Advancing the design and optimization of drug formulations with combined computational and experimental approaches

Scientists needed to understand why drug load affects the release mechanism and loss of release in amorphous solid dispersion (ASD) formulations, since "the underpinning principles and mechanisms are less investigated," requiring better understanding of ASD dissolution thermodynamics and molecular interactions. AbbVie and Schrodinger researchers studied ritonavir/copovidone ASDs using Schrodinger's Materials Science platform, combining thermodynamic modeling, molecular dynamics, coarse-grained simulations, and experimental microscopic erosion-time testing across different drug-load levels. At low-to-moderate drug load (5-15 wt%) the polymer formed the major phase, while at high drug load (40 wt%) drug molecules aggregated into clusters near the ASD surface, delaying erosion and drug release considerably; the combined approach gave a more complete understanding of the release mechanism for formulation optimization. No further numerical performance metrics beyond the drug-load percentages are stated.

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.