Cargando…

Chemistry-Based Modeling on Phenotype-Based Drug-Induced Liver Injury Annotation: From Public to Proprietary Data

[Image: see text] 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 (finge...

Descripción completa

Detalles Bibliográficos
Autores principales: Moein, Mohammad, Heinonen, Markus, Mesens, Natalie, Chamanza, Ronnie, Amuzie, Chidozie, Will, Yvonne, Ceulemans, Hugo, Kaski, Samuel, Herman, Dorota
Formato: Online Artículo Texto
Lenguaje:English
Publicado: American Chemical Society 2023
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10445287/
https://www.ncbi.nlm.nih.gov/pubmed/37556769
http://dx.doi.org/10.1021/acs.chemrestox.2c00378
_version_ 1785094141766533120
author Moein, Mohammad
Heinonen, Markus
Mesens, Natalie
Chamanza, Ronnie
Amuzie, Chidozie
Will, Yvonne
Ceulemans, Hugo
Kaski, Samuel
Herman, Dorota
author_facet Moein, Mohammad
Heinonen, Markus
Mesens, Natalie
Chamanza, Ronnie
Amuzie, Chidozie
Will, Yvonne
Ceulemans, Hugo
Kaski, Samuel
Herman, Dorota
author_sort Moein, Mohammad
collection PubMed
description [Image: see text] 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.
format Online
Article
Text
id pubmed-10445287
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher American Chemical Society
record_format MEDLINE/PubMed
spelling pubmed-104452872023-08-24 Chemistry-Based Modeling on Phenotype-Based Drug-Induced Liver Injury Annotation: From Public to Proprietary Data Moein, Mohammad Heinonen, Markus Mesens, Natalie Chamanza, Ronnie Amuzie, Chidozie Will, Yvonne Ceulemans, Hugo Kaski, Samuel Herman, Dorota Chem Res Toxicol [Image: see text] 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. American Chemical Society 2023-08-09 /pmc/articles/PMC10445287/ /pubmed/37556769 http://dx.doi.org/10.1021/acs.chemrestox.2c00378 Text en © 2023 The Authors. Published by American Chemical Society https://creativecommons.org/licenses/by/4.0/Permits the broadest form of re-use including for commercial purposes, provided that author attribution and integrity are maintained (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Moein, Mohammad
Heinonen, Markus
Mesens, Natalie
Chamanza, Ronnie
Amuzie, Chidozie
Will, Yvonne
Ceulemans, Hugo
Kaski, Samuel
Herman, Dorota
Chemistry-Based Modeling on Phenotype-Based Drug-Induced Liver Injury Annotation: From Public to Proprietary Data
title Chemistry-Based Modeling on Phenotype-Based Drug-Induced Liver Injury Annotation: From Public to Proprietary Data
title_full Chemistry-Based Modeling on Phenotype-Based Drug-Induced Liver Injury Annotation: From Public to Proprietary Data
title_fullStr Chemistry-Based Modeling on Phenotype-Based Drug-Induced Liver Injury Annotation: From Public to Proprietary Data
title_full_unstemmed Chemistry-Based Modeling on Phenotype-Based Drug-Induced Liver Injury Annotation: From Public to Proprietary Data
title_short Chemistry-Based Modeling on Phenotype-Based Drug-Induced Liver Injury Annotation: From Public to Proprietary Data
title_sort chemistry-based modeling on phenotype-based drug-induced liver injury annotation: from public to proprietary data
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10445287/
https://www.ncbi.nlm.nih.gov/pubmed/37556769
http://dx.doi.org/10.1021/acs.chemrestox.2c00378
work_keys_str_mv AT moeinmohammad chemistrybasedmodelingonphenotypebaseddruginducedliverinjuryannotationfrompublictoproprietarydata
AT heinonenmarkus chemistrybasedmodelingonphenotypebaseddruginducedliverinjuryannotationfrompublictoproprietarydata
AT mesensnatalie chemistrybasedmodelingonphenotypebaseddruginducedliverinjuryannotationfrompublictoproprietarydata
AT chamanzaronnie chemistrybasedmodelingonphenotypebaseddruginducedliverinjuryannotationfrompublictoproprietarydata
AT amuziechidozie chemistrybasedmodelingonphenotypebaseddruginducedliverinjuryannotationfrompublictoproprietarydata
AT willyvonne chemistrybasedmodelingonphenotypebaseddruginducedliverinjuryannotationfrompublictoproprietarydata
AT ceulemanshugo chemistrybasedmodelingonphenotypebaseddruginducedliverinjuryannotationfrompublictoproprietarydata
AT kaskisamuel chemistrybasedmodelingonphenotypebaseddruginducedliverinjuryannotationfrompublictoproprietarydata
AT hermandorota chemistrybasedmodelingonphenotypebaseddruginducedliverinjuryannotationfrompublictoproprietarydata