Novel Cocrystals of Vonoprazan: Machine Learning-Assisted Discovery.

Vonoprazan (VPZ) is the first-in-class potassium-competitive acid blocker (P-CAB), and has many advantages over proton pump inhibitors (PPIs). It is administered as a fumarate salt for the treatment of acid-related diseases, including reflux esophagitis, gastric ulcer, and duodenal ulcer, and for eradication of Helicobacter pylori. To discover novel cocrystals of VPZ, we adopted an artificial neural network (ANN)-based machine learning model as a virtual screening tool that can guide selection of the most promising coformers for VPZ cocrystals. Experimental screening by liquid-assisted grinding (LAG) confirmed that 8 of 19 coformers selected by the ANN model were likely to create new solid forms with VPZ. Structurally similar benzenediols and benzenetriols, i.e., catechol (CAT), resorcinol (RES), hydroquinone (HYQ), and pyrogallol (GAL), were used as coformers to obtain phase pure cocrystals with VPZ by reaction crystallization. We successfully prepared and characterized three novel cocrystals: VPZ-RES, VPZ-CAT, and VPZ-GAL. VPZ-RES had the highest solubility among the novel cocrystals studied here, and was even more soluble than the commercially available fumarate salt of VPZ in solution at pH 6.8. In addition, novel VPZ cocrystals had superior stability in aqueous media than VPZ fumarates, demonstrating their potential for improved pharmaceutical performance.

Drug Properties Prediction Based on Deep Learning.

In recent research on the formulation prediction of oral dissolving drugs, deep learning models with significantly improved performance compared to machine learning models were proposed. However, the performance degradation due to limitations of an imbalanced dataset with a small size and inefficient neural network structure has still not been resolved. Therefore, we propose new deep learning-based prediction models that maximize the prediction performance for disintegration time of oral fast disintegrating films (OFDF) and cumulative dissolution profiles of sustained-release matrix tablets (SRMT). In the case of OFDF, we use principal component analysis (PCA) to reduce the dimensionality of the dataset, thereby improving the prediction performance and reducing the training time. In the case of SRMT, the Wasserstein generative adversarial network (WGAN), a neural network-based generative model, is used to overcome the limitation of performance improvement due to the lack of experimental data. To the best of our knowledge, this is the first work that utilizes WGAN for pharmaceutical formulation prediction. Experimental results show that the proposed methods have superior performance than the existing methods for all the performance metrics considered.

Antimalarial Drug Predictions Using Molecular Descriptors and Machine Learning against Plasmodium Falciparum.

Malaria remains by far one of the most threatening and dangerous illnesses caused by the plasmodium falciparum parasite. Chloroquine (CQ) and first-line artemisinin-based combination treatment (ACT) have long been the drug of choice for the treatment and controlling of malaria; however, the emergence of CQ-resistant and artemisinin resistance parasites is now present in most areas where malaria is endemic. In this work, we developed five machine learning models to predict antimalarial bioactivities of a drug against plasmodium falciparum from the features (i.e., molecular descriptors values) obtained from PaDEL software from SMILES of compounds and compare the machine learning models by experiments with our collected data of 4794 instances. As a consequence, we found that three models amongst the five, namely artificial neural network (ANN), extreme gradient boost (XGB), and random forest (RF), outperform the others in terms of accuracy while observing that, using roughly a quarter of the promising descriptors picked by the feature selection algorithm, the five models achieved equivalent and comparable performance. Nevertheless, the contribution of all molecular descriptors in the models was investigated through the comparison of their rank values by the feature selection algorithm and found that the most potent and relevant descriptors which come from the 'Autocorrelation' module contributed more while the 'Atom type electrotopological state' contributed the least to the model.

Agomelatine-hydroquinone (1:1) cocrystal: novel polymorphs and their thermodynamic relationship.

