Predicting Glass-Forming Ability of Pharmaceutical Compounds by Using Machine Learning Technologies.

Low aqueous solubility is a common and serious challenge for most drug substances not only in development but also in the market, and it may cause low absorption and bioavailability as a result. Amorphization is an intermolecular modification strategy to address the issue by breaking the crystal lattice and enhancing the energy state. However, due to the physicochemical properties of the amorphous state, drugs are thermodynamically unstable and tend to recrystallize over time. Glass-forming ability (GFA) is an experimental method to evaluate the forming and stability of glass formed by crystallization tendency. Machine learning (ML) is an emerging technique widely applied in pharmaceutical sciences. In this study, we successfully developed multiple ML models (i.e., random forest (RF), XGBoost, and support vector machine (SVM)) to predict GFA from 171 drug molecules. Two different molecular representation methods (i.e., 2D descriptor and Extended-connectivity fingerprints (ECFP)) were implemented to process the drug molecules. Among all ML algorithms, 2D-RF performed best with the highest accuracy, AUC, and F1 of 0.857, 0.850, and 0.828, respectively, in the testing set. In addition, we conducted a feature importance analysis, and the results mostly agreed with the literature, which demonstrated the interpretability of the model. Most importantly, our study showed great potential for developing amorphous drugs by in silico screening of stable glass formers.

Novel 3D Printed Modular Tablets Containing Multiple Anti-Viral Drugs: a Case of High Precision Drop-on-Demand Drug Deposition.

3D printed drug delivery systems have gained tremendous attention in pharmaceutical research due to their inherent benefits over conventional systems, such as provisions for customized design and personalized dosing. The present study demonstrates a novel approach of drop-on-demand (DoD) droplet deposition to dispense drug solutions precisely on binder jetting-based 3D printed multi-compartment tablets containing 3 model anti-viral drugs (hydroxychloroquine sulfate - HCS, ritonavir and favipiravir). The printing pressure affected the printing quality whereas the printing speed and infill density significantly impacted the volume dispersed on the tablets. Additionally, the DoD parameters such as nozzle valve open time and cycle time affected both dispersing volume and the uniformity of the tablets. The solid-state characterization, including DSC, XRD, and PLM, revealed that all drugs remained in their crystalline forms. Advanced surface analysis conducted by microCT imaging as well as Artificial Intelligence (AI)/Deep Learning (DL) model validation showed a homogenous drug distribution in the printed tablets even at ultra-low doses. For a four-hour in vitro drug release study, the drug loaded in the outer layer was released over 90%, and the drug incorporated in the middle layer was released over 70%. In contrast, drug encapsulated in the core was only released about 40%, indicating that outer and middle layers were suitable for immediate release while the core could be applied for delayed release. Overall, this study demonstrates a great potential for tailoring drug release rates from a customized modular dosage form and developing personalized drug delivery systems coupling different 3D printing techniques.

Novel Inhalable Ciprofloxacin Dry Powders for Bronchiectasis Therapy: Mannitol-Silk Fibroin Binary Microparticles with High-Payload and Improved Aerosolized Properties.

Non-cystic fibrosis bronchiectasis (NCFB) is a chronic respiratory disease associated with the high morbidity and mortality. Long-term intermittent therapy by inhalable antibiotics has recently emerged as an effective approach for NCFB treatment. However, the effective delivery of antibiotics to the lung requires administering a high dose to the site of infection. Herein, we investigated the novel inhalable silk-based microparticles as a promising approach to deliver high-payload ciprofloxacin (CIP) for NCFB therapy. Silk fibroin (SF) was applied to improve drug-payload and deposit efficiency of the dry powder particles. Mannitol was added as a mucokinetic agent. The dry powder inhaler (DPI) formulations of CIP microparticles were evaluated in vitro in terms of the aerodynamic performance, particle size distribution, drug loading, morphology, and their solid state. The optimal formulation (highest drug loading, 80%) exhibited superior aerosolization performance in terms of fine particle fraction (45.04 ± 0.84%), emitted dose (98.10 ± 1.27%), mass median aerodynamic diameter (3.75 ± 0.03 µm), and geometric standard deviation (1.66 ± 0.10). The improved drug loading was due to the electrostatic interactions between the SF and CIP by adsorption, and the superior aerosolization efficiency would be largely attributed to the fluffy and porous cotton-like property and low-density structure of SF. The presented results indicated the novel inhalable silk-based DPI microparticles of CIP could provide a promising strategy for the treatment of NCFB.

The Necessity to Investigate In Vivo Fate of Nanoparticle-Loaded Dissolving Microneedles.

