Selection of safe artemisinin derivatives using a machine learning-based cardiotoxicity platform and in vitro and in vivo validation
- Publication type:
- Journal article
- Metadata:
-
- Autoren
- Onat Kadioglu
- Sabine M Klauck
- Edmond Fleischer
- Letian Shan
- Thomas Efferth
- Autoren-URL
- https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=fis-test-1&SrcAuth=WosAPI&KeyUT=WOS:000652979200002&DestLinkType=FullRecord&DestApp=WOS_CPL
- DOI
- 10.1007/s00204-021-03058-4
- eISSN
- 1432-0738
- Externe Identifier
- Clarivate Analytics Document Solution ID: TB9AI
- PubMed Identifier: 34021777
- ISSN
- 0340-5761
- Ausgabe der Veröffentlichung
- 7
- Zeitschrift
- ARCHIVES OF TOXICOLOGY
- Schlüsselwörter
- Artificial intelligence
- Cardiotoxicity
- Drug discovery
- Machine learning
- Paginierung
- 2485 - 2495
- Datum der Veröffentlichung
- 2021
- Status
- Published
- Titel
- Selection of safe artemisinin derivatives using a machine learning-based cardiotoxicity platform and in vitro and in vivo validation
- Sub types
- Article
- Ausgabe der Zeitschrift
- 95
Data source: Web of Science (Lite)
- Other metadata sources:
-
- Abstract
- <jats:title>Abstract</jats:title><jats:p>The majority of drug candidates fails the approval phase due to unwanted toxicities and side effects. Establishment of an effective toxicity prediction platform is of utmost importance, to increase the efficiency of the drug discovery process. For this purpose, we developed a toxicity prediction platform with machine-learning strategies. Cardiotoxicity prediction was performed by establishing a model with five parameters (arrhythmia, cardiac failure, heart block, hypertension, myocardial infarction) and additional toxicity predictions such as hepatotoxicity, reproductive toxicity, mutagenicity, and tumorigenicity are performed by using Data Warrior and Pro-Tox-II software. As a case study, we selected artemisinin derivatives to evaluate the platform and to provide a list of safe artemisinin derivatives. Artemisinin from <jats:italic>Artemisia annua</jats:italic> was described first as an anti-malarial compound and later its anticancer properties were discovered. Here, random forest feature selection algorithm was used for the establishment of cardiotoxicity models. High AUC scores above 0.830 were achieved for all five cardiotoxicity indications. Using a chemical library of 374 artemisinin derivatives as a case study, 7 compounds (deoxydihydro-artemisinin, 3-hydroxy-deoxy-dihydroartemisinin, 3-desoxy-dihydroartemisinin, dihydroartemisinin-furano acetate-d3, deoxyartemisinin, artemisinin G, artemisinin B) passed the toxicity filtering process for hepatotoxicity, mutagenicity, tumorigenicity, and reproductive toxicity in addition to cardiotoxicity. Experimental validation with the cardiomyocyte cell line AC16 supported the findings from the in silico cardiotoxicity model predictions. Transcriptomic profiling of AC16 cells upon artemisinin B treatment revealed a similar gene expression profile as that of the control compound, dexrazoxane. In vivo experiments with a Zebrafish model further substantiated the in silico and in vitro data, as only slight cardiotoxicity in picomolar range was observed. In conclusion, our machine-learning approach combined with in vitro and in vivo experimentation represents a suitable method to predict cardiotoxicity of drug candidates.</jats:p>
- Autoren
- Onat Kadioglu
- Sabine M Klauck
- Edmond Fleischer
- Letian Shan
- Thomas Efferth
- DOI
- 10.1007/s00204-021-03058-4
- eISSN
- 1432-0738
- ISSN
- 0340-5761
- Ausgabe der Veröffentlichung
- 7
- Zeitschrift
- Archives of Toxicology
- Sprache
- en
- Online publication date
- 2021
- Paginierung
