Unlocking the Potential of Machine Learning in Co‐crystal Prediction by a Novel Approach Integrating Molecular Thermodynamics

Co‐crystal engineering is of interest for many applications in pharmaceutical, chemistry and material fields, but rational design of co‐crystals is still challenging. Although artificial intelligence has brought major changes in the decision‐making process for materials design, yet limitations in generalization and mechanistic understanding remain. Herein, we sought to improve prediction of co‐crystal by combining mechanistic thermodynamic modeling with machine learning. We constructed a brand‐new co‐crystal database, integrating drug, coformer and reaction solvent information. By incorporating various thermodynamic models, the predictive performance was significantly enhanced. Benefiting from the complementarity of thermodynamic mechanisms and structural descriptors, the model coupling three thermodynamic models achieved optimal predictive performance. The model was rigorously validated against five benchmark models using challenging independent test sets, showcasing superior performance in both coformer and reaction solvent predicting with accuracy over 90%. Further, we employed SHAP analysis for model interpretation, suggesting that thermodynamic mechanisms are prominent in model's decision‐making. Proof‐of‐concept studies on ketoconazole validated the model's efficacy in identifying coformers/solvents, demonstrating its potential in practical application. Overall, our work enhanced the understanding of co‐crystallization, and shed light on the strategy that integrates mechanistic insights with data‐driven models to accelerate the creation of new co‐crystals, as well as various functional materials.