LAUSR

Toxicity is a major cause of attrition in the development of pharmaceuticals, and the off-target effects are a frequent contributor. The 5-HT2B receptor agonism is known to be responsible for a variety of safety concerns including valvular heart disease which was the cause for the withdrawal of several compounds from the market. An early detection of potential binding to this receptor is thus desirable. Herein, we present the identification of key amino acid residues in the active site of 5-HT2B by molecular dynamics simulations, the development of pharmacophore models and their performance on in-house data, and a structurally highly diverse subset of Enamine REAL labeled for 5-HT2B activity by a machine learning model. These models may be used as filters employed on screening compound sets for the early filtration of compounds with potential 5-HT2B off-target liabilities.