Machine Learning Prediction of Cancer Cell Sensitivity to Drugs Based on Genomic and Chemical Properties

Abstract

Predicting the response of a specific cancer to a therapy is a major goal in modern oncology that should ultimately lead to a personalised treatment. High-throughput screenings of potentially active compounds against a panel of genomically heterogeneous cancer cell lines have unveiled multiple relationships between genomic alterations and drug responses. Various computational approaches have been proposed to predict sensitivity based on genomic features, while others have used the chemical properties of the drugs to ascertain their effect. In an effort to integrate these complementary approaches, we developed machine learning models to predict the response of cancer cell lines to drug treatment, quantified through IC₅₀ values, based on both the genomic features of the cell lines and the chemical properties of the considered drugs. Models predicted IC₅₀ values in a 8-fold cross-validation and an independent blind test with coefficient of determination R² of 0.72 and 0.64 respectively. Furthermore, models were able to predict with comparable accuracy (R² of 0.61) IC50s of cell lines from a tissue not used in the training stage. Our in silico models can be used to optimise the experimental design of drug-cell screenings by estimating a large proportion of missing IC₅₀ values rather than experimentally measuring them. The implications of our results go beyond virtual drug screening design: potentially thousands of drugs could be probed in silico to systematically test their potential efficacy as anti-tumour agents based on their structure, thus providing a computational framework to identify new drug repositioning opportunities as well as ultimately be useful for personalized medicine by linking the genomic traits of patients to drug sensitivity.

Full text

Its licence does not allow us to show the full text. Read it at PubMed Central:

References 41

1. 1.

   Sharma SV, Haber DA, Settleman J (2010 ) Cell line-based platforms to evaluate the therapeutic efficacy of candidate anticancer agents. Nat Rev Cancer 10: 241–253.

   Not in our library10.1038/nrc2820

2. 2.

   Grever MR, Schepartz SA, Chabner BA (1992 ) The National Cancer Institute: cancer drug discovery and development program. Semin Oncol 19: 622–638.

   Not in our library

3. 3.

   Garnett MJ, Edelman EJ, Heidorn SJ, Greenman CD, Dastur A, et al (2012 ) Systematic identification of genomic markers of drug sensitivity in cancer cells. Nature 483: 570–575.

   Not in our library10.1038/nature11005

4. 4.

   Barretina J, Caponigro G, Stransky N, Venkatesan K, Margolin AA, et al (2012 ) The Cancer Cell Line Encyclopedia enables predictive modelling of anticancer drug sensitivity. Nature 483: 603–607.

   Not in our library10.1038/nature11003

5. 5.

   Heiser LM, Sadanandam A, Kuo WL, Benz SC, Goldstein TC, et al (2012 ) Subtype and pathway specific responses to anticancer compounds in breast cancer. Proc Natl Acad Sci U S A 109: 2724–2729.

   Not in our library10.1073/pnas.1018854108

6. 6.

   Stevens JP (2002) Applied multivariate statistics for the social sciences; Riegert D, editor. Mahwah, NJ: Lawrence Erblaum Associates, Inc.

   Not in our library

7. 7.

   Hui Zou TH (2005 ) Regularization and variable selection via the elastic net. Journal of the Royal Statistical Society: Series B (Statistical Methodology) 67: 301–320.

   Not in our library

8. 8.

   Ashburn TT, Thor KB (2004 ) Drug repositioning: identifying and developing new uses for existing drugs. Nat Rev Drug Discov 3: 673–683.

   Not in our library10.1038/nrd1468

9. 9.

   Sanseau P, Koehler J (2011 ) Editorial: computational methods for drug repurposing. Brief Bioinform 12: 301–302.

   Not in our library10.1093/bib/bbr047

10. 10.

    Paull KD, Shoemaker RH, Hodes L, Monks A, Scudiero DA, et al (1989 ) Display and analysis of patterns of differential activity of drugs against human tumor cell lines: development of mean graph and COMPARE algorithm. J Natl Cancer Inst 81: 1088–1092.

    Not in our library10.1093/jnci/81.14.1088

11. 11.

    Zaharevitz DW, Holbeck SL, Bowerman C, Svetlik PA (2002 ) COMPARE: a web accessible tool for investigating mechanisms of cell growth inhibition. J Mol Graph Model 20: 297–303.

