Treffer: Development and evaluation of a java-based deep neural network method for drug response predictions.

Title:
Development and evaluation of a java-based deep neural network method for drug response predictions.
Authors:
Huang B; Intelligent Molecular Discovery Laboratory, Department of Experimental Therapeutics, The University of Texas MD Anderson Cancer Center, Houston, TX, United States., Fong LWR; Intelligent Molecular Discovery Laboratory, Department of Experimental Therapeutics, The University of Texas MD Anderson Cancer Center, Houston, TX, United States., Chaudhari R; Intelligent Molecular Discovery Laboratory, Department of Experimental Therapeutics, The University of Texas MD Anderson Cancer Center, Houston, TX, United States., Zhang S; Intelligent Molecular Discovery Laboratory, Department of Experimental Therapeutics, The University of Texas MD Anderson Cancer Center, Houston, TX, United States.
Source:
Frontiers in artificial intelligence [Front Artif Intell] 2023 Mar 23; Vol. 6, pp. 1069353. Date of Electronic Publication: 2023 Mar 23 (Print Publication: 2023).
Publication Type:
Journal Article
Language:
English
Journal Info:
Publisher: Frontiers Media SA Country of Publication: Switzerland NLM ID: 101770551 Publication Model: eCollection Cited Medium: Internet ISSN: 2624-8212 (Electronic) Linking ISSN: 26248212 NLM ISO Abbreviation: Front Artif Intell Subsets: PubMed not MEDLINE
Imprint Name(s):
Original Publication: Lausanne, Switzerland : Frontiers Media SA, [2018]-
References:
J Chem Inf Model. 2011 Nov 28;51(11):2948-60. (PMID: 21902220)
J Chem Inf Model. 2015 May 26;55(5):1062-76. (PMID: 25918827)
Nat Med. 2018 May;24(5):638-646. (PMID: 29686424)
Nature. 2018 Mar 28;555(7698):604-610. (PMID: 29595767)
ACS Med Chem Lett. 2018 Oct 08;9(11):1065-1069. (PMID: 30429945)
Cogn Sci. 2014 Aug;38(6):1078-101. (PMID: 23800216)
J Comput Aided Mol Des. 2003 Feb-Apr;17(2-4):241-53. (PMID: 13677490)
J Chem Inf Model. 2006 Sep-Oct;46(5):1984-95. (PMID: 16995729)
Nature. 2019 Sep;573(7775):S100-S102. (PMID: 31554996)
PLoS One. 2016 Jun 01;11(6):e0156338. (PMID: 27248692)
J Chem Inf Model. 2006 Jul-Aug;46(4):1535. (PMID: 16859285)
J Chem Inf Model. 2015 Feb 23;55(2):263-74. (PMID: 25635324)
J Chem Inf Comput Sci. 2004 Sep-Oct;44(5):1630-8. (PMID: 15446820)
Mol Inform. 2016 Jan;35(1):3-14. (PMID: 27491648)
Nat Med. 2019 Jan;25(1):60-64. (PMID: 30617323)
J Chem Inf Model. 2017 Dec 26;57(12):2996-3010. (PMID: 29111719)
Expert Opin Drug Discov. 2017 Mar;12(3):279-291. (PMID: 28067061)
J Med Chem. 2006 May 4;49(9):2713-24. (PMID: 16640331)
Nat Rev Drug Discov. 2019 Jun;18(6):463-477. (PMID: 30976107)
J Cancer Res Clin Oncol. 2019 Apr;145(4):829-837. (PMID: 30603908)
Chem Biol Drug Des. 2018 Jul;92(1):1272-1278. (PMID: 29536635)
ChemMedChem. 2016 Jun 20;11(12):1211-8. (PMID: 27154144)
IEEE Trans Neural Netw Learn Syst. 2018 Feb;29(2):457-469. (PMID: 27959823)
Drug Discov Today. 2018 Aug;23(8):1538-1546. (PMID: 29750902)
Mini Rev Med Chem. 2016;16(5):345-57. (PMID: 26423695)
Science. 2021 Dec 10;374(6573):eabm4805. (PMID: 34762488)
PLoS Comput Biol. 2019 Mar 27;15(3):e1006269. (PMID: 30917113)
Nature. 2019 Dec;576(7787):S49-S53. (PMID: 31853074)
J Digit Imaging. 2018 Dec;31(6):923-928. (PMID: 29948436)
Sci Rep. 2016 Sep 21;6:33534. (PMID: 27650168)
