Using Drug Expression Profiles and Machine Learning Approach for Drug Repurposing

  • Kai Zhao
  • Hon-Cheong SoEmail author
Part of the Methods in Molecular Biology book series (MIMB, volume 1903)


The cost of new drug development has been increasing, and repurposing known medications for new indications serves as an important way to hasten drug discovery. One promising approach to drug repositioning is to take advantage of machine learning (ML) algorithms to learn patterns in biological data related to drugs and then link them up to the potential of treating specific diseases. Here we give an overview of the general principles and different types of ML algorithms, as well as common approaches to evaluating predictive performances, with reference to the application of ML algorithms to predict repurposing opportunities using drug expression data as features. We will highlight common issues and caveats when applying such models to repositioning. We also introduce resources of drug expression data and highlight recent studies employing such an approach to repositioning.

Key words

Drug repositioning Machine learning Drug transcriptome Genomics Deep learning 



This work is partially supported by the Lo Kwee-Seong Biomedical Research Fund and a Direct Grant from the Chinese University of Hong Kong to HCS.


  1. 1.
    DiMasi JA, Grabowski HG, Hansen RW (2016) Innovation in the pharmaceutical industry: new estimates of R&D costs. J Health Econ 47:20–33. CrossRefPubMedPubMedCentralGoogle Scholar
  2. 2.
    Dudley JT, Deshpande T, Butte AJ (2011) Exploiting drug-disease relationships for computational drug repositioning. Brief Bioinform 12(4):303–311. CrossRefPubMedPubMedCentralGoogle Scholar
  3. 3.
    Hodos RA, Kidd BA, Shameer K, Readhead BP, Dudley JT (2016) In silico methods for drug repurposing and pharmacology. Wiley Interdiscip Rev Syst Biol Med 8(3):186–210. CrossRefPubMedPubMedCentralGoogle Scholar
  4. 4.
    Vanhaelen Q, Mamoshina P, Aliper AM, Artemov A, Lezhnina K, Ozerov I, Zhavoronkov A (2017) Design of efficient computational workflows for in silico drug repurposing. Drug Discov Today 22(2):210–222. CrossRefGoogle Scholar
  5. 5.
    Aliper A, Plis S, Artemov A, Ulloa A, Mamoshina P, Zhavoronkov A (2016) Deep learning applications for predicting pharmacological properties of drugs and drug repurposing using transcriptomic data. Mol Pharm 13(7):2524–2530. CrossRefPubMedPubMedCentralGoogle Scholar
  6. 6.
    Zhao K, So H-C (2018) Drug repositioning for schizophrenia and depression/anxiety disorders: A machine learning approach leveraging expression data. IEEE journal of biomedical and health informatics (in press)Google Scholar
  7. 7.
    Friedman J, Hastie T, Tibshirani R (2001) The elements of statistical learning, vol 1. Springer Series in Statistics, New YorkGoogle Scholar
  8. 8.
    Hoerl AE, Kennard RW (2000) Ridge regression: biased estimation for nonorthogonal problems. Technometrics 42(1):80–86. CrossRefGoogle Scholar
  9. 9.
    Tibshirani R (2011) Regression shrinkage and selection via the lasso: a retrospective. J R Stat Soc Series B Stat Methodol 73:273–282. CrossRefGoogle Scholar
  10. 10.
    Zou H, Hastie T (2005) Regularization and variable selection via the elastic net (vol B 67, pg 301, 2005). J R Stat Soc Series B Stat Methodol 67:768–768. CrossRefGoogle Scholar
  11. 11.
    Bishop CM (2006) Pattern recognition and machine learning. Springer, New YorkGoogle Scholar
  12. 12.
    Xie LW, He S, Wen YQ, Bo XC, Zhang ZN (2017) Discovery of novel therapeutic properties of drugs from transcriptional responses based on multi-label classification. Sci Rep 7. ARTN 7136
  13. 13.
    Wang F, Zhang P, Cao N, Hu JY, Sorrentino R (2014) Exploring the associations between drug side-effects and therapeutic indications. J Biomed Inform 51:15–23. CrossRefPubMedGoogle Scholar
  14. 14.
    Friedman J, Hastie T, Tibshirani R (2010) Regularization paths for generalized linear models via coordinate descent. J Stat Softw 33(1):1–22CrossRefGoogle Scholar
  15. 15.
    Lockhart R, Taylor J, Tibshirani RJ, Tibshirani R (2014) A significance test for the lasso. Ann Stat 42(2):413CrossRefGoogle Scholar
  16. 16.
    Breiman, L. (1984). Classification and regression trees. Belmont, CA.: Wadsworth International GroupGoogle Scholar
  17. 17.
    Breiman L (2001) Random forests. Mach Learn 45(1):5–32. CrossRefGoogle Scholar
  18. 18.
    Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29(5):1189–1232. CrossRefGoogle Scholar
  19. 19.
    James G, Witten D, Hastie T, Tibshirani R (2013) An introduction to statistical learning, vol 112. Springer, New YorkCrossRefGoogle Scholar
  20. 20.
    Freund Y, Schapire RE (1997) A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci 55(1):119–139. CrossRefGoogle Scholar
