Computational and experimental study demonstrates effective cocrystal prediction for tiopronin and dapagliflozin, indicating accelerated pharmaceutical formulation workflows.
A novel virtual coformer screening model, COSMO-RS + Δ-ML, integrating COSMO-RS with machine learning to account for both miscibility in the amorphous phase and crystallinity contributions to cocrystallization, was developed. This computational approach was validated against published experimental cocrystal screening data for multiple APIs, demonstrating superior performance compared with the pure COSMO-RS method. The COSMO-RS + Δ-ML model was subsequently applied to guide targeted experimental cocrystal screenings for tiopronin and dapagliflozin. This led to the discovery and characterization of the first known anhydrous 4,4’-bipyridine cocrystal of tiopronin and two anhydrous cocrystals of dapagliflozin: citrate and a new bis- l -proline cocrystal. The demonstrated workflow, combining virtual screening by the COSMO-RS + Δ-ML model and targeted experimental studies, accelerates and derisks pharmaceutical coformer screening projects.
No takes yet. Share an insight, caveat, or question.
Abramov et al. (2025) studied this question.