Deep Learning for Drug Discovery and Cancer Research: Automated Analysis of Vascularization Images.

Bibliographic Details
Title:	Deep Learning for Drug Discovery and Cancer Research: Automated Analysis of Vascularization Images.
Authors:	Urban G, Bache KM, Phan D, Sobrino A, Shmakov AK, Hachey SJ, Hughes C, Baldi P
Source:	IEEE/ACM transactions on computational biology and bioinformatics [IEEE/ACM Trans Comput Biol Bioinform] 2019 May-Jun; Vol. 16 (3), pp. 1029-1035. Date of Electronic Publication: 2018 May 29.
Publication Type:	Journal Article; Research Support, N.I.H., Extramural; Research Support, Non-U.S. Gov't; Research Support, U.S. Gov't, Non-P.H.S.
Language:	English
Journal Info:	Publisher: IEEE Computer Society Country of Publication: United States NLM ID: 101196755 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1557-9964 (Electronic) Linking ISSN: 15455963 NLM ISO Abbreviation: IEEE/ACM Trans Comput Biol Bioinform Subsets: MEDLINE
Imprint Name(s):	Original Publication: New York, NY : IEEE Computer Society, 2004-
MeSH Terms:	Deep Learning* , Image Processing, Computer-Assisted, Antineoplastic Agents/pharmacology , Drug Discovery/methods , Neoplasms/drug therapy , Neovascularization, Pathologic/*diagnostic imaging, Cell Culture Techniques ; Extracellular Matrix/metabolism ; Humans ; Microscopy ; Neoplasms/diagnostic imaging ; Neural Networks, Computer ; Pattern Recognition, Automated
Abstract:	Likely drug candidates which are identified in traditional pre-clinical drug screens often fail in patient trials, increasing the societal burden of drug discovery. A major contributing factor to this phenomenon is the failure of traditional in vitro models of drug response to accurately mimic many of the more complex properties of human biology. We have recently introduced a new microphysiological system for growing vascularized, perfused microtissues that more accurately models human physiology and is suitable for large drug screens. In this work, we develop a machine learning model that can quickly and accurately flag compounds which effectively disrupt vascular networks from images taken before and after drug application in vitro. The system is based on a convolutional neural network and achieves near perfect accuracy while committing potentially no expensive false negatives.
References:	Mol Inform. 2016 Jan;35(1):3-14. (PMID: 27491648) Tissue Eng Part C Methods. 2013 Sep;19(9):730-7. (PMID: 23320912) Nat Rev Drug Discov. 2015 Apr;14(4):248-60. (PMID: 25792263) Nature. 2017 Feb 2;542(7639):115-118. (PMID: 28117445) Comput Struct Biotechnol J. 2016 May 10;14:207-210. (PMID: 27904714) Sci Rep. 2015 Mar 09;5:8883. (PMID: 25748532) Comput Biol Med. 2017 May 1;84:137-146. (PMID: 28364643) Annu Rev Biomed Eng. 2011 Aug 15;13:55-72. (PMID: 21513459) Lab Chip. 2016 Jul 5;16(14):2719-29. (PMID: 27332143) IEEE Trans Med Imaging. 2017 May;36(5):1172-1181. (PMID: 28113340) PLoS One. 2011;6(11):e27385. (PMID: 22110636) Nat Rev Drug Discov. 2013 Aug;12(8):569. (PMID: 23903212) IEEE Trans Pattern Anal Mach Intell. 2008 Oct;30(10):1858-65. (PMID: 18703836) Expert Opin Orphan Drugs. 2016;4(11):1113-1121. (PMID: 28626620) Sci Rep. 2016 Aug 23;6:31589. (PMID: 27549930) Lab Chip. 2013 Sep 21;13(18):3588-98. (PMID: 23743770) Biomicrofluidics. 2015 Oct 26;9(5):054124. (PMID: 26576206) Exp Biol Med (Maywood). 2014 Sep;239(9):1073-7. (PMID: 24962171) Nat Rev Drug Discov. 2012 Mar 01;11(3):191-200. (PMID: 22378269) Stem Cell Res Ther. 2013;4 Suppl 1:I1. (PMID: 24565163) Lab Chip. 2017 Jan 31;17(3):511-520. (PMID: 28092382) J Cheminform. 2015 Dec 29;7:63. (PMID: 26719774) Science. 2010 Jun 25;328(5986):1662-8. (PMID: 20576885) Lab Chip. 2016 Jan 21;16(2):282-90. (PMID: 26616908)
Grant Information:	P30 CA062203 United States CA NCI NIH HHS; R01 CA180122 United States CA NCI NIH HHS; UG3 HL141799 United States HL NHLBI NIH HHS; UH3 TR000481 United States TR NCATS NIH HHS
Substance Nomenclature:	0 (Antineoplastic Agents)
Entry Date(s):	Date Created: 20180712 Date Completed: 20200220 Latest Revision: 20210226
Update Code:	20221216
PubMed Central ID:	PMC7904235
DOI:	10.1109/TCBB.2018.2841396
PMID:	29993583
Database:	MEDLINE

Description
ISSN:	1557-9964
DOI:	10.1109/TCBB.2018.2841396