Beacon-2 is now available, marking an important step in the launch of Inductive Bio’s groundbreaking solution that predicts effective human doses of small molecules from their molecular structures. With the ability to make these predictions using mechanistic pharmacokinetic models to predict ADMET (absorption, distribution, metabolism, excretion, and toxicity) combined with potency prediction, Beacon-2 provides a valuable tool in biopharma chemistry and for AI. Built upon ADMET models that secured victory in three consecutive OpenADMET blind benchmark challenges against over 750 industry competitors, the technology seamlessly integrates into partner workflows via Inductive’s Compass platform.
Also Read: Deloitte and Salesforce Launch Agentforce-Powered CRM Accelerator for Mid-Sized Life Sciences Companies
Demonstrating its agentic utility, Inductive deployed Beacon-2 alongside its autonomous medicinal chemistry AI agent, Indy, achieving a 17-fold improvement in predicted human dose over five design cycles on a target SARS-CoV-2 compound. Highlighting the system’s core value proposition, Josh Haimson, co-founder and CEO of Inductive, noted, “Chemists have always had to balance a dozen separate properties against each other to decide whether a compound is worth making. Dose is what those properties all add up to. Computing it from structure changes which compounds a team decides to make and helps them identify the highest quality compounds faster.” Available immediately to pharmaceutical partners, Beacon-2 is currently active across live drug discovery pipelines, setting a new benchmark for structure-based computational drug design.
