Discovery of a novel, potent ACC inhibitor driven by computationally-guided design and assessment of water energetics in the binding site

ACC inhibition is a validated approach for metabolic disorders including type 2 diabetes, NASH, and atherosclerotic vascular disease, but prior molecules targeting the carboxyltransferase domain had poor drug-like properties and selectivity issues. Nimbus Therapeutics and Schrodinger instead targeted the biotin carboxylase domain, using WaterMap to find high-energy hydration sites plus Glide docking and Phase pharmacophore screening against a commercial library, aiming for molecules that displace high-energy waters near Val587 and Tyr683. This produced ND-022, a low-micromolar dual ACC1/ACC2 inhibitor, and ultimately ND-630 (GS-0976/firsocostat), a potential first-in-class potent and selective inhibitor discovered within 16 months. 2017 clinical data showed statistically significant reductions in hepatic steatosis at a 20 mg daily dose over 12 weeks, and a 2020 trial in 108 NASH patients found all combination regimens well tolerated.

The customer is anonymised in Schrödinger’s own case study — not withheld by us.

Schrödinger is a physics-plus-machine-learning computational platform for molecular design; all top-20 pharma companies by revenue are customers of its drug-discovery software.

This sits in the Build stage of the AI use-case lifecycle: Named examples from the foundation-model labs and platforms pharma teams use to actually construct, train and generate the model or application.