Optimization of an adverse outcome pathway network on chemical-induced cholestasis using an artificial intelligence-assisted data collection
Commonly used acronym: AOP
Scope of the method
- Human health
- Translational - Applied Research
- Other
Description
- AOP network
- Adverse outcome pathway
- Shiny application
- artificial intelligence
- weight-of-evidence assessment
- key events
- Data Collection
- cholestasis
- Mechanistic toxicology
- risk assessment
- chemical
- Drug-induced liver injury (DILI)
- Hepatotoxicity
Adverse outcome pathway (AOP) networks are versatile tools in toxicology and risk assessment that capture and visualize mechanisms driving toxicity originating from various data sources. They share a common structure consisting of a set of molecular initiating events and key events, connected by key event relationships, leading to the actual adverse outcome. AOP networks are to be considered living documents that should be frequently updated by feeding in new data. Such iterative optimization exercises are typically done manually, which not only is a time-consuming effort, but also bears the risk of overlooking critical data. The present study introduces a novel approach for AOP network optimization of a previously published AOP network on chemical-induced cholestasis using artificial intelligence to facilitate automated data collection followed by subsequent quantitative confidence assessment of molecular initiating events, key events, and key event relationships. Artificial intelligence-assisted data collection was performed by means of the free web platform Sysrev. The optimized AOP network was visualized using Cytoscape with the node size representing the incidence of the key event and the edge size indicating the total confidence in the key event relationship. This resulted in the identification of 38 and 135 unique key events and key event relationships, respectively. Transporter changes was the key event with the highest incidence, and formed the most confident key event relationship with the adverse outcome, cholestasis. This process led to the creation of an extensively informative AOP network focused on chemical-induced cholestasis. This optimized AOP network may serve as a mechanistic compass for the development of a battery of in vitro assays to reliably predict chemical-induced cholestatic injury.
- - Access to the free web platform Sysrev,
- - Cytoscap.
- Published in peer reviewed journal
Pros, cons & Future potential
- The optimized and fully assessed AOP network resulting from the present study provides an important contribution to this goal, and will thus assist in delivering safer chemicals, including pharmaceutical drugs, while using fewer animals.
- The AOP network optimized in the present study is in the first instance being used as the conceptual mechanistic basis for setting up a battery of in vitro assays to predict cholestatic liver injury induced by chemical compounds from various applicability domains. In fact, this is embedded in a 2-tiered testing approach, whereby first tier testing relies on measuring transcriptional changes indicative of cholestatic liver injury. Unlike other types of hepatotoxicity, such transcriptional signature for chemical-induced cholestatic liver insult does not have sufficient predictive value on its own, and hence cannot be used as a stand-alone method.
Predictive power can be considerably increased when following up with second tier testing by applying a battery of in vitro assays mechanistically anchored in the AOP network, in which each assay monitors a selected MIE and KE individually at the translational level, but preferably at the activity level.
References, associated documents and other information
This work was performed in the context of the ONTOX project (https://ontox-project.eu/) supported by the European Commission under the Horizon2020 Research and Innovation Framework program (grant number 963845 “ONTOX”).
Organisations
Vrije Universiteit Brussel (VUB)In Vitro Toxicology and Dermato-Cosmetology
In Vitro Toxicology and Dermato-Cosmetology
Belgium