Predicting the Mutagenic Activity of Nitroaromatics Using Conceptual Density Functional Theory Descriptors and Explainable No-Code Machine Learning Approaches
Journal of Chemical Information and Modeling · 2025
DOI: 10.1021/acs.jcim.4c02401 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, 2025. Verfasst von Andrés Halabi Diaz und 3 weiteren Autor:innen. Beteiligte Einrichtung: Departamento de Ciencias Químicas, Facultad de Ciencias Exactas, Universidad Andrés Bello, Avenida Republica 275, Santiago 8370146, Chile. Hauptthemen laut MEDLINE: Machine Learning, Mutagens, Density Functional Theory, Nitro Compounds. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 59 Literaturangaben. Gefördert von: Fondo Nacional de Desarrollo Cient?fico y Tecnol?gico, Agencia Nacional de Investigaci?n y Desarrollo.
Abstract (Originalsprache)
Nitroaromatic compounds (NAs) are widely used in industrial applications but pose significant genotoxic risks, necessitating accurate mutagenicity prediction for chemical safety assessments. This study integrates conceptual density functional theory (CDFT) descriptors with explainable no-code machine learning (ML) models to predict NA mutagenicity based on Ames test results. Following OECD QSAR guidelines, feature selection and model development were performed using decision-tree-based algorithms (Random Tree, JCHAID*, SPAARC) and multilayer perceptrons (MLPs). These models exhibited high predictive accuracy (internal: >80%, κ = 0.21-0.37; external: ∼90%, κ = 0.41-0.62) with strong interpretability. The study also explores the role of metabolic activation and aqueous-phase descriptors, evaluating a novel electronic analog to LogP (LogQP) to assess hydrophobicity-mutagenicity relationships. Results demonstrate that aqueous-phase electronic properties and electrophilicity descriptors outperform vacuum-based methods in mutagenicity prediction. The combination of CDFT descriptors with shallow ML models proves to be a robust, interpretable, and accessible framework for predictive toxicology. This approach enhances chemical risk assessment and bridges computational chemistry with toxicology for regulatory applications.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Departamento de Ciencias Químicas, Facultad de Ciencias Exactas, Universidad Andrés Bello, Avenida Republica 275, Santiago 8370146, Chile.
- Departamento de Investigación y Desarrollo, Good Global Research and Science (GGRS), Avenida Ramón Picarte 780, Valdivia 5090000, Chile.
- Departamento de I+D+i, CatchPredict SpA, Avenida Ramón Picarte 780, Valdivia 5090000, Chile.
- Centro de Química Teórica y Computacional (CQT&C), Departamento de Ciencias Químicas, Facultad de Ciencias Exactas, Universidad Andrés Bello, Avenida Republica 275, Santiago 8370146, Chile.
- Facultad de Ciencias, Instituto de Ciencias Químicas, Universidad Austral de Chile, Independencia 631, Valdivia 5090000, Chile.
- Facultad de Ingeniería, Arquitectura y Diseño, Universidad San Sebastián, Campus Ciudad Universitaria, Avenida del Cóndor 720, Huechuraba, Ciudad Empresarial, Santiago 8580704, Chile.
ORCID-Profile: Andrés Halabi Diaz, Eduardo Chamorro
Förderung
- Fondo Nacional de Desarrollo Cient?fico y Tecnol?gico
- Agencia Nacional de Investigaci?n y Desarrollo
Zitieren
APA
Halabi Diaz, A., Duque-Noreña, M., Rincón, E., & Chamorro, E. (2025). Predicting the Mutagenic Activity of Nitroaromatics Using Conceptual Density Functional Theory Descriptors and Explainable No-Code Machine Learning Approaches. Journal of Chemical Information and Modeling. https://doi.org/10.1021/acs.jcim.4c02401
Vancouver
Halabi Diaz A, Duque-Noreña M, Rincón E, Chamorro E. Predicting the Mutagenic Activity of Nitroaromatics Using Conceptual Density Functional Theory Descriptors and Explainable No-Code Machine Learning Approaches. Journal of Chemical Information and Modeling. 2025. doi:10.1021/acs.jcim.4c02401
BibTeX
@article{HalabiDiaz2025,
author = {Halabi Diaz, Andrés and Duque-Noreña, Mario and Rincón, Elizabeth and Chamorro, Eduardo},
title = {Predicting the Mutagenic Activity of Nitroaromatics Using Conceptual Density Functional Theory Descriptors and Explainable No-Code Machine Learning Approaches},
journal = {Journal of Chemical Information and Modeling},
year = {2025},
doi = {10.1021/acs.jcim.4c02401}
}
EUVIMED