    Not in our library10.1016/s1093-3263(01)00126-7

12. 12.

    Kelloff GJ, Sigman CC (2012 ) Cancer biomarkers: selecting the right drug for the right patient. Nat Rev Drug Discov 11: 201–214.

    Not in our library10.1038/nrd3651

13. 13.

    Kubinyi H (1990 ) Quantitative structure-activity relationships (QSAR) and molecular modelling in cancer research. J Cancer Res Clin Oncol 116: 529–537.

    Not in our library10.1007/bf01637071

14. 14.

    Li GH, Huang JF (2012 ) CDRUG: a web server for predicting anticancer activity of chemical compounds. Bioinformatics 28: 3334–3335.

    Not in our library10.1093/bioinformatics/bts625

15. 15.

    Agarwal S, Dugar D, Sengupta S (2010 ) Ranking chemical structures for drug discovery: a new machine learning approach. J Chem Inf Model 50: 716–731.

    Not in our library10.1021/ci9003865

16. 16.

    Swamidass SJ, Chen J, Bruand J, Phung P, Ralaivola L, et al (2005 ) Kernels for small molecules and the prediction of mutagenicity, toxicity and anti-cancer activity. Bioinformatics 21 Suppl 1i359–368.

    Not in our library10.1093/bioinformatics/bti1055

17. 17.

    Shi LM, Fan Y, Myers TG, O'Connor PM, Paull KD, et al (1998 ) Mining the NCI anticancer drug discovery databases: genetic function approximation for the QSAR study of anticancer ellipticine analogues. J Chem Inf Comput Sci 38: 189–199.

    Not in our library10.1021/ci970085w

18. 18.

    Shi LM, Fan Y, Lee JK, Waltham M, Andrews DT, et al (2000 ) Mining and visualizing large anticancer drug discovery databases. J Chem Inf Comput Sci 40: 367–379.

    Not in our library10.1021/ci990087b

19. 19.

    Yap CW (2011 ) PaDEL-descriptor: an open source software to calculate molecular descriptors and fingerprints. J Comput Chem 32: 1466–1474.

    Not in our library10.1002/jcc.21707

20. 20.

    Solit DB, Garraway LA, Pratilas CA, Sawai A, Getz G, et al (2006 ) BRAF mutation predicts sensitivity to MEK inhibition. Nature 439: 358–362.

    Not in our library10.1038/nature04304

21. 21.

    Chen BJ, Causton HC, Mancenido D, Goddard NL, Perlstein EO, et al (2009 ) Harnessing gene expression to identify the genetic basis of drug resistance. Mol Syst Biol 5: 310.

    Not in our library10.1038/msb.2009.69

22. 22.

    Park ES, Rabinovsky R, Carey M, Hennessy BT, Agarwal R, et al (2010 ) Integrative analysis of proteomic signatures, mutations, and drug responsiveness in the NCI 60 cancer cell line set. Mol Cancer Ther 9: 257–267.

    Not in our library10.1158/1535-7163.mct-09-0743

23. 23.

    Ruderfer DM, Roberts DC, Schreiber SL, Perlstein EO, Kruglyak L (2009 ) Using expression and genotype to predict drug response in yeast. PLoS One 4: e6907.

    Not in our library10.1371/journal.pone.0006907

24. 24.

    Reinhold WC, Sunshine M, Liu H, Varma S, Kohn KW, et al (2012 ) CellMiner: A Web-Based Suite of Genomic and Pharmacologic Tools to Explore Transcript and Drug Patterns in the NCI-60 Cell Line Set. Cancer Res 72: 3499–3511.

    Not in our library10.1158/0008-5472.can-12-1370

25. 25.

    Kutalik Z, Beckmann JS, Bergmann S (2008 ) A modular approach for integrative analysis of large-scale gene-expression and drug-response data. Nat Biotechnol 26: 531–539.

    Not in our library10.1038/nbt1397

26. 26.

    Lamb J, Crawford ED, Peck D, Modell JW, Blat IC, et al (2006 ) The Connectivity Map: using gene-expression signatures to connect small molecules, genes, and disease. Science 313: 1929–1935.

    Not in our library10.1126/science.1132939

27. 27.
    Transcriptional data: a new gateway to drug repositioning? · 2013

    No notice
28. 28.

