Login Register Cart 0
Generic placeholder image

Current Bioinformatics

Editor-in-Chief

ISSN (Print): 1574-8936
ISSN (Online): 2212-392X

Back
Journal Home About Journal Editorial Board Journal Insight Current Issue Volumes/Issues
Subscribe
Research Article

NeuMF: Predicting Anti-cancer Drug Response Through a Neural Matrix Factorization Model

Author(s): Hui Liu, Jian Yu, Xiangzhi Chen and Lin Zhang*

Volume 17, Issue 9, 2022

Published on: 29 August, 2022

Page: [835 - 847] Pages: 13

DOI: 10.2174/1574893617666220609114052

Price: $65

conference banner
Abstract

Background: Anti-cancer drug response is urgently required for individualized therapy. Measurements with wet experiments are costly and time-consuming. Artificial intelligence-based models are currently available for predicting drug response but still have challenges in prediction accuracy.

Objective: Construct a model to predict drug response values for unknown cell lines and analyze drug potential association properties in sparse data.

Methods: Propose a Neural Matrix Factorization (NeuMF) framework to help predict the unknown responses of cell lines to drugs. The model uses a deep neural network to figure out drug and cell lines' latent variables. In NeuMF, the inputs and the parameters of the multi-layer neural network are simultaneously optimized by gradient descent to minimize the reconstruction errors between the predicted and natural values of the observed entries. Then the unknown entries can be readily recovered by propagating the latent variables to the output layer.

Results: Experiments on the Cancer Cell Line Encyclopedia (CCLE) dataset and Genomics of Drug Sensitivity in Cancer (GDSC) dataset compare NeuMF with the other three state-of-the-art methods. NeuMF reduces constructing drug or cell line similarity and mines the response matrix itself for correlations in the network, avoiding the inclusion of redundant noise. NeuMF obtained drug averaged PCC_sr of 0.83 and 0.84 on both datasets. It demonstrates that NeuMF substantially improves the prediction. Some essential parameters in NeuMF, such as the global effect removal strategy and the input layer scales, are also discussed. Finally, case studies have shown that NeuMF can better learn the latent characteristics of drugs, e.g., Irinotecan and Topotecan are found to act on the same pathway TOP1. The conclusions are in line with some existing biological findings.

Conclusion: NeuMF achieves better prediction accuracy than existing models, and its output is biologically interpretable. NeuMF also helps analyze the correlations between drugs.

Keywords: Neural matrix factorization, Drug response prediction, Neural networks, Precision medicine, Genomics of Drug Sensitivity in Cancer (GDSC), Cancer Cell Line Encyclopedia (CCLE)