Polymorphism of active pharmaceutical ingredients (APIs) is of significance in the pharmaceutical industry because it can affect the quality, efficacy and safety of the final drug product. In this regard, polymorphic behavior of cocrystals is no exception because it can influence the development of cocrystals as potential drug formulations. The current contribution aims to introduce two novel polymorphs [forms (III) and (IV)] of agomelatine-hydroquinone (AGO-HYQ) cocrystal and to describe the thermodynamic relationship between the cocrystal polymorphs. All polymorphs were characterized using powder X-ray diffraction, differential scanning calorimetry, hot-stage microscopy and solubility measurements. In addition, the crystal structure of form (II), which has been previously solved from powder diffraction data [Prohens et al. (2016), Cryst. Growth Des. 16, 1063-1070] and form (III) were determined from the single-crystal X-ray diffraction data. Thermal analysis revealed that AGO-HYQ cocrystal form (III) exhibits a higher melting point and a lower heat of fusion than those of form (II). According to the heat of fusion rule, the polymorphs are enantiotropically related, with form (III) being stable at higher temperatures. Our results also show that the novel form (IV) is the most stable form at ambient conditions and it transforms into form (II) on heating, and therefore, the two polymorphs are enantiotropically related. Furthermore, solubility and van't Hoff plot results suggest that the transition points are approximately 339 K for the pair form (IV)-(II) and 352 K for the pair form (II)-(III).

Paracellular permeation-enhancing effect of AT1002 C-terminal amidation in nasal delivery.

BACKGROUND: The identification of permeation enhancers has gained interest in the development of drug delivery systems. A six-mer peptide, H-FCIGRL-OH (AT1002), is a tight junction modulator with promising permeation-enhancing activity. AT1002 enhances the transport of molecular weight markers or agents with low bioavailability with no cytotoxicity. However, AT1002 is not stable in neutral pH or after incubation under physiological conditions, which is necessary to fully uncover its permeation-enhancing effect. Thus, we increased the stability or mitigated the instability of AT1002 by modifying its terminal amino acids and evaluated its subsequent biological activity. METHODS: C-terminal-amidated (FCIGRL-NH2, Pep1) and N-terminal-acetylated (Ac-FCIGRL, Pep2) peptides were analyzed by liquid chromatography-mass spectrometry. We further assessed cytotoxicity on cell monolayers, as well as the permeation-enhancing activity following nasal administration of the paracellular marker mannitol. RESULTS: Pep1 was nontoxic to cell monolayers and showed a relatively low decrease in peak area compared to AT1002. In addition, administration of mannitol with Pep1 resulted in significant increases in the area under the plasma concentration-time curve and peak plasma concentration at 3.63-fold and 2.68-fold, respectively, compared to mannitol alone. In contrast, no increase in mannitol concentration was shown with mannitol/AT1002 or mannitol/Pep2 compared to the control. Thus, Pep1 increased the stability or possibly reduced the instability of AT1002, which resulted in an increased permeation-enhancing effect of AT1002. CONCLUSION: These results suggest the potential usefulness of C-terminal-amidated AT1002 in enhancing nasal drug delivery, which may lead to the development of a practical drug delivery technology for drugs with low bioavailability.

Anti-solvent co-crystallization of carbamazepine and saccharin.

The co-crystal approach has been investigated extensively over the past decade as one of the most promising methods to enhance the dissolution properties of insoluble drug substances. Co-crystal powders are typically produced by mechanical grinding (neat or wet) or a solution method (evaporation or cooling). In this study, high-purity carbamazepine-saccharin (CBZ-SAC) co-crystals were manufactured by a novel method, anti-solvent addition. Among various solvents, methanol was found to perform well with water as the anti-solvent for the co-crystallization of CBZ and SAC. When water was added to the methanol solution of CBZ and SAC at room temperature under agitation, nucleation of CBZ-SAC co-crystals occurred within 2-3 min. Co-crystallization was complete after 30 min, giving a solid yield as high as 84.5% on a CBZ basis. The effects of initial concentrations, focusing on the SAC/CBZ ratio, were examined to establish optimal conditions. The whole anti-solvent co-crystallization process was monitored at-line via ATR-FTIR analysis of regularly sampled solutions. The nucleation and crystal growth of CBZ-SAC co-crystals were detected by a significant increase in absorption in the range of 2400-2260 cm(-1), associated with the formation of hydrogen bonds between the carbonyl group in CBZ and the N-H of SAC. When CBZ hydrates were formed as impurities during anti-solvent co-crystallization, the hydrogen bonding between methanol and water was reduced greatly, primarily due to the incorporation of water molecules into the CBZ crystal lattice. In conclusion, an anti-solvent approach can be used to produce highly pure CBZ-SAC co-crystal powders with a high solid yield.

