D.; Wang, L.; Hatton, C.; Palescandolo, E.; Gupta, S.; Mahan, S.; Sougnez, C.; Onofrio, R. C.; Liefeld, T.; MacConaill, L.; Winckler, W.; Reich, M.; Li, N.; Mesirov, J. P.; Gabriel, S. B.; Getz, G.; Ardlie, K.; Chan, V.; Myer, V. E.; Weber, B. L.; Porter, J.; Warmuth, M.; Finan, P.; Harris, J. L.; Meyerson, M.; Golub, T. R.; Morrissey, M. P.; Sellers, W. R.; Schlegel, R.; Garraway, L. A. Addendum: The Cancer Cell Line Encyclopedia Enables Predictive Modelling of Anticancer Drug Sensitivity. Nature 2012, 492 (7428), 290–290. https://doi.org/10.1038/nature11735.
[13] Partin, A.; Brettin, T. S.; Zhu, Y.; Narykov, O.; Clyde, A.; Overbeek, J.; Stevens, R. L. Deep Learning Methods for Drug Response Prediction in Cancer: Predominant and Emerging Trends. Front. Med. 2023, 10, 1086097. https://doi.org/10.3389/fmed.2023.1086097.
[14] Jafari, M.; Tao, X.; Barua, P.; Tan, R.-S.; Acharya, U. R. Application of Transfer Learning for Biomedical Signals: A Comprehensive Review of the Last Decade (2014–2024). Inf. Fusion 2025, 118, 102982. https://doi.org/10.1016/j.inffus.2025.102982.
[15] Zhao, Z.; Alzubaidi, L.; Zhang, J.; Duan, Y.; Gu, Y. A Comparison Review of Transfer Learning and Self-Supervised Learning: Definitions, Applications, Advantages and Limitations. Expert Syst. Appl. 2024, 242, 122807. https://doi.org/10.1016/j.eswa.2023.122807.
[16] Gaudelet, T.; Day, B.; Jamasb, A. R.; Soman, J.; Regep, C.; Liu, G.; Hayter, J. B. R.; Vickers, R.; Roberts, C.; Tang, J.; Roblin, D.; Blundell, T. L.; Bronstein, M. M.; Taylor-King, J. P. Utilizing Graph Machine Learning within Drug Discovery and Development. Brief. Bioinform. 2021, 22 (6), bbab159. https://doi.org/10.1093/bib/bbab159.
[17] Sartori, F.; Codicè, F.; Caranzano, I.; Rollo, C.; Birolo, G.; Fariselli, P.; Pancotti, C. A Comprehensive Review of Deep Learning Applications with Multi-Omics Data in Cancer Research. Genes 2025, 16 (6), 648. https://doi.org/10.3390/genes16060648.
[18] Bunne, C.; Stark, S. G.; Gut, G.; Del Castillo, J. S.; Levesque, M.; Lehmann, K.-V.; Pelkmans, L.; Krause, A.; Rätsch, G. Learning Single-Cell Perturbation Responses Using Neural Optimal Transport. Nat. Methods 2023, 20 (11), 1759–1768. https://doi.org/10.1038/s41592-023-01969-x.
[19] Nyman, E.; Stein, R. R.; Jing, X.; Wang, W.; Marks, B.; Zervantonakis, I. K.; Korkut, A.; Gauthier, N. P.; Sander, C. Perturbation Biology Links Temporal Protein Changes to Drug Responses in a Melanoma Cell Line. PLOS Comput. Biol. 2020, 16 (7), e1007909. https://doi.org/10.1371/journal.pcbi.1007909.
[20] (20) An, X.; Chen, X.; Yi, D.; Li, H.; Guan, Y. Representation of Molecules for Drug Response Prediction. Brief. Bioinform. 2022, 23 (1), bbab393. https://doi.org/10.1093/bib/bbab393.
[21] Zhang, X.; Cha, I.-H.; Kim, K.-Y. Use of a Combined Gene Expression Profile in Implementing a Drug Sensitivity Predictive Model for Breast Cancer. Cancer Res. Treat. 2017, 49 (1), 116–128. https://doi.org/10.4143/crt.2016.085.
[22] Pozdeyev, N.; Yoo, M.; Mackie, R.; Schweppe, R. E.; Tan, A. C.; Haugen, B. R. Integrating Heterogeneous Drug Sensitivity Data from Cancer Pharmacogenomic Studies. Oncotarget 2016, 7 (32), 51619–51625. https://doi.org/10.18632/oncotarget.10010.
[23] Joseph, V. R. Optimal Ratio for Data Splitting. Stat. Anal. Data Min. ASA Data Sci. J. 2022, 15 (4), 531–538. https://doi.org/10.1002/sam.11583.
[24] Jiang, J.; Chen, L.; Ke, L.; Dou, B.; Zhang, C.; Feng, H.; Zhu, Y.; Qiu, H.; Zhang, B.; Wei, G.-W. A Review of Transformer Models in Drug Discovery and Beyond. J. Pharm. Anal. 2025, 15 (6), 101081. https://doi.org/10.1016/j.jpha.2024.101081.