Transdermal drug delivery systems are rapidly gaining prominence and have found widespread application in the treatment of numerous diseases. However, they encounter the challenge of a low transdermal absorption rate. Microneedles can overcome the stratum corneum barrier to enhance the transdermal absorption rate. Among various types of microneedles, nanoparticle-loaded dissolving microneedles (DMNs) present a unique combination of advantages, leveraging the strengths of DMNs (high payload, good mechanical properties, and easy fabrication) and nanocarriers (satisfactory solubilization capacity and a controlled release profile). Consequently, they hold considerable clinical application potential in the precision medicine era. Despite this promise, no nanoparticle-loaded DMN products have been approved thus far. The lack of understanding regarding their in vivo fate represents a critical bottleneck impeding the clinical translation of relevant products. This review aims to elucidate the current research status of the in vivo fate of nanoparticle-loaded DMNs and elaborate the necessity to investigate the in vivo fate of nanoparticle-loaded DMNs from diverse aspects. Furthermore, it offers insights into potential entry points for research into the in vivo fate of nanoparticle-loaded DMNs, aiming to foster further advancements in this field.

The applications of machine learning to predict the forming of chemically stable amorphous solid dispersions prepared by hot-melt extrusion.

Amorphous solid dispersion (ASD) is one of the most important strategies to improve the solubility and dissolution rate of poorly water-soluble drugs. As a widely used technique to prepare ASDs, hot-melt extrusion (HME) provides various benefits, including a solvent-free process, continuous manufacturing, and efficient mixing compared to solvent-based methods, such as spray drying. Energy input, consisting of thermal and specific mechanical energy, should be carefully controlled during the HME process to prevent chemical degradation and residual crystallinity. However, a conventional ASD development process uses a trial-and-error approach, which is laborious and time-consuming. In this study, we have successfully built multiple machine learning (ML) models to predict the amorphization of crystalline drug formulations and the chemical stability of subsequent ASDs prepared by the HME process. We utilized 760 formulations containing 49 active pharmaceutical ingredients (APIs) and multiple types of excipients. By evaluating the built ML models, we found that ECFP-LightGBM was the best model to predict amorphization with an accuracy of 92.8%. Furthermore, ECFP-XGBoost was the best in estimating chemical stability with an accuracy of 96.0%. In addition, the feature importance analyses based on SHapley Additive exPlanations (SHAP) and information gain (IG) revealed that several processing parameters and material attributes (i.e., drug loading, polymer ratio, drug's Extended-connectivity fingerprints (ECFP) fingerprints, and polymer's properties) are critical for achieving accurate predictions for the selected models. Moreover, important API's substructures related to amorphization and chemical stability were determined, and the results are largely consistent with the literature. In conclusion, we established the ML models to predict formation of chemically stable ASDs and identify the critical attributes during HME processing. Importantly, the developed ML methodology has the potential to facilitate the product development of ASDs manufactured by HME with a much reduced human workload.

Emerging Artificial Intelligence (AI) Technologies Used in the Development of Solid Dosage Forms.

Artificial Intelligence (AI)-based formulation development is a promising approach for facilitating the drug product development process. AI is a versatile tool that contains multiple algorithms that can be applied in various circumstances. Solid dosage forms, represented by tablets, capsules, powder, granules, etc., are among the most widely used administration methods. During the product development process, multiple factors including critical material attributes (CMAs) and processing parameters can affect product properties, such as dissolution rates, physical and chemical stabilities, particle size distribution, and the aerosol performance of the dry powder. However, the conventional trial-and-error approach for product development is inefficient, laborious, and time-consuming. AI has been recently recognized as an emerging and cutting-edge tool for pharmaceutical formulation development which has gained much attention. This review provides the following insights: (1) a general introduction of AI in the pharmaceutical sciences and principal guidance from the regulatory agencies, (2) approaches to generating a database for solid dosage formulations, (3) insight on data preparation and processing, (4) a brief introduction to and comparisons of AI algorithms, and (5) information on applications and case studies of AI as applied to solid dosage forms. In addition, the powerful technique known as deep learning-based image analytics will be discussed along with its pharmaceutical applications. By applying emerging AI technology, scientists and researchers can better understand and predict the properties of drug formulations to facilitate more efficient drug product development processes.

3D bioprinted microparticles: Optimizing loading efficiency using advanced DoE technique and machine learning modeling.