« Previous Next »
Graphical Abstract

[1]
Berns A. Gene expression in diagnosis. Nature 2000; 403(6769): 491-2.
[http://dx.doi.org/10.1038/35000684] [PMID: 10676943]
[2]
Marquet P, Longeray P-H, Barlesi F, et al. Translational research: Precision medicine, personalized medicine, targeted therapies: Marketing or science? Therapie 2015; 70(1): 1-19.
[http://dx.doi.org/10.2515/therapie/2014230] [PMID: 25679189]
[3]
Vougas K, Krochmal M, Jackson T, et al. Deep learning and association rule mining for predicting drug response in cancer. A personalised medicine approach. bioRxiv 2017; 2017; 070490.
[4]
Sharifi-Noghabi H, Zolotareva O, Collins CC, Ester M. MOLI: Multi-omics late integration with deep neural networks for drug response prediction. Bioinformatics 2019; 35(14): i501-9.
[http://dx.doi.org/10.1093/bioinformatics/btz318] [PMID: 31510700]
[5]
Dong Z, Zhang N, Li C, et al. Anticancer drug sensitivity prediction in cell lines from baseline gene expression through recursive feature selection. BMC Cancer 2015; 15(1): 489.
[http://dx.doi.org/10.1186/s12885-015-1492-6] [PMID: 26121976]
[6]
Ammad-ud-din M, Georgii E, Gönen M, et al. Integrative and personalized QSAR analysis in cancer by kernelized Bayesian matrix factorization. J Chem Inf Model 2014; 54(8): 2347-59.
[http://dx.doi.org/10.1021/ci500152b] [PMID: 25046554]
[7]
Wang L, Li X, Zhang L, Gao Q. Improved anticancer drug response prediction in cell lines using matrix factorization with similarity regularization. BMC Cancer 2017; 17(1): 513.
[http://dx.doi.org/10.1186/s12885-017-3500-5] [PMID: 28768489]
[8]
Suphavilai C, Bertrand D, Nagarajan N. Predicting cancer drug response using a recommender system. Bioinformatics 2018; 34(22): 3907-14.
[http://dx.doi.org/10.1093/bioinformatics/bty452] [PMID: 29868820]
[9]
Guan NN, Zhao Y, Wang CC, Li JQ, Chen X, Piao X. Anticancer drug response prediction in cell lines using weighted graph regularized matrix factorization. Mol Ther Nucleic Acids 2019; 17: 164-74.
[http://dx.doi.org/10.1016/j.omtn.2019.05.017] [PMID: 31265947]
[10]
Liu C, Wei D, Xiang J, et al. An improved anticancer drug-response prediction based on an ensemble method integrating matrix completion and ridge regression. Mol Ther Nucleic Acids 2020; 21: 676-86.
[http://dx.doi.org/10.1016/j.omtn.2020.07.003] [PMID: 32759058]
[11]
Pouryahya M, Oh JH, Mathews JC, et al. Pan-cancer prediction of cell-line drug sensitivity using network-based methods. Int J Mol Sci 2022; 23(3): 1074.
[http://dx.doi.org/10.3390/ijms23031074] [PMID: 35163005]
[12]
Hassan M, Ali S, Sanaullah M, et al. Drug response prediction of liver cancer cell line using deep learning COMPUTERS MATERIALS AND CONTINUA Yчpeдитeли. Tech Science Press 2022; 70(2): 2743-60.
[http://dx.doi.org/10.32604/cmc.2022.020055]
[13]
Koren Y, Bell R, Volinsky C. Matrix factorization techniques for recommender systems. Computer 2009; 42: 30-7.
[http://dx.doi.org/10.1109/MC.2009.263]
[14]
Schmidhuber J. Deep learning in neural networks: An overview. Neural Netw 2015; 61: 85-117.
[http://dx.doi.org/10.1016/j.neunet.2014.09.003] [PMID: 25462637]
[15]
Barretina J, Caponigro G, Stransky N, et al. The cancer cell line encyclopedia enables predictive modelling of anticancer drug sensitivity. Nature 2012; 483(7391): 603-7.
[http://dx.doi.org/10.1038/nature11003] [PMID: 22460905]
[16]
Garnett MJ, Edelman EJ, Heidorn SJ, et al. Systematic identification of genomic markers of drug sensitivity in cancer cells. Nature 2012; 483(7391): 570-5.
[http://dx.doi.org/10.1038/nature11005] [PMID: 22460902]
[17]
Yang W, Soares J, Greninger P, et al. Genomics of Drug Sensitivity in Cancer (GDSC): A resource for therapeutic biomarker discovery in cancer cells. Nucleic Acids Res 2013; 41(Database issue): D955-61.
[PMID: 23180760]
[18]
Wen Z, Yin W, Zhang Y. Solving a low-rank factorization model for matrix completion by a nonlinear successive over-relaxation algorithm. Math Program Comput 2012; 4(4): 333-61.
[http://dx.doi.org/10.1007/s12532-012-0044-1]
[19]
Hinton GE, Salakhutdinov RR. Reducing the dimensionality of data with neural networks. Science 2006; 313(5786): 504-7.
[http://dx.doi.org/10.1126/science.1127647] [PMID: 16873662]
[20]
Igel C, Hüsken M. Improving the Rprop learning algorithm Proceedings of the Second International ICSC Symposium on Neural Computation (NC 2000). Bochum, Germany. 115-21.
[21]
Igel C, Hüsken M. Empirical evaluation of the improved Rprop learning algorithms. Neurocomputing 2003; 50: 105-23.
[http://dx.doi.org/10.1016/S0925-2312(01)00700-7]
[22]
Calin O. Activation Functions.Deep Learning Architectures: A Mathematical Approach. Cham: Springer International Publishing 1st ed. Cham, Switzerland 2021; pp. 21-39.
[http://dx.doi.org/10.1007/978-3-030-36721-3_2]
[23]
Browne MW. Cross-validation methods. J Math Psychol 2000; 44(1): 108-32.
