Mechanistic Expert Call Datasets Provide In Silico Prediction of Teratogenicity for a Wider Chemical Space
This poster was presented at the 2016 Society of Toxicology Annual Meeting.
The scarcity of teratogenicity data and the cost of in vivo reproductive toxicity studies are driving the use of a wider range of assays, where the relationship between data and teratogenicity can be established. Similarly this lack of data is affecting the applicability domain of prediction systems for teratogenicity. Using an adverse outcome pathway (AOP) framework, key events (KE) leading to teratogenicity can be mapped and suitable in vitro and in vivo assays, which model the KEs can be identified.
This type of relevant data is available for a significantly larger number of chemicals in comparison to teratogenicity data, which in turn can be mined to extract useful knowledge allowing for teratogenicity predictions for a wider chemical space. This mechanistic approach provides a clear rationale between a specific molecular initiating event (MIE) or KE and a toxicity endpoint.
During this study three AOPs (estrogen receptor modulation (ERM), androgen receptor modulation (ARM) & 5alpha-reductase inhibition (5aRI)) which have a strong association with teratogenicity were mapped. Relevant data for the MIEs and KEs identified were gathered from ChEMBL and curated into structured Lhasa mechanistic expert call activity datasets (LMEADs) (Fig 1). These purposeful datasets were then mined for the creation of MIE structural alerts for Derek Nexus, a transparent in silico expert system for toxicity prediction.