Nature. 2021 Aug;596(7873):583-589. (PMID: 34265844)
Sci Rep. 2015 Jun 22;5:11476. (PMID: 26098304)
EC Pharmacol Toxicol. 2017;SI(1):16-17. (PMID: 30215059)
Nat Chem Biol. 2011 Jun;7(6):327-30. (PMID: 21587249)
Comput Biol Med. 2018 Sep 1;100:270-278. (PMID: 28974302)
Cell. 2016 Nov 17;167(5):1281-1295.e18. (PMID: 27863244)
Nature. 2020 Jan;577(7792):706-710. (PMID: 31942072)
Methods Mol Biol. 2008;458:25-44. (PMID: 19065804)
IEEE Trans Pattern Anal Mach Intell. 2018 May;40(5):1245-1258. (PMID: 28489533)
Nat Biotechnol. 2017 Jul 12;35(7):604-605. (PMID: 28700560)
Mol Syst Biol. 2016 Jul 29;12(7):878. (PMID: 27474269)
NPJ Precis Oncol. 2020 Jun 15;4:19. (PMID: 32566759)
Expert Opin Drug Discov. 2020 Jul;15(7):755-764. (PMID: 32228116)
Bioinformatics. 2019 Dec 15;35(24):5191-5198. (PMID: 31116390)
J Chem Inf Model. 2014 Sep 22;54(9):2536-43. (PMID: 25133604)
JCO Precis Oncol. 2017 Nov;1:1-10. (PMID: 35172522)
BMC Bioinformatics. 2019 Aug 6;20(1):415. (PMID: 31387547)
Expert Opin Drug Discov. 2017 Sep;12(9):879-883. (PMID: 28685615)
Mol Inform. 2017 Jan;36(1-2):. (PMID: 27783464)
Front Med. 2020 Aug;14(4):450-469. (PMID: 31840200)
Bioorg Med Chem. 2009 Oct 1;17(19):6983-92. (PMID: 19734051)
Comput Biol Chem. 2019 Jun;80:90-101. (PMID: 30939415)
BMJ. 2019 Sep 13;366:l5434. (PMID: 31519553)
BMC Bioinformatics. 2018 Dec 21;19(Suppl 20):502. (PMID: 30577745)
J Mol Graph Model. 2002 Jan;20(4):269-76. (PMID: 11858635)
Contributed Indexing:
Keywords: artificial intelligence (AI); deep learning; deep neural network; drug response; multilayer neural network (MNN); quantitative structure activity relationship (QSAR); triple-negative breast cancer (TNBC)
Entry Date(s):
Date Created: 20230410 Latest Revision: 20230411
Update Code:
20250114
PubMed Central ID:
PMC10076891
DOI:
10.3389/frai.2023.1069353
PMID:
37035534
Database:
MEDLINE

Weitere Informationen

Accurate prediction of drug response is a crucial step in personalized medicine. Recently, deep learning techniques have been witnessed with significant breakthroughs in a variety of areas including biomedical research and chemogenomic applications. This motivated us to develop a novel deep learning platform to accurately and reliably predict the response of cancer cells to different drug treatments. In the present work, we describe a Java-based implementation of deep neural network method, termed JavaDL, to predict cancer responses to drugs solely based on their chemical features. To this end, we devised a novel cost function and added a regularization term which suppresses overfitting. We also adopted an early stopping strategy to further reduce overfit and improve the accuracy and robustness of our models. To evaluate our method, we compared with several popular machine learning and deep neural network programs and observed that JavaDL either outperformed those methods in model building or obtained comparable predictions. Finally, JavaDL was employed to predict drug responses of several aggressive breast cancer cell lines, and the results showed robust and accurate predictions with r<sup>2</sup> as high as 0.81.
(Copyright © 2023 Huang, Fong, Chaudhari and Zhang.)

Author RC is currently employed by the company Eurofins Beacon Discovery. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.