Chemistry-Based Modeling on Phenotype-Based Drug-Induced Liver Injury Annotation: From Public to Proprietary Data
Chemical Research in Toxicology · 2023
DOI: 10.1021/acs.chemrestox.2c00378 ↗Kurz gefasst
Fachartikel in der Zeitschrift Chemical Research in Toxicology, 2023. Verfasst von Mohammad Moein und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Aalto University, Konemiehentie 2, 02150 Espoo, Finland. Hauptthemen laut MEDLINE: Chemical and Drug Induced Liver Injury, Drug-Related Side Effects and Adverse Reactions. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: UK Research and Innovation, Janssen Pharmaceuticals.
Abstract (Originalsprache)
Drug-induced liver injury (DILI) is an important safety concern and a major reason to remove a drug from the market. Advancements in recent machine learning methods have led to a wide range of in silico models for DILI predictive methods based on molecule chemical structures (fingerprints). Existing publicly available DILI data sets used for model building are based on the interpretation of drug labels or patient case reports, resulting in a typical binary clinical DILI annotation. We developed a novel phenotype-based annotation to process hepatotoxicity information extracted from repeated dose in vivo preclinical toxicology studies using INHAND annotation to provide a more informative and reliable data set for machine learning algorithms. This work resulted in a data set of 430 unique compounds covering diverse liver pathology findings which were utilized to develop multiple DILI prediction models trained on the publicly available data (TG-GATEs) using the compound's fingerprint. We demonstrate that the TG-GATEs compounds DILI labels can be predicted well and how the differences between TG-GATEs and the external test compounds (Johnson & Johnson) impact the model generalization performance.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Computer Science, Aalto University, Konemiehentie 2, 02150 Espoo, Finland.
- Predictive, Investigative and Translational Toxicology, PSTS, Janssen Research & Development, Pharmaceutical Companies of Johnson & Johnson, 2340 Beerse, Belgium.
- Pathology, PSTS, Janssen Research & Development, Pharmaceutical Companies of Johnson & Johnson, 2340 Beerse, Belgium.
- Johnson & Johnson Innovation-JLABS, 661 University Avenue, CA014 ON Toronto, Canada.
- Predictive, Investigative and Translational Toxicology, PSTS, Janssen Research & Development, Pharmaceutical Companies of Johnson & Johnson, 3210 Merryfield Row, San Diego, California 92121, United States.
- In-Silico Discovery, Janssen Pharmaceutica, Janssen Research & Development, Pharmaceutical Companies of Johnson & Johnson, 2340 Beerse, Belgium.
ORCID-Profile: Mohammad Moein, Dorota Herman
Förderung
- UK Research and Innovation
- Janssen Pharmaceuticals
Zitieren
APA
Moein, M., Heinonen, M., Mesens, N., Chamanza, R., Amuzie, C., Will, Y., Ceulemans, H., Kaski, S., & Herman, D. (2023). Chemistry-Based Modeling on Phenotype-Based Drug-Induced Liver Injury Annotation: From Public to Proprietary Data. Chemical Research in Toxicology. https://doi.org/10.1021/acs.chemrestox.2c00378
Vancouver
Moein M, Heinonen M, Mesens N, Chamanza R, Amuzie C, Will Y, et al. Chemistry-Based Modeling on Phenotype-Based Drug-Induced Liver Injury Annotation: From Public to Proprietary Data. Chemical Research in Toxicology. 2023. doi:10.1021/acs.chemrestox.2c00378
BibTeX
@article{Moein2023,
author = {Moein, Mohammad and Heinonen, Markus and Mesens, Natalie and Chamanza, Ronnie and Amuzie, Chidozie and Will, Yvonne and Ceulemans, Hugo and Kaski, Samuel and Herman, Dorota},
title = {Chemistry-Based Modeling on Phenotype-Based Drug-Induced Liver Injury Annotation: From Public to Proprietary Data},
journal = {Chemical Research in Toxicology},
year = {2023},
doi = {10.1021/acs.chemrestox.2c00378}
}
EUVIMED