Inductive Bio Wins World's Largest ADMET Prediction Competition

Inductive Bio won the OpenADMET-ExpansionRx blind challenge with its Beacon models. The company placed first among more than 370 submissions in the largest industry competition to date. The submissions came from scientists at large pharma, biotech, academic and AI organizations. The challenge tasked participants with predicting nine critical ADMET endpoints from a real-world drug discovery campaign targeting myotonic dystrophy, ALS and dementia. It was launched in partnership with Expansion Therapeutics. The blind challenge format required participants to predict properties of previously unseen compounds from actual drug programs. Josh Haimson, co-founder and CEO of Inductive Bio, said the team is proud to place first among competitors from some of the largest companies in the space. The results demonstrate for a second time that Inductive Beacon models represent the state of the art in ADMET prediction, Haimson said. These results affirm the value of the small but mighty team experience in drug discovery and focus on building a diverse, high-quality dataset, he said. Inductive Beacon ADMET and PK models are trained on one of the industry's largest and most diverse ADMET datasets. The models are engineered with proprietary fine-tuning technology that adapts global trends to novel chemical space. The models guide small molecule discovery campaigns toward compounds with improved dose, safety margins and developability earlier in the discovery process.