Reimagining Drug Potential: Machine Learning As A Catalyst In Drug Repurposing
Abstract
Drug discovery has long been a cornerstone of medical progress, yet the conventional path of developing new therapeutics is notoriously lengthy, costly, and fraught with uncertainty. On average, it requires more than a decade of intensive research, billions of dollars in investment, and multiple phases of preclinical and clinical testing to bring a single novel drug to market. Despite such efforts, the attrition rate remains strikingly high, with only a small fraction of candidates achieving regulatory approval. In this context, drug repurposing, also known as drug repositioning, has emerged as a pragmatic and highly valuable strategy to address unmet medical needs and optimise available therapeutic resources. The history of drug repurposing is deeply embedded in the evolution of modern pharmacology. Early examples demonstrate how serendipitous observations, clinical experiences, and detailed pharmacological studies gave new life to compounds originally designed for unrelated purposes. Aspirin, first introduced as an analgesic and antipyretic, was later recognised for its antiplatelet effects, transforming it into a cornerstone therapy for cardiovascular diseases. Thalidomide, infamous for its teratogenic effects, was subsequently repurposed as an immunomodulatory drug to treat multiple myeloma and leprosy-related complications. Sildenafil, initially developed for angina, gained global recognition when repurposed for erectile dysfunction and later for pulmonary arterial hypertension.
Keywords:
Drug discovery has long been a cornerstone of medical progress, yet the conventional path of developing new therapeutics is notoriously lengthy, costly, and fraught with uncertainty. On average, it requires more than a decade of intensive research, billions of dollars in investment, and multiple phases of preclinical and clinical testing to bring a single novel drug to market. Despite such efforts, the attrition rate remains strikingly high, with only a small fraction of candidates achieving regulatory approval. In this context, drug repurposing, also known as drug repositioning, has emerged as a pragmatic and highly valuable strategy to address unmet medical needs and optimise available therapeutic resources. The history of drug repurposing is deeply embedded in the evolution of modern pharmacology. Early examples demonstrate how serendipitous observations, clinical experiences, and detailed pharmacological studies gave new life to compounds originally designed for unrelated purposes. Aspirin, first introduced as an analgesic and antipyretic, was later recognised for its antiplatelet effects, transforming it into a cornerstone therapy for cardiovascular diseases. Thalidomide, infamous for its teratogenic effects, was subsequently repurposed as an immunomodulatory drug to treat multiple myeloma and leprosy-related complications. Sildenafil, initially developed for angina, gained global recognition when repurposed for erectile dysfunction and later for pulmonary arterial hypertension.
Downloads
References
Machine learning and artificial intelligence have already transformed drug repurposing into a faster, more cost-effective, and more precise approach compared to traditional methods. The future had promised even greater integration of computational models with experimental and clinical pipelines, ultimately delivering more accessible, effective, and personalised therapies for patients worldwide. By overcoming existing challenges and fostering collaborative innovation, ML and AI have been positioned to become indispensable pillars of 21st-century pharmaceutical research
The authors would like to express their heartfelt gratitude to their respected guides and mentors for their invaluable support, encouragement, and constructive feedback throughout the preparation of this review. We sincerely thank our institution for providing access to resources and literature that greatly facilitated this work. Our appreciation also goes to all researchers whose studies have been cited, as their contributions form the backbone of this review. Lastly, we are deeply grateful to our family and friends for their constant motivation and encouragement.
REFERENCES:
Paul, S. M., Mytelka, D. S., Dunwiddie, C. T., Persinger, C. C., Munos, B. H., Lindborg, S. R., & Schacht, A. L. (2010). How to improve R&D productivity: the pharmaceutical industry’s grand challenge. Nature Reviews Drug Discovery, 9(3), 203–214.2q2
DiMasi, J. A., Grabowski, H. G., & Hansen, R. W. (2016). Innovation in the pharmaceutical industry: New estimates of R&D costs. Journal of Health Economics, 47, 20–33.
Pushpakom, S., Iorio, F., Eyers, P. A., Escott, K. J., Hopper, S., Wells, A., ... & Pirmohamed, M. (2019). Drug repurposing: Progress, challenges and recommendations. Nature Reviews Drug Discovery, 18(1), 41–58.