[http://dx.doi.org/10.1006/jmps.1999.1279] [PMID: 10733860]
[24]
Ly A, Marsman M, Wagenmakers EJ. Analytic posteriors for Pearson’s correlation coefficient. Stat Neerl 2018; 72(1): 4-13.
[http://dx.doi.org/10.1111/stan.12111] [PMID: 29353942]
[25]
Cohen FE, Sternberg MJ. On the prediction of protein structure: The significance of the root-mean-square deviation. J Mol Biol 1980; 138(2): 321-33.
[http://dx.doi.org/10.1016/0022-2836(80)90289-2] [PMID: 7411610]
[26]
Koren Y. The bellkor solution to the netflix grand prize. Netflix prize documentation 2009; 81(2009): 1-10.
[27]
Taheri S, Hesamian G. A generalization of the Wilcoxon signed-rank test and its applications. Stat Hefte 2013; 54(2): 457-70.
[28]
Brugge J, Hung MC, Mills GB. A new mutational AKTivation in the PI3K pathway. Cancer Cell 2007; 12(2): 104-7.
[http://dx.doi.org/10.1016/j.ccr.2007.07.014] [PMID: 17692802]
[29]
Liu P, Cheng H, Roberts TM, Zhao JJ. Targeting the phosphoinositide 3-kinase pathway in cancer. Nat Rev Drug Discov 2009; 8(8): 627-44.
[http://dx.doi.org/10.1038/nrd2926] [PMID: 19644473]
[30]
Ali MM, Bagratuni T, Davenport EL, et al. Structure of the Ire1 autophosphorylation complex and implications for the unfolded protein response. EMBO J 2011; 30(5): 894-905.
[http://dx.doi.org/10.1038/emboj.2011.18] [PMID: 21317875]
[31]
Lombardo LJ, Lee FY, Chen P, et al. Discovery of N-(2-chloro-6-methyl- phenyl)-2-(6-(4-(2-hydroxyethyl)- piperazin-1-yl)-2-methylpyrimidin-4- ylamino)thiazole-5-carboxamide (BMS-354825), a dual Src/Abl kinase inhibitor with potent antitumor activity in preclinical assays. J Med Chem 2004; 47(27): 6658-61.
[http://dx.doi.org/10.1021/jm049486a] [PMID: 15615512]
[32]
Fabbro D, Ruetz S, Bodis S, et al. PKC412--a protein kinase inhibitor with a broad therapeutic potential. Anticancer Drug Des 2000; 15(1): 17-28.
[PMID: 10888033]
[33]
Moyer JD, Barbacci EG, Iwata KK, et al. Induction of apoptosis and cell cycle arrest by CP-358,774, an inhibitor of epidermal growth factor receptor tyrosine kinase. Cancer Res 1997; 57(21): 4838-48.
[PMID: 9354447]
[34]
Rusnak DW, Lackey K, Affleck K, et al. The effects of the novel, reversible epidermal growth factor receptor/ErbB-2 tyrosine kinase inhibitor, GW2016, on the growth of human normal and tumor-derived cell lines in vitro and in vivo. Mol Cancer Ther 2001; 1(2): 85-94.
[PMID: 12467226]
[35]
Baldi P, Hornik K. Neural networks and principal component analysis: Learning from examples without local minima. Neural Netw 1989; 2(1): 53-8.
[http://dx.doi.org/10.1016/0893-6080(89)90014-2]
[36]
Barrett SD, Bridges AJ, Dudley DT, et al. The discovery of the benzhydroxamate MEK inhibitors CI-1040 and PD 0325901. Bioorg Med Chem Lett 2008; 18(24): 6501-4.
[http://dx.doi.org/10.1016/j.bmcl.2008.10.054] [PMID: 18952427]
[37]
Huynh H, Soo KC, Chow PKH, Tran E. Targeted inhibition of the extracellular signal-regulated kinase kinase pathway with AZD6244 (ARRY-142886) in the treatment of hepatocellular carcinoma. Mol Cancer Ther 2007; 6(1): 138-46.
[http://dx.doi.org/10.1158/1535-7163.MCT-06-0436] [PMID: 17237274]
[38]
Peyssonnaux C, Eychène A. The Raf/MEK/ERK pathway: New concepts of activation. Biol Cell 2001; 93(1-2): 53-62.
[http://dx.doi.org/10.1016/S0248-4900(01)01125-X] [PMID: 11730323]
[39]
Green TP, Fennell M, Whittaker R, et al. Preclinical anticancer activity of the potent, oral Src inhibitor AZD0530. Mol Oncol 2009; 3(3): 248-61.
[http://dx.doi.org/10.1016/j.molonc.2009.01.002] [PMID: 19393585]
[40]
Takeda H, Takigawa N, Ohashi K, et al. Vandetanib is effective in EGFR-mutant lung cancer cells with PTEN deficiency. Exp Cell Res 2013; 319(4): 417-23.
[http://dx.doi.org/10.1016/j.yexcr.2012.12.018] [PMID: 23274758]
[41]
Pavillard V, Agostini C, Richard S, Charasson V, Montaudon D, Robert J. Determinants of the cytotoxicity of irinotecan in two human colorectal tumor cell lines. Cancer Chemother Pharmacol 2002; 49(4): 329-35.
[http://dx.doi.org/10.1007/s00280-001-0416-0] [PMID: 11914913]
[42]
Zhang FL, Wang P, Liu YH, et al. Topoisomerase I inhibitors, shikonin and topotecan, inhibit growth and induce apoptosis of glioma cells and glioma stem cells. PLoS One 2013; 8(11): e81815.
[http://dx.doi.org/10.1371/journal.pone.0081815] [PMID: 24303074]
[43]
Huynh H, Chow PKH, Tai WM, et al. Dovitinib demonstrates antitumor and antimetastatic activities in xenograft models of hepatocellular carcinoma. J Hepatol 2012; 56(3): 595-601.
[http://dx.doi.org/10.1016/j.jhep.2011.09.017] [PMID: 22027573]
[44]
El-Ashmawy NE, Khedr EG, El-Bahrawy HA, Abd El-Fattah EE. Sorafenib effect on liver neoplastic changes in rats: More than a kinase inhibitor. Clin Exp Med 2017; 17(2): 185-91.
[http://dx.doi.org/10.1007/s10238-016-0416-3] [PMID: 27085325]

Rights & Permissions Print Cite
Article Metrics
3
© 2024 Bentham Science Publishers | Privacy Policy