Chemical Space Networks Enhance Toxicity Recognition via Graph Embedding
Journal of Chemical Information and Modeling · 24.02.2025 · 65 (4) · 1850-1861
DOI: 10.1021/acs.jcim.4c02140 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 06.02.2025. Verfasst von F Mastrolorito und 12 weiteren Autor:innen. Beteiligte Einrichtung: Dipartimento di Farmacia-Scienze del Farmaco, Universit̀a degli studi di Bari Aldo Moro, Bari 70125, Italy. Hauptthemen laut MEDLINE: Neural Networks, Computer. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 71 Literaturangaben.
Abstract (Originalsprache)
Chemical space networks (CSNs) are a new effective strategy for detecting latent chemical patterns irrespective of defined coordinate systems based on molecular descriptors and fingerprints. CSNs can be a new powerful option as a new approach method and increase the capacity of assessing potential adverse impacts of chemicals on human health. Here, CSNs are shown to effectively characterize the toxicity of chemicals toward several human health end points, namely chromosomal aberrations, mutagenicity, carcinogenicity, developmental toxicity, skin irritation, estrogenicity, androgenicity, and hepatoxicity. In this work, we report how the content from CSNs structure can be embedded through graph neural networks into a metric space, which, for eight different toxicological human health end points, allows better discrimination of toxic and nontoxic chemicals. In fact, using embeddings returns, on average, an increase in predictive performances. In fact, embedding employment enhances the learning, leading to an increment of the classification performance of +12% in terms of the area under the ROC curve. Moreover, through a dedicated eXplainable Artificial Intelligence framework, a straight interpretation of results is provided through the detection of putative structural alerts related to a given toxicity. Hence, the proposed approach represents a step forward in the area of alternative methods and could lead to breakthrough innovations in the design of safer chemicals and drugs.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Dipartimento di Farmacia-Scienze del Farmaco, Universit̀a degli studi di Bari Aldo Moro, Bari 70125, Italy.
- Divisione di Genetica Medica, IRCCS Casa Sollievo della Sofferenza, San Giovanni Rotondo 71013, Italy.
- Dipartimento di Chimica, Universit̀a degli studi di Bari Aldo Moro, Bari 70121, Italy.
- Istituto Nazionale di Fisica Nucleare, Sezione di Bari, via E. Orabona, 4, 70125 Bari, Italy.
- Dipartimento Interateneo di Fisica, Universit̀a degli studi di Bari Aldo Moro, Bari 70121, Italy.
ORCID-Profile: N Gambacorta, O Nicolotti
Zitieren
APA
Mastrolorito, F., Gambacorta, N., Ciriaco, F., Cutropia, F., Togo, M. V., Belgiovine, V., Tondo, A. R., Trisciuzzi, D., Monaco, A., Bellotti, R., Altomare, C. D., Nicolotti, O., & Amoroso, N. (2025). Chemical Space Networks Enhance Toxicity Recognition via Graph Embedding. Journal of Chemical Information and Modeling, 65(4), 1850-1861. https://doi.org/10.1021/acs.jcim.4c02140
Vancouver
Mastrolorito F, Gambacorta N, Ciriaco F, Cutropia F, Togo MV, Belgiovine V, et al. Chemical Space Networks Enhance Toxicity Recognition via Graph Embedding. Journal of Chemical Information and Modeling. 2025;65(4):1850-1861. doi:10.1021/acs.jcim.4c02140
BibTeX
@article{Mastrolorito2025,
author = {Mastrolorito, F and Gambacorta, N and Ciriaco, F and Cutropia, F and Togo, Maria Vittoria and Belgiovine, V and Tondo, A R and Trisciuzzi, D and Monaco, A and Bellotti, R and Altomare, C D and Nicolotti, O and Amoroso, N},
title = {Chemical Space Networks Enhance Toxicity Recognition via Graph Embedding},
journal = {Journal of Chemical Information and Modeling},
year = {2025},
volume = {65},
number = {4},
pages = {1850--1861},
doi = {10.1021/acs.jcim.4c02140}
}
EUVIMED