Zhou, Y., Wang, F., Tang, J., Nussinov, R., & Cheng, F. (2020). Artificial intelligence in COVID-19 drug repurposing. The Lancet Digital Health, 2(12), e667–e676.
Ekins, S., Puhl, A. C., Zorn, K. M., Lane, T. R., Russo, D. P., Klein, J. J., ... & Freundlich, J. S. (2019). Exploiting machine learning for end-to-end drug discovery and development. Nature Materials, 18(5), 435–441.
Cao, B., Wang, Y., Wen, D., Liu, W., Wang, J., Fan, G., ... & Wang, C. (2020). A trial of lopinavir–ritonavir in adults hospitalised with severe COVID-19. New England Journal of Medicine, 382(19), 1787–1799.
Li, J., Zheng, S., Chen, B., Butte, A. J., Swamidass, S. J., & Lu, Z. (2021). A survey of current trends in computational drug repositioning. Briefings in Bioinformatics, 22(2), 1232–1241.
Gysi, D. M., Valle, Í. D., Zitnik, M., Ameli, A., Gan, X., Varol, O., ... & Barabási, A. L. (2021). Network medicine framework for identifying drug repurposing opportunities for COVID-19. PNAS, 118(19), e2025581118.
Chen, X., Liu, M. X., & Yan, G. Y. (2016). Drug–target interaction prediction by random walk on the heterogeneous network. Molecular BioSystems, 8(7), 1970–1978.
Yamanishi, Y., Araki, M., Gutteridge, A., Honda, W., & Kanehisa, M. (2008). Prediction of drug–target interaction networks from the integration of chemical and genomic spaces. Bioinformatics, 24(13), i232–i240.
Napolitano, F., Zhao, Y., Moreira, V. M., Tagliaferri, R., Kere, J., D’Amato, M., & Greco, D. (2013). Drug repositioning: a machine-learning approach through data integration. Journal of Cheminformatics, 5(1), 30.
Luo, H., Li, M., Wang, S., Liu, Q., Li, Y., & Wang, J. (2011). Drug repositioning based on comprehensive similarity measures and a bi-random walk algorithm. Bioinformatics, 32(17), 2664–2671.
Zhou, J., Troyanskaya, O. G. (2018). Predicting effects of noncoding variants with a deep learning–based sequence model. Nature Methods, 12(10), 931–934.
Li, J., & Lu, Z. (2012). A new method for computational drug repositioning using drug–drug interactions. Journal of the American Medical Informatics Association, 19(6), 999–1005.
Campillos, M., Kuhn, M., Gavin, A. C., Jensen, L. J., & Bork, P. (2008). Drug target identification using side-effect similarity. Science, 321(5886), 263–266.
Lamb, J., Crawford, E. D., Peck, D., Modell, J. W., Blat, I. C., Wrobel, M. J., ... & Golub, T. R. (2006). The Connectivity Map: using gene-expression signatures to connect small molecules, genes, and disease. Science, 313(5795), 1929–1935.
Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794.
Xu, R., & Wang, Q. (2014). Large-scale drug–disease association prediction by integrative analysis of multiple data sources. Bioinformatics, 30(17), 2160–2166.
Miotto, R., Wang, F., Wang, S., Jiang, X., & Dudley, J. T. (2018). Deep learning for healthcare: review, opportunities and challenges. Briefings in Bioinformatics, 19(6), 1236–1246.
Ashburn, T. T., & Thor, K. B. (2004). Drug repositioning: identifying and developing new uses for existing drugs. Nature Reviews Drug Discovery, 3(8), 673–683.
Boolell, M., Gepi-Attee, S., Gingell, C., & Allen, M. J. (1996). Sildenafil is a novel, effective oral therapy for male erectile dysfunction. British Journal of Urology, 78(2), 257–261.
Goldstein, I., Lue, T. F., Padma-Nathan, H., Rosen, R. C., Steers, W. D., & Wicker, P. A. (1998). Oral sildenafil in the treatment of erectile dysfunction. New England Journal of Medicine, 338(20), 1397–1404.
Galie, N., Ghofrani, H. A., Torbicki, A., Barst, R. J., Rubin, L. J., Badesch, D., ... & Simonneau, G. (2005). Sildenafil citrate therapy for pulmonary arterial hypertension. New England Journal of Medicine, 353(20), 2148–2157.
