Generative Model for Proposing Drug Candidates Satisfying Anticancer Properties Using a Conditional Variational Autoencoder.
Journal
ACS omega
ISSN: 2470-1343
Titre abrégé: ACS Omega
Pays: United States
ID NLM: 101691658
Informations de publication
Date de publication:
04 Aug 2020
04 Aug 2020
Historique:
received:
16
03
2020
accepted:
07
07
2020
entrez:
11
8
2020
pubmed:
11
8
2020
medline:
11
8
2020
Statut:
epublish
Résumé
Deep learning-based molecular generative models have successfully identified drug candidates with desired properties against biological targets of interest. However, syntactically invalid molecules generated from a deep learning-generated model hinder the model from being applied to drug discovery. Herein, we propose a conditional variational autoencoder (CVAE) as a generative model to propose drug candidates with the desired property outside a data set range. We train the CVAE using molecular fingerprints and corresponding GI50 (inhibition of growth by 50%) results for breast cancer cell lines instead of training with various physical properties for each molecule together. We confirm that the generated fingerprints, not included in the training data set, represent the desired property using the CVAE model. In addition, our method can be used as a query expansion method for searching databases because fingerprints generated using our method can be regarded as expanded queries.
Identifiants
pubmed: 32775866
doi: 10.1021/acsomega.0c01149
pmc: PMC7407547
doi:
Types de publication
Journal Article
Langues
eng
Pagination
18642-18650Informations de copyright
Copyright © 2020 American Chemical Society.
Déclaration de conflit d'intérêts
The authors declare no competing financial interest.
Références
Trends Pharmacol Sci. 2019 Aug;40(8):592-604
pubmed: 31320117
J Chem Inf Model. 2017 Apr 24;57(4):875-882
pubmed: 28257191
Mol Pharm. 2018 Oct 1;15(10):4398-4405
pubmed: 30180591
Nat Methods. 2016 Jun;13(6):521-7
pubmed: 27135972
J Chem Inf Model. 2016 Feb 22;56(2):286-99
pubmed: 26818135
J Cheminform. 2017 Sep 4;9(1):48
pubmed: 29086083
J Cheminform. 2015 May 20;7:20
pubmed: 26052348
J Chem Inf Model. 2005 Jan-Feb;45(1):177-82
pubmed: 15667143
Oncotarget. 2017 Feb 14;8(7):10883-10890
pubmed: 28029644
Sci Adv. 2018 Jul 25;4(7):eaap7885
pubmed: 30050984
J Chem Inf Model. 2010 May 24;50(5):742-54
pubmed: 20426451
J Chem Inf Model. 2019 Sep 23;59(9):3981-3988
pubmed: 31443612
Mol Inform. 2018 Jan;37(1-2):
pubmed: 29235269
Expert Opin Drug Discov. 2016;11(2):137-48
pubmed: 26558489
J Cheminform. 2018 Jul 11;10(1):31
pubmed: 29995272
Rev Sci Instrum. 2008 Jul;79(7):076106
pubmed: 18681743
J Cheminform. 2018 Jul 24;10(1):33
pubmed: 30043127
Nucleic Acids Res. 2009 Jul;37(Web Server issue):W623-33
pubmed: 19498078
J Comput Aided Mol Des. 2000 Jul;14(5):449-66
pubmed: 10896317
Nat Rev Cancer. 2006 Oct;6(10):813-23
pubmed: 16990858
Nucleic Acids Res. 2012 Jan;40(Database issue):D1100-7
pubmed: 21948594
Polymers (Basel). 2020 Jan 08;12(1):
pubmed: 31936321
J Chem Inf Model. 2019 Jan 28;59(1):43-52
pubmed: 30016587
Mol Pharm. 2017 Sep 5;14(9):3098-3104
pubmed: 28703000
ACS Cent Sci. 2018 Jan 24;4(1):120-131
pubmed: 29392184
Nat Med. 2018 Sep;24(9):1337-1341
pubmed: 30104767
J Cheminform. 2009 Apr 28;1:4
pubmed: 20142987
Drug Discov Today. 2018 Jun;23(6):1241-1250
pubmed: 29366762
ACS Cent Sci. 2018 Feb 28;4(2):268-276
pubmed: 29532027