EnsInfer: a simple ensemble approach to network inference outperforms any single method.
Gene regulatory networks
Machine learning
Non homogeneous ensemble
Transcriptional regulation
Journal
BMC bioinformatics
ISSN: 1471-2105
Titre abrégé: BMC Bioinformatics
Pays: England
ID NLM: 100965194
Informations de publication
Date de publication:
24 Mar 2023
24 Mar 2023
Historique:
received:
12
12
2022
accepted:
15
03
2023
medline:
28
3
2023
entrez:
25
3
2023
pubmed:
26
3
2023
Statut:
epublish
Résumé
This study evaluates both a variety of existing base causal inference methods and a variety of ensemble methods. We show that: (i) base network inference methods vary in their performance across different datasets, so a method that works poorly on one dataset may work well on another; (ii) a non-homogeneous ensemble method in the form of a Naive Bayes classifier leads overall to as good or better results than using the best single base method or any other ensemble method; (iii) for the best results, the ensemble method should integrate all methods that satisfy a statistical test of normality on training data. The resulting ensemble model EnsInfer easily integrates all kinds of RNA-seq data as well as new and existing inference methods. The paper categorizes and reviews state-of-the-art underlying methods, describes the EnsInfer ensemble approach in detail, and presents experimental results. The source code and data used will be made available to the community upon publication.
Identifiants
pubmed: 36964499
doi: 10.1186/s12859-023-05231-1
pii: 10.1186/s12859-023-05231-1
pmc: PMC10037858
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
114Subventions
Organisme : NIGMS NIH HHS
ID : R01 GM121753
Pays : United States
Organisme : NIH HHS
ID : R01GM121753-01A1
Pays : United States
Organisme : National Science Foundation
ID : MCB-1412232
Informations de copyright
© 2023. The Author(s).
Références
Mol Syst Biol. 2015 Nov 17;11(11):839
pubmed: 26577401
Cell Syst. 2017 Sep 27;5(3):251-267.e3
pubmed: 28957658
Commun Stat Appl Methods. 2015 Nov;22(6):665-674
pubmed: 26688802
Bioinformatics. 2018 Jan 15;34(2):258-266
pubmed: 28968704
Nat Methods. 2016 Apr;13(4):310-8
pubmed: 26901648
Nat Rev Genet. 2019 Nov;20(11):631-656
pubmed: 31341269
Bioinformatics. 2017 Mar 1;33(5):764-766
pubmed: 27993778
Brief Bioinform. 2021 Sep 2;22(5):
pubmed: 33539514
PLoS One. 2010 Sep 28;5(9):
pubmed: 20927193
Nat Methods. 2012 Jul 15;9(8):796-804
pubmed: 22796662
Genome Biol. 2016 Aug 17;17(1):173
pubmed: 27534536
Bioinformatics. 2022 Apr 28;38(9):2519-2528
pubmed: 35188184
Nat Methods. 2020 Feb;17(2):147-154
pubmed: 31907445
Proc Natl Acad Sci U S A. 2018 Jun 19;115(25):6494-6499
pubmed: 29769331
Sci Rep. 2020 Apr 22;10(1):6804
pubmed: 32321967
Curr Opin Biotechnol. 2020 Jun;63:89-98
pubmed: 31927423
Bioinformatics. 2020 Sep 15;36(18):4774-4780
pubmed: 33026066
Bioinformatics. 2017 Aug 01;33(15):2314-2321
pubmed: 28379368
Nat Commun. 2018 Feb 12;9(1):619
pubmed: 29434199
Bioinformatics. 2011 Aug 15;27(16):2263-70
pubmed: 21697125
Genome Biol. 2006;7(5):R36
pubmed: 16686963
Cell Syst. 2020 Mar 25;10(3):265-274.e11
pubmed: 32135093
Bioinformatics. 2019 Jun 1;35(11):1893-1900
pubmed: 30395189
PLoS One. 2010 Feb 23;5(2):e9202
pubmed: 20186320
Bioinformatics. 2019 Jun 1;35(12):2159-2161
pubmed: 30445495