    Rodriguez-Paredes M, Esteller M (2011 ) Cancer epigenetics reaches mainstream oncology. Nat Med 17: 330–339.

    Not in our library10.1038/nm.2305

29. 29.

    Jorgensen C, Linding R (2010 ) Simplistic pathways or complex networks? Curr Opin Genet Dev 20: 15–22.

    Not in our library10.1016/j.gde.2009.12.003

30. 30.

    Torkamani A, Schork NJ (2011) Background gene expression networks significantly enhance drug response prediction by transcriptional profiling. Pharmacogenomics J.

    Not in our library10.1038/tpj.2011.35

31. 31.

    Mani KM, Lefebvre C, Wang K, Lim WK, Basso K, et al (2008 ) A systems biology approach to prediction of oncogenes and molecular perturbation targets in B-cell lymphomas. Mol Syst Biol 4: 169.

    Not in our library10.1038/msb.2008.2

32. 32.

    Silberberg Y, Gottlieb A, Kupiec M, Ruppin E, Sharan R (2012 ) Large-scale elucidation of drug response pathways in humans. J Comput Biol 19: 163–174.

    Not in our library10.1089/cmb.2011.0264

33. 33.

    Liu Y, Ringner M (2007 ) Revealing signaling pathway deregulation by using gene expression signatures and regulatory motif analysis. Genome Biol 8: R77.

    Not in our library10.1186/gb-2007-8-5-r77

34. 34.
    DEGAS: de novo discovery of dysregulated pathways in human diseases. · 2010

    Not checked
35. 35.
    Identifying Causal Genes and Dysregulated Pathways in Complex Diseases · 2011

    No notice
36. 36.

    Mitchell T (1997) Machine Learning.

    Not in our library

37. 37.

    Jeff H (2008) Introduction to Neural Networks for Java.

    Not in our library

38. 38.

    Jeff H (2011) Programming Neural Networks with Encog3 in Java.

    Not in our library

39. 39.

    Riedmiller M, Braun H (1993 ) A Direct Adaptive Method for Faster Backpropagation Learning - the Rprop Algorithm. 1993 Ieee International Conference on Neural Networks, Vols 1–3: 586–591.

    Not in our library

40. 40.

    Breiman L (2001 ) Random forests. Machine Learning 45: 5–32.

    Not in our library

41. 41.

    Wiener ALaM (2002 ) Classification and Regression by randomForest. R News 2: 18–22.

    Not in our library

Cited by papers we hold 16

• Artificial Intelligence in Pharmaceutical Technology and Drug Delivery Design · 2023
  No notice
• Machine Learning for Lung Cancer Diagnosis, Treatment, and Prognosis · 2022
  No notice
• A review of deep learning applications for genomic selection · 2021
  No notice
• Machine learning approaches to drug response prediction: challenges and recent progress · 2020
  No notice
• Predicting Synergism of Cancer Drug Combinations Using NCI-ALMANAC Data · 2019
  No notice
• Improving prediction of phenotypic drug response on cancer cell lines using deep convolutional network · 2019
  No notice
• Dr.VAE: improving drug response prediction via modeling of drug perturbation effects · 2019
  No notice
• Multi-trait, Multi-environment Deep Learning Modeling for Genomic-Enabled Prediction of Plant Traits · 2018
  No notice
• Opportunities and obstacles for deep learning in biology and medicine · 2018
  No notice
• Multi-environment Genomic Prediction of Plant Traits Using Deep Learners With Dense Architecture · 2018
  No notice
• Cancer Drug Response Profile scan (CDRscan): A Deep Learning Model That Predicts Drug Effectiveness from Cancer Genomic Signature · 2018
  No notice
• Machine learning and feature selection for drug response prediction in precision oncology applications · 2018
  No notice
• Improved anticancer drug response prediction in cell lines using matrix factorization with similarity regularization · 2017
  No notice
• Predicting Anticancer Drug Responses Using a Dual-Layer Integrated Cell Line-Drug Network Model · 2015
  No notice
• Toward more realistic drug-target interaction predictions · 2014
  No notice
• Clinical drug response can be predicted using baseline gene expression levels and in vitro drug sensitivity in cell lines · 2014
  No notice

Reads

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.