Non-animal approaches are needed to assess an increasing number of chemicals for acute oral systemic toxicity potential (LD50). NICEATM and the ICCVAM Acute Toxicity Workgroup organized an international collaborative project to develop in silico models to predict LD50 and bridge data gaps. Participants from 35 groups submitted a total of 139 predictive models built using a dataset of 11,992 chemicals split into training (75%) and evaluation sets (25%). Crowdsourced models were developed for five endpoints: LD50 point estimates, EPA hazard categories, GHS hazard categories, very toxic (LD50 &lt; 50 mg/kg), and non-toxic (LD50 &gt; 2000 mg/kg). Predictions within the applicability domains of the submitted models were evaluated, then combined into consensus predictions based on a weight-of-evidence approach. The resulting consensus model, forming the Collaborative Acute Toxicity Modeling Suite (CATMoS), leverages the strengths and overcomes the limitations of individual modeling approaches. The consensus predictions are fully reproduceable and performed at least as well as independent replicates of in vivo acute oral toxicity assays. The CATMoS consensus model is available via the free and open-source tool OPERA (Open Structure-activity/property Relationship App). OPERA also provides predictions for physicochemical and pharmacokinetic properties and other toxicological endpoints with applicability domain and accuracy assessment. CATMoS predictions for the ~850k chemical structures in DSSTox are being made publicly accessible via NTP’s Integrated Chemical Environment and the EPA’s CompTox Chemicals Dashboard.

Collaborative modeling project for predicting acute oral toxicity (CATMoS)

ACS Fall 2020 Virtual Meeting

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.