Prediction of Drug Side Effects with a Refined Negative Sample Selection Strategy.
Journal
Computational and mathematical methods in medicine
ISSN: 1748-6718
Titre abrégé: Comput Math Methods Med
Pays: United States
ID NLM: 101277751
Informations de publication
Date de publication:
2020
2020
Historique:
received:
28
01
2020
revised:
14
04
2020
accepted:
23
04
2020
entrez:
27
5
2020
pubmed:
27
5
2020
medline:
27
3
2021
Statut:
epublish
Résumé
Drugs are an important way to treat various diseases. However, they inevitably produce side effects, bringing great risks to human bodies and pharmaceutical companies. How to predict the side effects of drugs has become one of the essential problems in drug research. Designing efficient computational methods is an alternative way. Some studies paired the drug and side effect as a sample, thereby modeling the problem as a binary classification problem. However, the selection of negative samples is a key problem in this case. In this study, a novel negative sample selection strategy was designed for accessing high-quality negative samples. Such strategy applied the random walk with restart (RWR) algorithm on a chemical-chemical interaction network to select pairs of drugs and side effects, such that drugs were less likely to have corresponding side effects, as negative samples. Through several tests with a fixed feature extraction scheme and different machine-learning algorithms, models with selected negative samples produced high performance. The best model even yielded nearly perfect performance. These models had much higher performance than those without such strategy or with another selection strategy. Furthermore, it is not necessary to consider the balance of positive and negative samples under such a strategy.
Identifiants
pubmed: 32454877
doi: 10.1155/2020/1573543
pmc: PMC7232712
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
1573543Informations de copyright
Copyright © 2020 Haiyan Liang et al.
Déclaration de conflit d'intérêts
The authors declare that there is no conflict of interest regarding the publication of this paper.
Références
Biomed Res Int. 2013;2013:485034
pubmed: 24078917
PLoS One. 2017 May 4;12(5):e0177017
pubmed: 28472169
Nucleic Acids Res. 2010 Jul;38(Web Server issue):W652-6
pubmed: 20460463
BMC Syst Biol. 2017 Mar 14;11(Suppl 2):9
pubmed: 28361676
Comb Chem High Throughput Screen. 2020;23(4):274-284
pubmed: 31267864
Biochim Biophys Acta. 1975 Oct 20;405(2):442-51
pubmed: 1180967
PLoS One. 2011;6(12):e29491
pubmed: 22220213
Math Biosci. 2018 Dec;306:136-144
pubmed: 30296417
Mol Biosyst. 2014 Apr;10(4):868-77
pubmed: 24492783
Mol Syst Biol. 2010;6:343
pubmed: 20087340
Bioinformatics. 2020 Mar 1;36(5):1391-1396
pubmed: 31593226
Mol Ther Methods Clin Dev. 2018 Jun 21;10:57-67
pubmed: 30069494
Sci Rep. 2017 Apr 13;7(1):872
pubmed: 28408735
Int J Mol Sci. 2017 May 13;18(5):
pubmed: 28505077
J Am Med Inform Assoc. 2012 Jun;19(e1):e28-35
pubmed: 22718037
BMC Bioinformatics. 2011 May 18;12:169
pubmed: 21586169
BMC Bioinformatics. 2019 Feb 4;19(Suppl 13):554
pubmed: 30717666
BMC Bioinformatics. 2018 Dec 28;19(Suppl 21):476
pubmed: 30591036
Biochim Biophys Acta Mol Basis Dis. 2018 Jun;1864(6 Pt B):2228-2240
pubmed: 29247833
J Chem Inf Model. 2012 Dec 21;52(12):3284-92
pubmed: 23157436
BMC Bioinformatics. 2015 Nov 04;16:365
pubmed: 26537615
Interdiscip Sci. 2017 Sep;9(3):434-444
pubmed: 28516319
PLoS One. 2012;7(4):e35254
pubmed: 22514724
J Am Chem Soc. 2003 Oct 1;125(39):11853-65
pubmed: 14505407
Biochim Biophys Acta Mol Basis Dis. 2018 Jun;1864(6 Pt B):2284-2293
pubmed: 29197663
Am J Hum Genet. 2008 Apr;82(4):949-58
pubmed: 18371930
IEEE J Biomed Health Inform. 2019 Nov;23(6):2619-2632
pubmed: 30507518
Nucleic Acids Res. 2014 Jan;42(Database issue):D401-7
pubmed: 24293645
J Comput Biol. 2011 Mar;18(3):207-18
pubmed: 21385029
Biochim Biophys Acta Mol Basis Dis. 2018 Jun;1864(6 Pt B):2369-2375
pubmed: 29237571
AMIA Annu Symp Proc. 2017 Feb 10;2016:924-933
pubmed: 28269889
Brief Bioinform. 2019 Jan 18;20(1):190-202
pubmed: 28968655
Nucleic Acids Res. 2008 Jan;36(Database issue):D684-8
pubmed: 18084021
PLoS One. 2012;7(9):e45944
pubmed: 23029334