Search

Solution crystallization is an important separation unit operation in active pharmaceutical ingredient production. Solvent is one of the important factors affecting crystal morphology. How to select/design suitable solvents is still one of the most urgent problems in the crystallization field. In this article, a framework for crystallization solvent design based on the developed quantitative prediction model of crystal morphology is proposed. First, molecular dynamics is used to predict the crystal morphology in solvents. Next, solvent descriptors are selected by stepwise regression method. Then, the quantitative relationship between crystal aspect ratio and solvent descriptors is developed. Subsequently, computer‐aided molecular design method is integrated with the developed quantitative prediction model. The crystallization solvent design problem is expressed as a mixed‐integer nonlinear programming model with maximum yield as the objective function, which is solved by decomposition algorithm. Finally, the crystallization solvent design framework is applied to two cases and experimental verification is implemented. [ABSTRACT FROM AUTHOR]

Solvents are widely used in chemical processes. The use of efficient model‐based solvent selection techniques is an option worth considering for rapid identification of candidates with better economic, environment and human health properties. In this paper, an optimization‐based MLAC‐CAMD framework is established for solvent design, where a novel machine learning‐based atom contribution method is developed to predict molecular surface charge density profiles (σ‐profiles). In this method, weighted atom‐centered symmetry functions are associated with atomic σ‐profiles using a high‐dimensional neural network model, successfully leading to a higher prediction accuracy in molecular σ‐profiles and better isomer identifications compared with group contribution methods. The new method is integrated with the computer‐aided molecular design technique by formulating and solving a mixed‐integer nonlinear programming model, where model complexities are managed with a decomposition‐based strategy. Finally, two case studies involving crystallization and reaction are presented to highlight the wide applicability and effectiveness of the MLAC‐CAMD framework. [ABSTRACT FROM AUTHOR]