Prediction of the Formation of Reactive Metabolites by A Novel Classifier Approach Based on Enrichment Factor Optimization (EFO) as Implemented in the VEGA Program.
Détails
Etat: Public
Version: Final published version
Licence: CC BY 4.0
ID Serval
serval:BIB_F10DAD8028D8
Type
Article: article d'un périodique ou d'un magazine.
Collection
Publications
Institution
Titre
Prediction of the Formation of Reactive Metabolites by A Novel Classifier Approach Based on Enrichment Factor Optimization (EFO) as Implemented in the VEGA Program.
Périodique
Molecules
ISSN
1420-3049 (Electronic)
ISSN-L
1420-3049
Statut éditorial
Publié
Date de publication
13/11/2018
Peer-reviewed
Oui
Volume
23
Numéro
11
Pages
E2955
Langue
anglais
Notes
Publication types: Journal Article
Publication Status: epublish
Publication Status: epublish
Résumé
The study is aimed at developing linear classifiers to predict the capacity of a given substrate to yield reactive metabolites. While most of the hitherto reported predictive models are based on the occurrence of known structural alerts (e.g., the presence of toxophoric groups), the present study is focused on the generation of predictive models involving linear combinations of physicochemical and stereo-electronic descriptors. The development of these models is carried out by using a novel classification approach based on enrichment factor optimization (EFO) as implemented in the VEGA suite of programs. The study took advantage of metabolic data as collected by manually curated analysis of the primary literature and published in the years 2004⁻2009. The learning set included 977 substrates among which 138 compounds yielded reactive first-generation metabolites, plus 212 substrates generating reactive metabolites in all generations (i.e., metabolic steps). The results emphasized the possibility of developing satisfactory predictive models especially when focusing on the first-generation reactive metabolites. The extensive comparison of the classifier approach presented here using a set of well-known algorithms implemented in Weka 3.8 revealed that the proposed EFO method compares with the best available approaches and offers two relevant benefits since it involves a limited number of descriptors and provides a score-based probability thus allowing a critical evaluation of the obtained results. The last analyses on non-cheminformatics UCI datasets emphasize the general applicability of the EFO approach, which conveniently performs using both balanced and unbalanced datasets.
Mots-clé
Algorithms, Biotransformation, Machine Learning, Models, Statistical, Pharmacological and Toxicological Phenomena, enrichment factor, machine learning, reactive metabolite, toxicity prediction, unbalanced datasets
Pubmed
Web of science
Open Access
Oui
Création de la notice
20/11/2018 9:39
Dernière modification de la notice
20/08/2019 17:18