[25] Jiangping, H.; Lihui, L.; Jiekai, C.; Center for Cell Lineage and Atlas (CCLA), Bioland Laboratory (Guangzhou Regenerative Medicine and Health Guangdong Laboratory), Guangzhou 510320, China; Key Laboratory of Regenerative Biology of the Chinese Academy of Sciences and Guangdong Provincial Key Laboratory of Stem Cell and Regenerative Medicine, Guangzhou Institutes of Biomedicine and Health, Chinese Academy of Sciences, Guangzhou 510530, China. Practical Bioinformatics Pipelines for Single-Cell RNA-Seq Data Analysis. Biophys. Rep. 2022, 8 (3), 158–169. https://doi.org/10.52601/bpr.2022.210041.
[26] Xu, Y.; Zhang, Y.; Song, K.; Liu, J.; Zhao, R.; Zhang, X.; Pei, L.; Li, M.; Chen, Z.; Zhang, C.; Wang, P.; Li, F. ScDrugAct: A Comprehensive Database to Dissect Tumor Microenvironment Cell Heterogeneity Contributing to Drug Action and Resistance across Human Cancers. Nucleic Acids Res. 2025, 53 (D1), D1536–D1546. https://doi.org/10.1093/nar/gkae994.
[27] 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. https://doi.org/10.1038/s41467-022-29358-6.
[28] Ali, S.; Abuhmed, T.; El-Sappagh, S.; Muhammad, K.; Alonso-Moral, J. M.; Confalonieri, R.; Guidotti, R.; Del Ser, J.; Díaz-Rodríguez, N.; Herrera, F. Explainable Artificial Intelligence (XAI): What We Know and What Is Left to Attain Trustworthy Artificial Intelligence. Inf. Fusion 2023, 99, 101805. https://doi.org/10.1016/j.inffus.2023.101805.
[29] Schissler, A. G.; Aberasturi, D.; Kenost, C.; Lussier, Y. A. A Single-Subject Method to Detect Pathways Enriched With Alternatively Spliced Genes. Front. Genet. 2019, 10, 414. https://doi.org/10.3389/fgene.2019.00414.
[30] Chen, L.; Chu, C.; Lu, J.; Kong, X.; Huang, T.; Cai, Y.-D. Gene Ontology and KEGG Pathway Enrichment Analysis of a Drug Target-Based Classification System. PLOS ONE 2015, 10 (5), e0126492. https://doi.org/10.1371/journal.pone.0126492.
[31] Ponce‐Bobadilla, A. V.; Schmitt, V.; Maier, C. S.; Mensing, S.; Stodtmann, S. Practical Guide to SHAP Analysis: Explaining Supervised Machine Learning Model Predictions in Drug Development. Clin. Transl. Sci. 2024, 17 (11), e70056. https://doi.org/10.1111/cts.70056.
[32] Opdam, F. L.; Guchelaar, H.-J.; Beijnen, J. H.; Schellens, J. H. M. Lapatinib for Advanced or Metastatic Breast Cancer. The Oncologist 2012, 17 (4), 536–542. https://doi.org/10.1634/theoncologist.2011-0461.
[33] Ding, S.; Chen, X.; Shen, K. Single‐cell RNA Sequencing in Breast Cancer: Understanding Tumor Heterogeneity and Paving Roads to Individualized Therapy. Cancer Commun. 2020, 40 (8), 329–344. https://doi.org/10.1002/cac2.12078.
[34] Dong, S.; Yousefi, H.; Savage, I. V.; Okpechi, S. C.; Wright, M. K.; Matossian, M. D.; Collins-Burow, B. M.; Burow, M. E.; Alahari, S. K. Ceritinib Is a Novel Triple Negative Breast Cancer Therapeutic Agent. Mol. Cancer 2022, 21 (1), 138. https://doi.org/10.1186/s12943-022-01601-0.
[35] Schäkel, L.; Mirza, S.; Winzer, R.; Lopez, V.; Idris, R.; Al-Hroub, H.; Pelletier, J.; Sévigny, J.; Tolosa, E.; Müller, C. E. Protein Kinase Inhibitor Ceritinib Blocks Ectonucleotidase CD39 – a Promising Target for Cancer Immunotherapy. J. Immunother. Cancer 2022, 10 (8), e004660. https://doi.org/10.1136/jitc-2022-004660.
[36] Petrazzuolo, A.; Perez-Lanzon, M.; Liu, P.; Maiuri, M. C.; Kroemer, G. Crizotinib and Ceritinib Trigger Immunogenic Cell Death via On-Target Effects. OncoImmunology 2021, 10 (1), 1973197. https://doi.org/10.1080/2162402X.2021.1973197.
[37] Qiu, S.; Chen, G.; Peng, J.; Liu, J.; Chen, J.; Wang, J.; Li, L.; Yang, K. LncRNA EGOT Decreases Breast Cancer Cell Viability and Migration via Inactivation of the Hedgehog Pathway. FEBS Open Bio 2020, 10 (5), 817–826. https://doi.org/10.1002/2211-5463.12833.
[38] Comşa, Ş.; Cîmpean, A. M.; Raica, M. The Story of MCF-7 Breast Cancer Cell Line: 40 Years of Experience in Research. Anticancer Res. 2015, 35 (6), 3147–3154.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Highlights in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
