Anti-cancer Drug Activity Prediction by Ensemble Learning

Ertan Tolan, Mehmet Tan


Personalized cancer treatment is an ever-evolving approach due to complexity of cancer. As a part of personalized therapy, effectiveness of a drug on a cell line is measured. However, these experiments are backbreaking and money consuming. To surmount these difficulties, computational methods are used with the provided data sets. In the present study, we considered this as a regression problem and designed an ensemble model by combining three different regression models to reduce prediction error for each drug-cell line pair. Two major data sets, were used to evaluate our method. Results of this evaluation show that predictions of ensemble method are significantly better than models \emph{per se}. Furthermore, we report the cytotoxicty predictions of our model for the drug-cell line pairs that do not appear in the original data sets.


  1. Bansal, M., Yang, J., et al. (2014). A community computational challenge to predict the activity of pairs of compounds. Nature Biotechnology, 32(2):1-3.
  2. Brem, G. J., Mylonas, I., et al. (2013). Eeyarestatin causes cervical cancer cell sensitization to bortezomib treatment by augmenting ER stress and CHOP expression. Gynecologic Oncology, 128:383-390.
  3. Caruana, R. (1998). Multitask Learning. In Learning to Learn, pages 95-133. Springer US, Boston, MA.
  4. Cort├ęs-Ciriano, I., van Westen, G. J. P., et al. (2015). Improved large-scale prediction of growth inhibition patterns using the NCI60 cancer cell line panel. Bioinformatics, 32(1):btv529.
  5. Costello, J. C., Heiser, L. M., et al. (2014). A community effort to assess and improve drug sensitivity prediction algorithms. Nature Biotechnology, 32(12):1202.
  6. Cukier, H., Peralta, R., et al. (2012). Preclinical dose scheduling studies of lor-253, a novel anticancer drug, in combination with chemotherapeutics in lung and colon cancers. In AACR; Cancer Res, volume 72.
  7. Dong, Z., Zhang, N., et al. (2015). Anticancer drug sensitivity prediction in cell lines from baseline gene expression through recursive feature selection. BMC cancer, 15(1):489.
  8. Friedman, H. (2002). Stochastic gradient boosting. Computational Statistics and Data Analysis, 38(4):367-378.
  9. Gonen, M. and Margolin, A. A. (2014). Drug susceptibility prediction against a panel of drugs using kernelized Bayesian multitask learning. Bioinformatics, 30(17):i556-i563.
  10. Haider, S., Rahman, R., et al. (2015). A Copula Based Approach for Design of Multivariate Random Forests for Drug Sensitivity Prediction. PLOS ONE, 10(12):e0144490.
  11. Jackson, S. E. and Chester, J. D. (2015). Personalised cancer medicine. International Journal of Cancer, 137(2):262-266.
  12. Ji, S. and Ye, J. (2009). An accelerated gradient method for trace norm minimization. In Proceedings of the 26th annual ICML, pages 457-464. ACM.
  13. Menden, M. P., Iorio, F., et al. (2013). Machine Learning Prediction of Cancer Cell Sensitivity to Drugs Based on Genomic and Chemical Properties. PLoS ONE, 8(4):e61318.
  14. Qin, Y., Chen, M., et al. (2015). A network flow-based method to predict anticancer drug sensitivity. PLoS ONE, 10(5):1-14.
  15. Rappaport, N., Nativ, N., et al. (2013). MalaCards: an integrated compendium for diseases and their annotation. Database : the journal of biological databases and curation, 2013:bat018.
  16. Rees, M. G., Seashore-Ludlow, B., et al. (2015). Correlating chemical sensitivity and basal gene expression reveals mechanism of action. Nature Chemical Biology, 12(2):109-116.
  17. Riddick, G., Song, H., et al. (2011). Predicting in vitro drug sensitivity using Random Forests. 27(2):220-22410.
  18. Seashore-Ludlow, B., Rees, M. G., et al. (2015). Harnessing Connectivity in a Large-Scale Small-Molecule Sensitivity Dataset. Cancer discovery, 5(11):1210-23.
  19. Sewell, M. (2008). Ensemble learning. RN, 11(02).
  20. Shi, L., Song, X.-B., et al. (2016). Docetaxel-conjugated monomethoxy-poly(ethylene glycol)-b-poly(lactide) (mPEG-PLA) polymeric micelles to enhance the therapeutic efficacy in oral squamous cell carcinoma.RSC Adv., 6(49):42819-42826.
  21. Wolpert, D. H. (1992). Stacked generalization. Neural Networks, 5(2):241-259.
  22. Yang, W., Soares, J., et al. (2013). Genomics of Drug Sensitivity in Cancer (GDSC): a resource for therapeutic biomarker discovery in cancer cells. Nucleic Acids Research, 41(D1):D955-D961.
  23. Zhang, N., Wang, H., et al. (2015). Predicting Anticancer Drug Responses Using a Dual-Layer Integrated Cell Line-Drug Network Model. PLoS computational biology, 11(9):e1004498.
  24. Zhao, Z., Fu, G., et al. (2013). Drug activity prediction using multiple-instance learning via joint instance and feature selection. BMC Bioinformatics, 14 Suppl 1(Suppl 14):S16.
  25. Zhou, J., Chen, J., and Ye, J. (2012). User's Manual MALSAR: Multi-tAsk Learning via StructurAl Regularization. Arizona State University.

Paper Citation

in Harvard Style

Tolan E. and Tan M. (2016). Anti-cancer Drug Activity Prediction by Ensemble Learning . In Proceedings of the 8th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR, (IC3K 2016) ISBN 978-989-758-203-5, pages 431-436. DOI: 10.5220/0006085704310436

in Bibtex Style

author={Ertan Tolan and Mehmet Tan},
title={Anti-cancer Drug Activity Prediction by Ensemble Learning},
booktitle={Proceedings of the 8th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR, (IC3K 2016)},

in EndNote Style

JO - Proceedings of the 8th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR, (IC3K 2016)
TI - Anti-cancer Drug Activity Prediction by Ensemble Learning
SN - 978-989-758-203-5
AU - Tolan E.
AU - Tan M.
PY - 2016
SP - 431
EP - 436
DO - 10.5220/0006085704310436