Machine learning (ML) is revolutionizing formulation design by enabling data-driven predictions of critical performance indicators, such as solubility, viscosity, stability, and even sensory properties. Chemistry-informed AI/ML models provide a powerful framework for accelerating innovation across a wide range of formulations — from personal care and food, to pharma and battery electrolytes. By analyzing large, diverse datasets, ML can predict the behavior of new formulations, including complex mixtures and ingredients that are combinations of multiple mixtures, dramatically reducing reliance on trial-and-error approaches and speeding time-to-market.
Automated solutions can integrate ingredient composition and molecular structure to generate predictive models that optimize formulation performance. This empowers R&D teams to explore complex formulation spaces, reduce development cycles, and innovate more effectively. In this webinar, we will demonstrate how Schrödinger’s integrated ML- and physics-based approaches are transforming formulation design, with an emphasis on applications relevant to consumer packaged goods (CPG).
Key Learning Objectives:
- How physics-based models can help generate meaningful data for enhancing ML models in projects with limited data inputs
- How an automated ML solution, incorporating chemistry and composition, can predict solubility in multi-component systems
- How ML models that are enhanced with physics-based descriptors can improve viscosity predictions
- How formulation ML tools enable non-computational experts to design novel CPG products that meet multiple target criteria—a case study with shampoo formulations
Who Should Attend:
- R&D Leaders
- Innovation Managers
- Digitization Managers
- Synthetic Chemists
- Materials Scientists
- Chemical Engineers
- Materials Research Engineers
- Computational Chemists
- Computational Materials Scientists