Characteristics of indomethacin-saccharin (IMC-SAC) co-crystals prepared by an anti-solvent crystallization process.

The creation of co-crystals of various insoluble drug substances has been extensively investigated as a promising approach to improve their pharmaceutical performance. In this study, co-crystal powders of indomethacin and saccharin (IMC-SAC) were prepared by an anti-solvent (water) addition and compared with co-crystals by evaporation method. No successful synthesis of a pharmaceutical co-crystal powder via an anti-solvent approach has been reported. Among solvents examined, methanol was practically the only one that resulted in the formation of highly pure IMC-SAC co-crystal powders by anti-solvent approach. The mechanism of a preferential formation of IMC-SAC co-crystal to IMC was explained with two aspects: phase solubility diagram and solution complexation concept. Accordingly, the anti-solvent approach can be considered as a competitive route for producing pharmaceutical co-crystal powders with acceptable properties.

Quantitative in-line monitoring of solvent-mediated polymorphic transformation of sulfamerazine by near-infrared spectroscopy.

The in-line monitoring of pharmaceutical processes with high risk, such as crystallization, has been one of the most popular research topics in recent years. Sulfamerazine (SMZ), a well-known sulfonamide antibacterial agent was investigated to examine the mechanism of polymorphic conversion by solvent-mediated polymorphic transformation (SMPT). The primary purpose of this study is to monitor the polymorphic transformation through in-line near-infrared (NIR) measurements and concurrently interpret the whole process quantitatively with off-line characterizations. Samples taken at every hour during SMPT were analyzed by X-ray diffractometry (XRD) and differential scanning calorimetry (DSC). NIR spectra in the range of 7500-4900 cm(-1) were taken into account for multivariate analysis, which included partial least square (PLS) regression and principal component analysis (PCA). In brief, the form II content was estimated very accurately and reproducibly during the SMPT process not only by XRD but also by the DSC measurements. In addition, the form II content values were predicted very accurately by separate experiments at two designated time points. In a separate study, it was demonstrated that PCA could be employed to explain a complicated process such as SMPT mechanistically by several stages.

In line NIR quantification of film thickness on pharmaceutical pellets during a fluid bed coating process.

Along with the risk-based approach, process analytical technology (PAT) has emerged as one of the key elements to fully implement QbD (quality-by-design). Near-infrared (NIR) spectroscopy has been extensively applied as an in-line/on-line analytical tool in biomedical and chemical industries. In this study, the film thickness on pharmaceutical pellets was examined for quantification using in-line NIR spectroscopy during a fluid-bed coating process. A precise monitoring of coating thickness and its prediction with a suitable control strategy is crucial to the quality assurance of solid dosage forms including dissolution characteristics. Pellets of a test formulation were manufactured and coated in a fluid-bed by spraying a hydroxypropyl methylcellulose (HPMC) coating solution. NIR spectra were acquired via a fiber-optic probe during the coating process, followed by multivariate analysis utilizing partial least squares (PLS) calibration models. The actual coating thickness of pellets was measured by two separate methods, confocal laser scanning microscopy (CLSM) and laser diffraction particle size analysis (LD-PSA). Both characterization methods gave superb correlation results, and all determination coefficient (R(2)) values exceeded 0.995. In addition, a prediction coating experiment for 70min demonstrated that the end-point can be accurately designated via NIR in-line monitoring with appropriate calibration models. In conclusion, our approach combining in-line NIR monitoring with CLSM and LD-PSA can be applied as an effective PAT tool for fluid-bed pellet coating processes.