- 2485 - 2495
- Datum der Veröffentlichung
- 2021
- Status
- Published
- Herausgeber
- Springer Science and Business Media LLC
- Herausgeber URL
- http://dx.doi.org/10.1007/s00204-021-03058-4
- Datum der Datenerfassung
- 2021
- Titel
- Selection of safe artemisinin derivatives using a machine learning-based cardiotoxicity platform and in vitro and in vivo validation
- Ausgabe der Zeitschrift
- 95
Data source: Crossref
- Abstract
- The majority of drug candidates fails the approval phase due to unwanted toxicities and side effects. Establishment of an effective toxicity prediction platform is of utmost importance, to increase the efficiency of the drug discovery process. For this purpose, we developed a toxicity prediction platform with machine-learning strategies. Cardiotoxicity prediction was performed by establishing a model with five parameters (arrhythmia, cardiac failure, heart block, hypertension, myocardial infarction) and additional toxicity predictions such as hepatotoxicity, reproductive toxicity, mutagenicity, and tumorigenicity are performed by using Data Warrior and Pro-Tox-II software. As a case study, we selected artemisinin derivatives to evaluate the platform and to provide a list of safe artemisinin derivatives. Artemisinin from Artemisia annua was described first as an anti-malarial compound and later its anticancer properties were discovered. Here, random forest feature selection algorithm was used for the establishment of cardiotoxicity models. High AUC scores above 0.830 were achieved for all five cardiotoxicity indications. Using a chemical library of 374 artemisinin derivatives as a case study, 7 compounds (deoxydihydro-artemisinin, 3-hydroxy-deoxy-dihydroartemisinin, 3-desoxy-dihydroartemisinin, dihydroartemisinin-furano acetate-d3, deoxyartemisinin, artemisinin G, artemisinin B) passed the toxicity filtering process for hepatotoxicity, mutagenicity, tumorigenicity, and reproductive toxicity in addition to cardiotoxicity. Experimental validation with the cardiomyocyte cell line AC16 supported the findings from the in silico cardiotoxicity model predictions. Transcriptomic profiling of AC16 cells upon artemisinin B treatment revealed a similar gene expression profile as that of the control compound, dexrazoxane. In vivo experiments with a Zebrafish model further substantiated the in silico and in vitro data, as only slight cardiotoxicity in picomolar range was observed. In conclusion, our machine-learning approach combined with in vitro and in vivo experimentation represents a suitable method to predict cardiotoxicity of drug candidates.
- Addresses
- Department of Pharmaceutical Biology, Institute of Pharmaceutical and Biomedical Sciences, Johannes Gutenberg University, Staudinger Weg 5, 55128, Mainz, Germany.
- Autoren
- Onat Kadioglu
- Sabine M Klauck
- Edmond Fleischer
- Letian Shan
- Thomas Efferth
- DOI
- 10.1007/s00204-021-03058-4
- eISSN
- 1432-0738
- Externe Identifier
- PubMed Identifier: 34021777
- PubMed Central ID: PMC8241674
- Funding acknowledgements
- Johannes Gutenberg-Universität Mainz:
- Open access
- true
- ISSN
- 0340-5761
- Ausgabe der Veröffentlichung
- 7
- Zeitschrift
- Archives of toxicology
- Schlüsselwörter
- Animals
- Zebrafish
- Artemisinins
- Software
- Cardiotoxicity
- Machine Learning
- Sprache
- eng
- Medium
- Print-Electronic
- Online publication date
- 2021
- Open access status
- Open Access
- Paginierung
- 2485 - 2495
- Datum der Veröffentlichung
- 2021
- Status
- Published
- Publisher licence
- CC BY
- Datum der Datenerfassung
- 2021
- Titel
- Selection of safe artemisinin derivatives using a machine learning-based cardiotoxicity platform and in vitro and in vivo validation.
