5/30/2023 0 Comments Crystal size in jmicrovision![]() According to previous studies, deep learning has been successfully used to identify and classify various chemical crystals, but its applications in the image analysis of pharmaceutical crystallization have not been exploited widely. Recently, deep learning has turned out to be a potent tool for analyzing high-dimensional data and has been increasingly applied to the field of image recognition. Since plenty of images are produced by time-lapse imaging, and each image usually contains numerous crystals, , conventional manual measurement is extremely time-consuming and error-prone. ![]() Real-time microscopic imaging has been widely adopted for in situ noninvasive monitoring of crystal growth. With increasing applications of HTC in the pharmaceutical industry, fully investigations of the effects of microwell sizes on the crystal growth kinetics of APIs is in demand (see Scheme 1). However, some studies have documented that the size of vessel could affect the crystallization rate and crystal size distribution (CSD) of crystals, ,, which might potentially influence the robustness of HTC and its effectiveness in guiding further large-scale industrial production. In most cases, the size of crystallization vessels in different well-plate formats is considered to have no or minor effects on the crystallization properties of APIs. In general, HTC of APIs is run in microwell plates of various formats (i.e., 96-, 384-well plates, etc.), which comprise crystallization vessels in microliters. To date, high-throughput crystallization (HTC) systems have become an attractive option to acquire API crystals with desirable properties, which can screen hundreds or thousands of crystallization conditions in parallel with low consumption of reagents and high efficiency. Consequently, a significant amount of effort has been dedicated to determining the optimal crystallization parameters to acquire APIs with desirable crystal characteristics, ,,. According to the findings of previous studies, the size and structure of API crystals are affected by various crystallization parameters, including the composition of solvents, ratios between solvent and antisolvent, supersaturation, seed quality, temperature, diffusion rate, , sizes of vessel, etc. Therefore, optimizing the crystallization conditions to manufacture APIs with the appropriate crystalline morphology, size, and uniformity is of great importance. It has been found that the same APIs with different crystal properties exhibit dissimilar solubility, bioavailability, stability, and other performance characteristics. In the pharmaceutical industry, crystallization is a crucial step to obtain pure active pharmaceutical ingredients (APIs). Moreover, our findings in the relationships between the size of the crystallization vessels and crystal growth kinetics are of great value in guiding the manufacture of APIs in the pharmaceutical industry. Our research demonstrated the powerful capability of deep learning in processing complicated crystalline images. And the relationships between crystallization properties (the average size, crystal size distribution, and the growth rate of crystals) and the size of the crystallization vessels were successfully revealed, which were further validated by the crystallization of ibuprofen and the scale-up experiment. With a combination of microscopic imaging and deep learning, the massive information of indomethacin crystals was successfully obtained and analyzed in a high-throughput manner. ![]() To address the issue, we proposed a novel deep-learning-based approach to investigate the effects of microwell sizes on the crystal growth kinetics of APIs. However, the microwell size effect on crystallization kinetics at the scale of microtiters has not been fully investigated and remains unsolved. It is typically processed in 96- and 384-well plates, which offer parallel crystallization vessels with microliter-scaled volume. In the pharmaceutical industry, high-throughput crystallization (HTC) is an emerging strategy to accelerate the discovery of active pharmaceutical ingredients (APIs) with appropriate crystallization properties.
0 Comments
Leave a Reply. |