EUVIMEDEUVIMED entdecken
Crossref

TIRESIA: An eXplainable Artificial Intelligence Platform for Predicting Developmental Toxicity

Maria Vittoria Togo, Fabrizio Mastrolorito, Fulvio Ciriaco, Daniela Trisciuzzi, Anna Rita Tondo, Nicola Gambacorta, Loredana Bellantuono, Alfonso Monaco, Francesco Leonetti, Roberto Bellotti, Cosimo Damiano Altomare, Nicola Amoroso und 1 weitere

Journal of Chemical Information and Modeling · 09.01.2023 · 63 (1) · 56-66

DOI: 10.1021/acs.jcim.2c01126 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 15.12.2022. Verfasst von Maria Vittoria Togo und 12 weiteren Autor:innen. Beteiligte Einrichtung: Dipartimento di Farmacia-Scienze del Farmaco, Università degli Studi di Bari Aldo Moro, 70125Bari, Italy. Hauptthemen laut MEDLINE: Artificial Intelligence, Algorithms. Die Arbeit wurde bisher 54-mal zitiert (Crossref) und nennt 72 Literaturangaben. Gefördert von: Universita degli Studi di Bari Aldo Moro, European Social Fund, Programma Operativo Nazionale Ricerca e Innovazione.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Herein, a robust and reproducible eXplainable Artificial Intelligence (XAI) approach is presented, which allows prediction of developmental toxicity, a challenging human-health endpoint in toxicology. The application of XAI as an alternative method is of the utmost importance with developmental toxicity being one of the most animal-intensive areas of regulatory toxicology. In this work, the established CAESAR (Computer Assisted Evaluation of industrial chemical Substances According to Regulations) training set made of 234 chemicals for model learning is employed. Two test sets, including as a whole 585 chemicals, were instead used for validation and generalization purposes. The proposed framework favorably compares with the state-of-the-art approaches in terms of accuracy, sensitivity, and specificity, thus resulting in a reliable support system for developmental toxicity ensuring informativeness, uncertainty estimation, generalization, and transparency. Based on the eXtreme Gradient Boosting (XGB) algorithm, our predictive model provides easy interpretative keys based on specific molecular descriptors and structural alerts enabling one to distinguish toxic and nontoxic chemicals. Inspired by the Organisation for Economic Co-operation and Development (OECD) principles for the validation of Quantitative Structure-Activity Relationships (QSARs) for regulatory purposes, the results are summarized in a standard report in portable document format, enclosing also details concerned with a density-based model applicability domain and SHAP (SHapley Additive exPlanations) explainability, the latter particularly useful to better understand the effective roles played by molecular features. Notably, our model has been implemented in TIRESIA (Toxicology Intelligence and Regulatory Evaluations for Scientific and Industry Applications), a free of charge web platform available at http://tiresia.uniba.it.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceAlgorithmsAnimalsHumansQuantitative Structure-Activity Relationship

Autor:innen und Institutionen

  • Dipartimento di Farmacia-Scienze del Farmaco, Università degli Studi di Bari Aldo Moro, 70125Bari, Italy.
  • Dipartimento di Chimica, Università degli Studi di Bari Aldo Moro, 70125, Bari, Italy.
  • Dipartimento di Biomedicina Traslazionale e Neuroscienze (DiBraiN), Università degli Studi di Bari Aldo Moro, 70124Bari, Italy.
  • Istituto Nazionale di Fisica Nucleare, Sezione di Bari, 70125Bari, Italy.
  • Dipartimento Interateneo di Fisica M. Merlin, Università degli Studi di Bari Aldo Moro, 70125Bari, Italy.

ORCID-Profile: Orazio Nicolotti

Förderung

  • Universita degli Studi di Bari Aldo Moro
  • European Social Fund
  • Programma Operativo Nazionale Ricerca e Innovazione
  • Casa Sollievo della Sofferenza
  • Comune di Bovino
  • PIANO STRALCIO

Zitieren

APA

Togo, M. V., Mastrolorito, F., Ciriaco, F., Trisciuzzi, D., Tondo, A. R., Gambacorta, N., Bellantuono, L., Monaco, A., Leonetti, F., Bellotti, R., Altomare, C. D., Amoroso, N., & Nicolotti, O. (2023). TIRESIA: An eXplainable Artificial Intelligence Platform for Predicting Developmental Toxicity. Journal of Chemical Information and Modeling, 63(1), 56-66. https://doi.org/10.1021/acs.jcim.2c01126

Vancouver

Togo MV, Mastrolorito F, Ciriaco F, Trisciuzzi D, Tondo AR, Gambacorta N, et al. TIRESIA: An eXplainable Artificial Intelligence Platform for Predicting Developmental Toxicity. Journal of Chemical Information and Modeling. 2023;63(1):56-66. doi:10.1021/acs.jcim.2c01126

BibTeX
@article{Togo2023,
  author = {Togo, Maria Vittoria and Mastrolorito, Fabrizio and Ciriaco, Fulvio and Trisciuzzi, Daniela and Tondo, Anna Rita and Gambacorta, Nicola and Bellantuono, Loredana and Monaco, Alfonso and Leonetti, Francesco and Bellotti, Roberto and Altomare, Cosimo Damiano and Amoroso, Nicola and Nicolotti, Orazio},
  title = {TIRESIA: An eXplainable Artificial Intelligence Platform for Predicting Developmental Toxicity},
  journal = {Journal of Chemical Information and Modeling},
  year = {2023},
  volume = {63},
  number = {1},
  pages = {56--66},
  doi = {10.1021/acs.jcim.2c01126}
}
Kostenlos starten →