McBride, W. G. (1961). Thalidomide and congenital abnormalities. The Lancet, 278(7216), 1358.
Singhal, S., Mehta, J., Desikan, R., Ayers, D., Roberson, P., Eddlemon, P., ... & Barlogie, B. (1999). Antitumor activity of thalidomide in refractory multiple myeloma. New England Journal of Medicine, 341(21), 1565–1571.
Kirk, J. E. (1981). The antihypertensive effect of minoxidil. Journal of Clinical Hypertension, 3(3), 380–385.
Olsen, E. A. (1998). Topical minoxidil in the treatment of androgenetic alopecia. Journal of the American Academy of Dermatology, 38(5), 705–718.
Horwitz, J. P., Chua, J., & Noel, M. (1964). Nucleosides. V. The Mon mesylates of 1-(2′-deoxy-β-D-lyxofuranosyl thymine. Journal of Organic Chemistry, 29(8), 2076–2078.
Mitsuya, H., Weinhold, K. J., Furman, P. A., St Clair, M. H., Lehrman, S. N., Gallo, R. C., ... & Broder, S. (1985). 3′-Azido-3′-deoxythymidine (BW A509U): an antiviral agent that inhibits the infectivity and cytopathic effect of human T-lymphotropic virus type III/lymphadenopathy-associated virus in vitro. PNAS, 82(20), 7096–7100.
Farber, S., & Diamond, L. K. (1948). Temporary remissions in acute leukaemia in children produced by folic acid antagonist, 4-aminopteroyl-glutamic acid (aminopterin). New England Journal of Medicine, 238(23), 787–793.
Weinblatt, M. E., Kaplan, H., Germain, B. F., Block, S., Solomon, S. D., Merryman, P., ... & Fraser, P. A. (1985). Methotrexate in rheumatoid arthritis. A double-blind, placebo-controlled trial. Arthritis & Rheumatism, 28(7), 721–730.
Vane, J. R. (1971). Inhibition of prostaglandin synthesis as a mechanism of action for aspirin-like drugs. Nature New Biology, 231(25), 232–235
Baigent, C., Blackwell, L., Collins, R., Emberson, J., Godwin, J., Peto, R., ... & Antithrombotic Trialists’ Collaboration. (2009). Aspirin in the primary and secondary prevention of vascular disease: collaborative meta-analysis of individual participant data from randomised trials. The Lancet, 373(9678), 1849–1860.
Wang, Y., Zhang, D., Du, G., Du, R., Zhao, J., Jin, Y., ... & Wang, C. (2020). Remdesivir in adults with severe COVID-19: a randomised, double-blind, placebo-controlled, multicentre trial. The Lancet, 395(10236), 1569–1578.35. Richardson, P., Griffin, I., Tucker, C., Smith, D., Oechsle, O., Phelan, A., ... & Stebbing, J. (2020). Baricitinib as a potential treatment for 2019-nCoV acute respiratory disease. The Lancet, 395(10223), e30–e31.
Barabási, A. L., Gulbahce, N., & Loscalzo, J. (2011). Network medicine: a network-based approach to human disease. Nature Reviews Genetics, 12(1), 56–68.
Wu, Z., Wang, Y., Chen, L., & Wei, G. W. (2013). Network-based drug repositioning. Molecular Biosystems, 9(6), 1268–1281.
Zitnik, M., Agrawal, M., & Leskovec, J. (2018). Modelling polypharmacy side effects with graph convolutional networks. Bioinformatics, 34(13), i457–i466.
Ragoza, M., Hochuli, J., Idrobo, E., Sunseri, J., & Koes, D. R. (2017). Protein–ligand scoring with convolutional neural networks. Journal of Chemical Information and Modelling, 57(4), 942–957.
Cheng, J., Randall, A., & Baldi, P. (2016). Prediction of protein stability changes for single-site mutations using support vector machines. Proteins, 62(4), 1125–1132.
Tan, J., Ung, M., Cheng, C., & Greene, C. S. (2019). Unsupervised feature construction and knowledge extraction from genome-wide assays of breast cancer with denoising autoencoders. Pacific Symposium on Biocomputing, 20, 132–143.
