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.
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.
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.
Display omitted
•PLGA microspheres based on exenatide encapsulated in nanoparticles were developed.•Ex-NPs-PLGA-Ms was prepared by modified S/O/W method with a low initial burst.•Ex-NPs-PLGA-Ms achieved zero-order ...controlled release.•S/O/W method could preserve the bioactivity of exenatide without cytotoxicity.
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.
Display omitted
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 ∼ 1-3μ m in diameter and reached ∼ 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.
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.
Graphical Abstract
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.
Graphical Abstract
Previous studies have shown that DWARFIO (D10) is a rice ortholog of MAX41RMS1/DAD1, encoding a carotenoid cleavage dioxygenase and functioning in strigolactones/strigolactone-derivatives (SL) ...biosynthesis. Here we use DIO. RNA interference (RNAi) transgenic plants similar to dlO mutant in phenotypes to investigate the interactions among DIO, auxin and cytokinin in regulating rice shoot branching. Auxin levels in node 1 of both decapitated DIO.RNAi and wild type plants decreased significantly, showing that decapitation does reduce endogenous auxin concentration, but decapitation has no clear effects on auxin levels in node 2 of the same plants. This implies that node 1 may be the location where a possible interaction between auxin and DIO gene would be detected. DIO expression in node 1 is inhibited by decapitation, and this inhibition can be restored by exogenous auxin application, indicating that DIO may play an important role in auxin regulation of SL. The decreased expression of most OsPINs in shoot nodes of DIO-RNAi plants may cause a reduced auxin transport capacity. Furthermore, effects of auxin treatment of decapitated plants on the expression of cytokinin biosynthetic genes suggest that DIO promotes cytokinin biosynthesis by reducing auxin levels. Besides, in DIO-RNAi plants, decreased storage cytokinin levels in the shoot node may partly account for the increased active cytokinin contents, resulting in more tillering phenotypes.
Aim: The aim of this study was to test the hypothesis that lower serum sodium may be associated with increased cardiovascular events and all-cause mortality by means of long-term follow-up of ...subjects with coronary atherosclerosis in a prospective, hospital-based epidemiological study in China.
Methods: A prospective, hospital-based epidemiological design was used. The study population consisted of 1069 consecutive patients who were scheduled to undergo coronary angiography for suspected or known coronary atherosclerosis. The severity of coronary atherosclerosis was defined using Gensini's score system. Age, sex-adjusted hazard ratios (HR) and 95% confidence intervals (CI) for the quartiles of serum sodium concentration were estimated with Cox proportional hazard models, using quartile 1 as the reference. Cox proportional hazard models were also constructed to estimate the hazard ratios and 95% confidence intervals for all-cause mortality and final end-point events by serum sodium quartile and to adjust for potentially confounding variables. Multivariate models were adjusted for the following variables: age, sex, smoking status, alcohol consumption, body mass index, blood pressure, potassium, chloride, total cholesterol, triglycerides, fasting blood glucose, urea, creatinine, uric acid, and Gensini's score. Results: During the median 2.86 years (3011.66 person-years) of follow-up, 176 final end-point events were documented. These events included 79 deaths and 97 readmissions for coronary heart disease. There was a statistically significant inverse association of serum sodium with all-cause mortality (P〈0.001). After full adjustment comparing the highest serum sodium quartile to the lowest, there was a non-significant inverse association with all-cause mortality, with an adjusted hazard ratio (95% CI) of 0.67 (0.25-1.80). After adjustment for age and increasing quartiles of serum sodium concentration were sex, the hazard ratio and 95% CI for final end-point events across 1.00, 0.85 (0.59-1.22), 0.52 (0.34-0.82), and 0.31 (0.19-0.49). After full adjustment comparing the highest serum sodium quartile to the lowest, there was a statistically significant inverse asso- ciation with final end-point events, with an adjusted hazard ratio (95% CI) of 0.46 (0.26-0.81).
Conclusion: The serum sodium concentration showed a statistically significant negative association with coronary events and all-cause mortality in subjects with coronary atherosclerosis; the actual mechanism underlying this association needs further study.