The performance, reliability and potential application of in silico models for predicting the acute oral toxicity of pharmaceutical compounds

Acute oral toxicity (AOT) information is utilized to categorize compounds according to the severity of their hazard and used to inform risk assessments for human health and the environment. Given the wealth of historical AOT information and technological advances, in silico models are being created and evaluated as potential tools to predict the AOT of compounds and reduce reliance on animal testing. Utilizing a historical database of AOT data on 371 Bristol Myers Squibb pharmaceutical compounds (PCs) (195 pharmaceutical intermediates and 176 active pharmaceutical ingredients), we evaluated two pioneering in silico AOT programs: the Leadscope Acute Oral Toxicity Model Suite and the Collaborative Acute Toxicity Modeling Suite. These models demonstrated a high degree of agreement with the in vivo results as well as a high level of sensitivity. We found that these models can be effectively utilized to identify PCs which are of low acute oral toxicity (LD₅₀ > 2000 mg/kg), PCs which should not be classified as Dangerous Goods (LD₅₀ > 300 mg/kg), and can assist in identifying a starting dose for in vivo AOT studies. This manuscript provides an evaluation of the performance of these in silico models and proposes use cases where these in silico models can be most confidently and effectively employed.