Kadurin, A., Nikolenko, S., Khrabrov, K., Aliper, A., & Zhavoronkov, A. (2017). druGAN: An advanced generative adversarial autoencoder model for de novo generation of new molecules with desired molecular properties in silico. Molecular Pharmaceutics, 14(9), 3098–3104.
Hasin, Y., Seldin, M., & Lusis, A. (2017). Multi-omics approaches to disease. Genome Biology, 18(1), 83.
Wang, Q., Wei, W., & Zhang, J. (2019). Using EHR data for drug repurposing: A review of approaches and challenges. Nature Computational Science, 1(3), 153–161.
Xu, H., Aldrich, M. C., Chen, Q., Liu, H., Peterson, N. B., Dai, Q., ... & Roden, D. M. (2015). Validating drug repurposing signals using electronic health records: a case study of metformin and cancer risk. Journal of the American Medical Informatics Association, 22(1), 179–191.
Liu, Q., Chen, H., & Li, Y. (2020). Drug–drug interaction prediction using deep reinforcement learning. Bioinformatics, 36(16), 4496–4503.
Garnett, M. J., Edelman, E. J., Heidorn, S. J., Greenman, C. D., Dastur, A., Lau, K. W., ... & Benes, C. H. (2012). Systematic identification of genomic markers of drug sensitivity in cancer cells. Nature, 483(7391), 570–575.
Iorio, F., Rittman, T., Ge, H., Mitrofanova, A., & Saez-Rodriguez, J. (2016). Transcriptional data: a new gateway to drug repurposing? Nature Reviews Drug Discovery, 15(10), 751–765.
Topol, E. J. (2019). High-performance medicine: the convergence of human and artificial intelligence. Nature Medicine, 25(1), 44–56.
Ferrucci, D., Brown, E., Chu-Carroll, J., Fan, J., Gondek, D., Kalyanpur, A. A., ... & Welty, C. (2010). Building Watson: An overview of the DeepQA project. AI Magazine, 31(3), 59–79.
Shickel, B., Tighe, P. J., Bihorac, A., & Rashidi, P. (2017). Deep EHR: A survey of recent advances in deep learning techniques for electronic health record (EHR) analysis. IEEE Journal of Biomedical and Health Informatics, 22(5), 1589–1604.
Lipton, Z. C. (2018). The mythos of model interpretability. Communications of the ACM, 61(10), 36–43.
Rajkomar, A., Dean, J., & Kohane, I. (2018). Machine learning in medicine. New England Journal of Medicine, 380(14), 1347–1358.
Kaplan, A. V., Petersen, J., & Hunt, C. M. (2021). Regulatory perspectives on artificial intelligence in drug 5development. Clinical Pharmacology & Therapeutics, 109(4), 823–826.
Price, W. N., & Cohen, I. G. (2019). Privacy in the age of medical big data. Nature Medicine, 25(1), 37–43.
Esteva, A., Robicquet, A., Ramsundar, B., Kuleshov, V., DePristo, M., Chou, K., ... & Dean, J. (2019). A guide to deep learning in healthcare. Nature Medicine, 25(1), 24–29.
Hutson, M. (2018). Artificial intelligence faces a reproducibility crisis. Science, 359(6377), 725–726.
Béranger, A., Meurs, M., & Guedj, M. (2021). Rare disease drug development: The promise of artificial intelligence. Therapeutic Innovation & Regulatory Science, 55(1), 25–36.
Pagan, F. L., Hebron, M. L., Wilmarth, B., Torres-Yaghi, Y., Lawler, A., Mundel, E. E., ... & Moussa, C. (2016). Nilotinib effects on safety, tolerability, and potential biomarkers in Parkinson’s disease: a phase 1 open-label study. JAMA Neurology, 73(8), 963–971.
Xie, L., Xie, L., Kinnings, S. L., Bourne, P. E. (2012). Novel computational approaches to polypharmacology as a means to define responses to individual drugs. Annu. Rev. Pharmacal. Toxicol., 52, 361–379.
Published
How to Cite
Issue
Section
Copyright (c) 2025 Sanap Mayuri P, Prof. B.T. Jagtap
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
AUTHORS WHO PUBLISH WITH THIS JOURNAL AGREE TO THE FOLLOWING TERMS:
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-NonCommercial 4.0 Unported License. that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
. 