Machine learning predictive classification models for the carcinogenic activity of activated metabolites derived from aromatic amines and nitroaromatics

A 3D-QSAR study based on DFT descriptors and machine learning calculations is presented in this work. Our goal has been to build predictive models for classifying the carcinogenic activity of a set of aromatic amines (AA) and nitroaromatic (NA) compounds. As the main result, we stress that calculati...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Toxicology in vitro Jg. 81; S. 105347
Hauptverfasser: Halabi, Andrés, Rincón, Elizabeth, Chamorro, Eduardo
Format: Journal Article
Sprache:Englisch
Veröffentlicht: England Elsevier Ltd 01.06.2022
Elsevier Science Ltd
Schlagworte:
Activated Metabolites
Amines
Aromatic amines
Carcinogenic activity
Carcinogenic potency
Carcinogens
Chemical potential
Classification
Decision trees
DFT
J48Consolidated
JCHAIDStar
Learning algorithms
Machine learning
Metabolites
Nitroaromatics
Prediction models
QSAR
RandomTree
Solvent Effects
Solvents
SPAARC
Structure-activity relationships
WEKA
Aromatic amines
SPAARC
WEKA
Carcinogenic activity
DFT
QSAR
Nitroaromatics
Machine learning
RandomTree
Solvent Effects
JCHAIDStar
Activated Metabolites
Carcinogenic potency
J48Consolidated
ISSN:0887-2333, 1879-3177, 1879-3177
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A 3D-QSAR study based on DFT descriptors and machine learning calculations is presented in this work. Our goal has been to build predictive models for classifying the carcinogenic activity of a set of aromatic amines (AA) and nitroaromatic (NA) compounds. As the main result, we stress that calculations must consider both the activated metabolites (derived from AA and NA species) and the water solvent to obtain reliable predictive classification models. We have obtained eight decision tree models that presented an accuracy of over 90% by using either Gázquez-Vela chemical potential (μ+) or the chemical hardness (η) of the activated metabolites in aqueous solvent. •Activated metabolites and solvent information is needed for predicting carcinogenic activity of nitro and aromatic amines.•Our models predicts carcinogenic activity with over 90% accuracy accordingly with high Cohen's kappa statistic values•For activated metabolites in the aqueous solvent phase, the electron-accepting chemical potential and hardness are essential.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0887-2333
1879-3177
1879-3177
DOI:10.1016/j.tiv.2022.105347