Opening the Random Forest Black Box of
characterization
chemometrics
classification
machine learning
nuclear magnetic resonance spectroscopy
random forest
surrogate minimal depth
truffles
variable relations
variable selection
Journal
Metabolites
ISSN: 2218-1989
Titre abrégé: Metabolites
Pays: Switzerland
ID NLM: 101578790
Informations de publication
Date de publication:
13 Oct 2023
13 Oct 2023
Historique:
received:
18
09
2023
revised:
05
10
2023
accepted:
10
10
2023
medline:
27
10
2023
pubmed:
27
10
2023
entrez:
27
10
2023
Statut:
epublish
Résumé
The untargeted metabolomics analysis of biological samples with nuclear magnetic resonance (NMR) provides highly complex data containing various signals from different molecules. To use these data for classification, e.g., in the context of food authentication, machine learning methods are used. These methods are usually applied as a black box, which means that no information about the complex relationships between the variables and the outcome is obtained. In this study, we show that the random forest-based approach surrogate minimal depth (SMD) can be applied for a comprehensive analysis of class-specific differences by selecting relevant variables and analyzing their mutual impact on the classification model of different truffle species. SMD allows the assignment of variables from the same metabolites as well as the detection of interactions between different metabolites that can be attributed to known biological relationships.
Identifiants
pubmed: 37887402
pii: metabo13101075
doi: 10.3390/metabo13101075
pmc: PMC10608983
pii:
doi:
Types de publication
Journal Article
Langues
eng
Subventions
Organisme : Federal Ministry of Food and Agriculture (BMEL)
ID : 2816500914
Références
Microb Cell. 2019 Apr 24;6(5):217-256
pubmed: 31114794
PLoS One. 2015 Jul 10;10(7):e0132369
pubmed: 26162077
Curr Opin Plant Biol. 2002 Jun;5(3):250-7
pubmed: 11960744
Brief Bioinform. 2019 Mar 22;20(2):492-503
pubmed: 29045534
Prog Nucl Magn Reson Spectrosc. 2016 Feb;92-93:18-53
pubmed: 26952191
Biochem J. 1968 Jan;106(2):461-9
pubmed: 5637353
Anal Chem. 2005 Mar 1;77(5):1282-9
pubmed: 15732908
Curr Metabolomics. 2013;1(1):92-107
pubmed: 26078916
Front Microbiol. 2019 Sep 25;10:2227
pubmed: 31608041
Metabolites. 2023 Jul 25;13(8):
pubmed: 37623826
NMR Biomed. 2022 Feb;35(2):e4638
pubmed: 34738674
ACS Nano. 2019 Aug 27;13(8):9363-9375
pubmed: 31314989
Anal Chim Acta. 2009 Jan 26;632(2):221-8
pubmed: 19110097
J Agric Food Chem. 2018 Dec 19;66(50):13328-13339
pubmed: 30472843
Metabolomics. 2018;14(3):31
pubmed: 29479299
J Agric Food Chem. 2018 Nov 7;66(44):11873-11879
pubmed: 30350982
Eur J Cell Biol. 2011 Sep;90(9):759-69
pubmed: 21700357
Anal Chem. 2006 Jan 15;78(2):363-71
pubmed: 16408915
Plant Physiol. 1984 Oct;76(2):395-9
pubmed: 16663852
Nat Protoc. 2020 Aug;15(8):2538-2567
pubmed: 32681152
Metabolites. 2021 Dec 21;12(1):
pubmed: 35050127
Nucleic Acids Res. 2023 Jan 6;51(D1):D368-D376
pubmed: 36478084
Plant Physiol. 1985 Feb;77(2):499-502
pubmed: 16664085
Sci Rep. 2020 Mar 25;10(1):5436
pubmed: 32214194
Brief Bioinform. 2007 Sep;8(5):279-93
pubmed: 17626065
Bioinformatics. 2023 Aug 1;39(8):
pubmed: 37522865
Electrophoresis. 2012 Aug;33(15):2290-313
pubmed: 22887151
Anal Chem. 2015 Apr 7;87(7):3864-70
pubmed: 25674812
Appl Microbiol Biotechnol. 2008 Mar;78(3):379-89
pubmed: 18214471
Comput Struct Biotechnol J. 2016 Mar 09;14:135-53
pubmed: 27087910
Bioinformatics. 2019 Oct 1;35(19):3663-3671
pubmed: 30824905
J Proteome Res. 2015 Jun 5;14(6):2642-8
pubmed: 25881480
Appl Environ Microbiol. 1986 Jul;52(1):128-33
pubmed: 16347099
Genetics. 2008 Jan;178(1):185-95
pubmed: 18202367
Curr Opin Biotechnol. 2017 Feb;43:34-40
pubmed: 27580257
Plant Mol Biol. 2002 Jan;48(1-2):155-71
pubmed: 11860207
Sci Rep. 2023 Sep 22;13(1):15834
pubmed: 37740032
J Magn Reson. 2015 Nov;260:144-60
pubmed: 26476597
Phytochem Anal. 2014 Jul-Aug;25(4):291-306
pubmed: 24523261
Metabolomics. 2019 Oct 18;15(11):142
pubmed: 31628551
PLoS One. 2015 May 27;10(5):e0124219
pubmed: 26017271
High Throughput. 2018 Apr 18;7(2):
pubmed: 29670016
Can J Microbiol. 2001 Mar;47(3):264-8
pubmed: 11315117
Annu Rev Plant Physiol Plant Mol Biol. 1996 Jun;47:569-593
pubmed: 15012301