Current microparticle (MP) development still strongly relies on the laborious trial-and-error approach. Herein, we developed a systemic method to evaluate the significance of MP formulation factors and predict drug loading efficiency (DLE) using design of experiment (DoE) and machine learning modeling. A first-in-class 3D printing concept was initially employed to fabricate polymeric MPs by a 3D printer. Sprayed Multi Adsorbed-droplet Reposing Technology (SMART) was developed to combine extrusion-based printing with emulsion evaporation technique to fabricate a small molecule drug i.e., 6-thioguanine (6-TG) loaded poly (lactide-co-glycolide) (PLGA) MPs. Compared to conventional emulsion evaporation method, SMART employs the shear force exerted by the printing nozzle rather than the sonication energy to generate smaller emulsion droplets in a single step. Furthermore, the applied shear force in the 3D printing process reported herein is controllable since the emulsion is extruded through the nozzle under preset printing conditions. The formulated MPs exhibited spherical structure with size distribution âˆ¼ 1-3µ m in diameter and reached âˆ¼ 100 % drug release at 10 h. Also, the papain-like protease (PLpro) inhibition efficacy of 6-TG in formulated MPs was maintained even after the printing process under different printing conditions. Furthermore, the formulation factor importance was assessed by DoE statistical analysis and further validated by machine learning modeling. Among the four process parameters (drug amount, printing speed, printing pressure, and nozzle size), drug amount was the most influential formulation factor. Moreover, it is interesting that nearly all the machine learning models, especially decision tree (DT), demonstrated superior performance in predicting DLE compared to DoE regression models. Overall, incorporating DoE and machine learning modeling shows great promises in the prediction and optimization of MP formulations factors by means of a novel SMART technology. Moreover, this systemic approach helps streamline the development of MP with programmable pharmaceutical attributes, representing a new paradigm for digital pharmaceutical science.

The applications of Machine learning (ML) in designing dry powder for inhalation by using thin-film-freezing technology.

Dry powder inhalers (DPIs) are one of the most widely used devices for treating respiratory diseases. Thin--film--freezing (TFF) is a particle engineering technology that has been demonstrated to prepare dry powder for inhalation with enhanced physicochemical properties. Aerosol performance, which is indicated by fine particle fraction (FPF) and mass median aerodynamic diameter (MMAD), is an important consideration during the product development process. However, the conventional approach for formulation development requires many trial-and-error experiments, which is both laborious and time consuming. As a state-of-the art technique, machine learning has gained more attention in pharmaceutical science and has been widely applied in different settings. In this study, we have successfully built a prediction model for aerosol performance by using both tabular data and scanning electron microscopy (SEM) images. TFF technology was used to prepare 134 dry powder formulations which were collected as a tabular dataset. After testing many machine learning models, we determined that the Random Forest (RF) model was best for FPF prediction with a mean absolute error of ± 7.251%, and artificial neural networks (ANNs) performed the best in estimating MMAD with a mean absolute error of ± 0.393 µm. In addition, a convolutional neural network was employed for SEM image classification and has demonstrated high accuracy (>83.86%) and adaptability in predicting 316 SEM images of three different drug formulations. In conclusion, the machine learning models using both tabular data and image classification were successfully established to evaluate the aerosol performance of dry powder for inhalation. These machine learning models facilitate the product development process of dry powder for inhalation manufactured by TFF technology and have the potential to significantly reduce the product development workload. The machine learning methodology can also be applied to other formulation design and development processes in the future.

Development of composite PLGA microspheres containing exenatide-encapsulated lecithin nanoparticles for sustained drug release.

This study aimed to prepare poly (D, L-lactic-co-glycolic acid) microspheres (PLGA-Ms) by a modified solid-in-oil-in-water (S/O/W) multi-emulsion technique in order to achieve sustained release with reduced initial burst and maintain efficient drug concentration for a prolonged period of time. Composite PLGA microspheres containing exenatide-encapsulated lecithin nanoparticles (Ex-NPs-PLGA-Ms) were obtained by initial fabrication of exenatide-loaded lecithin nanoparticles (Ex-NPs) via the alcohol injection method, followed by encapsulation of Ex-NPs into PLGA microspheres. Compared to Ms prepared by the conventional water-in-oil-in-water (W/O/W) technique (Ex-PLGA-Ms), Ex-NPs-PLGA-Ms showed a more uniform particle size distribution, reduced initial burst release, and sustained release for over 60 d in vitro. Cytotoxicity studies showed that Ms prepared by both techniques had superior biocompatibility without causing any detectable cytotoxicity. In pharmacokinetic studies, the effective drug concentration was maintained for over 30 d following a single subcutaneous injection of two types of Ms formulation in rats, potentially prolonging the therapeutic action of Ex. In addition, administration of Ex-NPs-PLGA-Ms resulted in a more smooth plasma concentration-time profile with a higher area under the curve (AUC) compared to that of Ex-PLGA-Ms. Overall, Ex-NPs-PLGA-Ms prepared by the novel S/O/W method could be a promising sustained drug release system with reduced initial burst release and prolonged therapeutic efficacy.