  21. 21.
    Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297. CrossRefGoogle Scholar
  22. 22.
    Napolitano F, Zhao Y, Moreira VM, Tagliaferri R, Kere J, D'Amato M, Greco D (2013) Drug repositioning: a machine-learning approach through data integration. J Cheminform 5. Artn 30CrossRefGoogle Scholar
  23. 23.
    Wang YC, Chen SL, Deng NY, Wang Y (2013) Drug repositioning by kernel-based integration of molecular structure, molecular activity, and phenotype data. PLoS One 8(11). ARTN e78518CrossRefGoogle Scholar
  24. 24.
    Buitinck L, Louppe G, Blondel M, Pedregosa F, Mueller A, Grisel O, Grobler J (2013) API design for machine learning software: experiences from the scikit-learn project. arXiv preprint arXiv 1309:0238Google Scholar
  25. 25.
    Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Duchesnay E (2011) Scikit-learn: machine learning in python. J Mach Learn Res 12:2825–2830Google Scholar
  26. 26.
    Bengio Y, Courville A, Vincent P (2013) Representation learning: a review and new perspectives. IEEE Trans Pattern Anal Mach Intell 35(8):1798–1828CrossRefGoogle Scholar
  27. 27.
    Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15:1929–1958Google Scholar
  28. 28.
    Klambauer G, Unterthiner T, Mayr A, Hochreiter S (2017) DeepTox: toxicity prediction using deep learning. Toxicol Lett 280:S69–S69. CrossRefGoogle Scholar
  29. 29.
    Ryu JY, Kim HU, Lee SY (2018) Deep learning improves prediction of drug-drug and drug-food interactions. Proc Natl Acad Sci U S A 115(18):E4304–E4311. CrossRefPubMedPubMedCentralGoogle Scholar
  30. 30.
    Preuer K, Lewis RPI, Hochreiter S, Bender A, Bulusu KC, Klambauer G (2018) DeepSynergy: predicting anti-cancer drug synergy with deep learning. Bioinformatics 34(9):1538–1546. CrossRefPubMedGoogle Scholar
  31. 31.
    Baskin II, Winkler D, Tetko IV (2016) A renaissance of neural networks in drug discovery. Expert Opin Drug Discov 11(8):785–795. CrossRefPubMedGoogle Scholar
  32. 32.
    Chen H, Engkvist O, Wang Y, Olivecrona M, Blaschke T (2018) The rise of deep learning in drug discovery. Drug Discov Today. CrossRefGoogle Scholar
  33. 33.
    Ching T, Himmelstein DS, Beaulieu-Jones BK, Kalinin AA, Do BT, Way GP, Greene CS (2018) Opportunities and obstacles for deep learning in biology and medicine. J R Soc Interface 15(141). CrossRefGoogle Scholar
  34. 34.
    Varma S, Simon R (2006) Bias in error estimation when using cross-validation for model selection. BMC Bioinformatics 7:91. CrossRefPubMedPubMedCentralGoogle Scholar
  35. 35.
    Davis J, Mark G (2006) The relationship between Precision-Recall and ROC curves. In: Proceedings of the 23rd international conference on Machine learning. ACM, pp 233–240Google Scholar
  36. 36.
    Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP (2002) SMOTE: synthetic minority over-sampling technique. J Artif Intell Res 16:321–357CrossRefGoogle Scholar
  37. 37.
    Lamb J, Crawford ED, Peck D, Modell JW, Blat IC, Wrobel MJ, Golub TR (2006) The connectivity map: using gene-expression signatures to connect small molecules, genes, and disease. Science 313(5795):1929–1935. CrossRefGoogle Scholar
  38. 38.
    Smyth GK (2005) Limma: linear models for microarray data Bioinformatics and computational biology solutions using R and Bioconductor. Springer, New York, pp 397–420CrossRefGoogle Scholar
  39. 39.
    Wei WQ, Cronin RM, Xu H, Lasko TA, Bastarache L, Denny JC (2013) Development and evaluation of an ensemble resource linking medications to their indications. J Am Med Inform Assoc 20(5):954–961. CrossRefPubMedPubMedCentralGoogle Scholar
  40. 40.
    Bergstra J, Bengio Y (2012) Random search for hyper-parameter optimization. J Mach Learn Res 13:281–305Google Scholar
  41. 41.
    Louppe G, Wehenkel L, Sutera A, Geurts P (2013) Understanding variable importances in forests of randomized trees. In: Advances in neural information processing systems, pp 431–439Google Scholar
  42. 42.
    Subramanian A, Narayan R, Corsello SM, Peck DD, Natoli TE, Lu XD, Golub TR (2017) A next generation connectivity map: L1000 platform and the first 1,000,000 profiles. Cell 171(6):1437. CrossRefPubMedPubMedCentralGoogle Scholar
  43. 43.
    So HC, Chau CKL, Chiu WT, Ho KS, Lo CP, Yim SHY, Sham PC (2017) Analysis of genome-wide association data highlights candidates for drug repositioning in psychiatry. Nat Neurosci 20(10):1342-+. CrossRefPubMedGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.School of Biomedical SciencesThe Chinese University of Hong KongShatinHong Kong
  2. 2.KIZ-CUHK Joint Laboratory of Bioresources and Molecular Research of Common DiseasesKunming Zoology Institute of ZoologyKunmingChina

Personalised recommendations