- Sub types
- research-article
- Journal Article
- Ausgabe der Zeitschrift
- 95
Files
https://link.springer.com/content/pdf/10.1007/s00204-021-03058-4.pdf https://europepmc.org/articles/PMC8241674?pdf=render
Data source: Europe PubMed Central
- Abstract
- The majority of drug candidates fails the approval phase due to unwanted toxicities and side effects. Establishment of an effective toxicity prediction platform is of utmost importance, to increase the efficiency of the drug discovery process. For this purpose, we developed a toxicity prediction platform with machine-learning strategies. Cardiotoxicity prediction was performed by establishing a model with five parameters (arrhythmia, cardiac failure, heart block, hypertension, myocardial infarction) and additional toxicity predictions such as hepatotoxicity, reproductive toxicity, mutagenicity, and tumorigenicity are performed by using Data Warrior and Pro-Tox-II software. As a case study, we selected artemisinin derivatives to evaluate the platform and to provide a list of safe artemisinin derivatives. Artemisinin from Artemisia annua was described first as an anti-malarial compound and later its anticancer properties were discovered. Here, random forest feature selection algorithm was used for the establishment of cardiotoxicity models. High AUC scores above 0.830 were achieved for all five cardiotoxicity indications. Using a chemical library of 374 artemisinin derivatives as a case study, 7 compounds (deoxydihydro-artemisinin, 3-hydroxy-deoxy-dihydroartemisinin, 3-desoxy-dihydroartemisinin, dihydroartemisinin-furano acetate-d3, deoxyartemisinin, artemisinin G, artemisinin B) passed the toxicity filtering process for hepatotoxicity, mutagenicity, tumorigenicity, and reproductive toxicity in addition to cardiotoxicity. Experimental validation with the cardiomyocyte cell line AC16 supported the findings from the in silico cardiotoxicity model predictions. Transcriptomic profiling of AC16 cells upon artemisinin B treatment revealed a similar gene expression profile as that of the control compound, dexrazoxane. In vivo experiments with a Zebrafish model further substantiated the in silico and in vitro data, as only slight cardiotoxicity in picomolar range was observed. In conclusion, our machine-learning approach combined with in vitro and in vivo experimentation represents a suitable method to predict cardiotoxicity of drug candidates.
- Date of acceptance
- 2021
- Autoren
- Onat Kadioglu
- Sabine M Klauck
- Edmond Fleischer
- Letian Shan
- Thomas Efferth
- Autoren-URL
- https://www.ncbi.nlm.nih.gov/pubmed/34021777
- DOI
- 10.1007/s00204-021-03058-4
- eISSN
- 1432-0738
- Externe Identifier
- PubMed Central ID: PMC8241674
- Ausgabe der Veröffentlichung
- 7
- Zeitschrift
- Arch Toxicol
- Schlüsselwörter
- Artificial intelligence
- Cardiotoxicity
- Drug discovery
- Machine learning
- Animals
- Artemisinins
- Cardiotoxicity
- Machine Learning
- Software
- Zebrafish
- Sprache
- eng
- Country
- Germany
- Paginierung
- 2485 - 2495
- PII
- 10.1007/s00204-021-03058-4
- Datum der Veröffentlichung
- 2021
- Status
- Published
- Datum, an dem der Datensatz öffentlich gemacht wurde
- 2022
- Titel
- Selection of safe artemisinin derivatives using a machine learning-based cardiotoxicity platform and in vitro and in vivo validation.
- Sub types
- Journal Article
- Ausgabe der Zeitschrift
- 95
Data source: PubMed
- Author's licence
- CC-BY
- Autoren
- Onat Kadioglu
- Sabine M Klauck
- Edmond Fleischer
- Letian Shan
- Thomas Efferth
- Hosting institution
- Universitätsbibliothek Mainz
- Sammlungen
- JGU-Publikationen
- Resource version
- Published version
- DOI
- 10.1007/s00204-021-03058-4
- File(s) embargoed
- false
- Open access
- true
- ISSN
- 1432-0738
- Zeitschrift
- Archives of toxicology
- Schlüsselwörter
- 570 Biowissenschaften
- 570 Life sciences
- Sprache
- eng
- Open access status
- Open Access
- Paginierung
- 2485 - 2495
- Datum der Veröffentlichung
- 2021
- Public URL
- https://openscience.ub.uni-mainz.de/handle/20.500.12030/7226
- Herausgeber
- Springer
- Datum der Datenerfassung
- 2022
- Datum, an dem der Datensatz öffentlich gemacht wurde
- 2022
- Zugang
- Public
- Titel
- Selection of safe artemisinin derivatives using a machine learning-based cardiotoxicity platform and in vitro and in vivo validation
- Ausgabe der Zeitschrift
- 95
Files
selection_of_safe_artemisinin-20220624130755185.pdf
Data source: OPENSCIENCE.UB
- Beziehungen:
- Property of