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

Andrés Halabi, Elizabeth Rincón, Eduardo Chamorro

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

Abstract

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.

Original languageEnglish
Article number105347
JournalToxicology in Vitro
Volume81
DOIs
Publication statusPublished - Jun 2022

Keywords

  • Activated Metabolites
  • Aromatic amines
  • Carcinogenic activity
  • Carcinogenic potency
  • DFT
  • J48Consolidated
  • JCHAIDStar
  • Machine learning
  • Nitroaromatics
  • QSAR
  • RandomTree
  • Solvent Effects
  • SPAARC
  • WEKA

ASJC Scopus subject areas

  • Toxicology

Fingerprint

Dive into the research topics of 'Machine learning predictive classification models for the carcinogenic activity of activated metabolites derived from aromatic amines and nitroaromatics'. Together they form a unique fingerprint.

Cite this