Artificial intelligence and specifically machine learning applications are nowadays used in a variety of scientific applications and cutting-edge technologies, where they have a transformative impact. Such an assembly of statistical and linear algebra methods making use of large data sets is becoming more and more integrated into chemistry and crystallization research workflows. This review aims to present, for the first time, a holistic overview of machine learning and cheminformatics applications as a novel, powerful means to accelerate the discovery of new crystal structures, predict key properties of organic crystalline materials, simulate, understand, and control the dynamics of complex crystallization process systems, as well as contribute to high throughput automation of chemical process development involving crystalline materials. We critically review the advances in these new, rapidly emerging research areas, raising awareness in issues such as the bridging of machine learning models with first-principles mechanistic models, data set size, structure, and quality, as well as the selection of appropriate descriptors. At the same time, we propose future research at the interface of applied mathematics, chemistry, and crystallography. Overall, this review aims to increase the adoption of such methods and tools by chemists and scientists across industry and academia.

The crystal growth kinetics of a proprietary active pharmaceutical ingredient (API) was investigated by isothermal seeded batch de-supersaturation experiments in solvent mixtures using the "true" thermodynamic representation of the supersaturation driving force, which considers the activities of the saturated and supersaturated states. Three approaches to approximate the experimentally inaccessible activity coefficients of the supersaturated state were assessed, as well as the most common approximation, which omits the activity coefficients altogether. Subsequently, the supersaturation data from the different expressions were fed into a population balance model to estimate kinetic parameters for the empirical, Burton− Cabrera−Frank, and birth-and-spread growth models. The results demonstrate that the approach used to compute the supersaturation alters the estimated kinetic parameters significantly, having potentially serious implications for their physical interpretation and for extracting the physical properties they represent in lumped form. Moreover, including the chemical activities in the supersaturation leads to kinetic parameters with a tighter joint confidence interval and weaker parameter correlation that can better explain the experimental observation of the API growing appreciably only under higher antisolvent amounts. Finally, the simultaneous occurrence of multiple crystal growth mechanisms is investigated, concluding that the additive contribution of B+S and BCF best explains the supersaturation decay observed in the experiments for this API.