A prediction model based on artificial intelligence techniques for disintegration time and hardness of fast disintegrating tablets in pre-formulation tests.

BACKGROUND: The pharmaceutical industry is continually striving to innovate drug development and formulation processes. Orally disintegrating tablets (ODTs) have gained popularity due to their quick release and patient-friendly characteristics. The choice of excipients in tablet formulations plays a critical role in ensuring product quality, highlighting its importance in tablet creation. The traditional trial-and-error approach to this process is both expensive and time-intensive. To tackle these obstacles, we introduce a fresh approach leveraging machine learning and deep learning methods to automate and enhance pre-formulation drug design. METHODS: We collected a comprehensive dataset of 1983 formulations, including excipient names, quantities, active ingredient details, and various physicochemical attributes. Our study focused on predicting two critical control test parameters: tablet disintegration time and hardness. We compared a range of models like deep learning, artificial neural networks, support vector machines, decision trees, multiple linear regression, and random forests. RESULTS: A 12-layer deep neural network, as a form of deep learning, surpassed alternative techniques by achieving 73% accuracy for disintegration time and 99% for tablet hardness. This success underscores its efficacy in predicting complex pharmaceutical factors. Such an approach streamlines the drug formulation process, reducing iterations and material consumption. CONCLUSIONS: Our findings highlight the deep learning potential in pharmaceutical formulations, particularly for tablet hardness prediction. Future work should focus on enlarging the dataset to improve model effectiveness and extend its application in pharmaceutical product development and assessment.

Novel rod-like [Cu(phen)2(OAc)]·PF6 complex for high-performance visible-light-driven photocatalytic degradation of hazardous organic dyes: DFT approach, Hirshfeld and fingerprint plot analysis.

A novel octahedral distorted coordination complex was formed from a copper transition metal with a bidentate ligand (1,10-Phenanthroline) and characterized by Ultraviolet-visible spectroscopy, Ultraviolet-visible diffuse reflectance spectroscopy, Fourier-transform infrared spectroscopy, Brunauer-Emmett-Teller, Field emission scanning electron microscopy, and Single-crystal X-ray diffraction. The Hirshfeld surface and fingerprint plot analyses were conducted to determine the interactions between atoms in the Cu(II) complex. DFT calculations showed that the central copper ion and its coordinated atoms have an octahedral geometry. The Molecular electrostatic potential (MEP) map indicated that the copper (II) complex is an electrophilic compound that can interact with negatively charged macromolecules. The HOMO-LUMO analysis demonstrated the π nature charge transfer from acetate to phenanthroline. The band gap of [Cu(phen)2(OAc)]·PF6 photocatalyst was estimated to be 2.88 eV, confirming that this complex is suitable for environmental remediation. The photocatalytic degradation of erythrosine, malachite green, methylene blue, and Eriochrome Black T as model organic pollutants using the prepared complex was investigated under visible light. The [Cu(phen)2(OAc)]·PF6 photocatalyst exhibited degradation 94.7, 90.1, 82.7, and 74.3 % of malachite green, methylene blue, erythrosine, and Eriochrome Black T, respectively, under visible illumination within 70 min. The results from the Langmuir-Hinshelwood kinetic analysis demonstrated that the Cu(II) complex has a higher efficiency for the degradation of cationic pollutants than the anionic ones. This was attributed to surface charge attraction between photocatalyst and cationic dyes promoting removal efficiency. The reusability test indicated that the photocatalyst could be utilized in seven consecutive photocatalytic degradation cycles with an insignificant decrease in efficiency.

Dataset development of pre-formulation tests on fast disintegrating tablets (FDT): data aggregation.

OBJECTIVES: Tablet manufacturing development is costly, laborious, and time-consuming. Technologies related to artificial intelligence like ,predictive model ,can be used in the control process to facilitate and accelerate the tablet manufacturing process. predictive models have become popular recently. However, predictive models need a comprehensive dataset of related data in the field, due to the lack of a dataset of tablet formulations, the aim of this study is to aggregate and integrate fast disintegration tablet's formulation into a comprehensive dataset. DATA DESCRIPTION: The search strategy has been prepared between the years of 2010 to 2020, consisting of the keyword's 'formulation' ,'disintegrating' and 'Tablet', as well as their synonyms. By searching four databases, 1503 articles were retrieved, from these articles only 232 articles met all of the study's criteria. By reviewing 232 articles, 1982 formulations have been extracted, afterward pre-processing and cleaning data, contain steps of unifying the name and units, removing inappropriate formulations by an expert, and finally, data tidying was done on data. The developed dataset contains valuable information from various FDT's formulations, which can be used in pharmaceutical studies that are critical to the discovery and development of new drugs. this method can be applied to aggregate datasets from the other dosage forms.

Injectable In-Situ Forming Depot Based on PLGA and PLGA-PEG-PLGA for Sustained-Release of Risperidone: In Vitro Evaluation and Pharmacokinetics in Rabbits.

In the current research, novel drug delivery systems based on in situ forming gel (ISFG) (PLGA-PEG-PLGA) and in situ forming implant (ISFI) (PLGA) were developed for one-month risperidone delivery. In vitro release evaluation, pharmacokinetics, and histopathology studies of ISFI, ISFG, and Risperdal CONSTA® were compared in rabbits. Formulation containing 50% (w/w %) of PLGA-PEG-PLGA triblock revealed sustained release for about one month. Scanning electron microscopy (SEM) showed a porous structure for ISFI, while a structure with fewer pores was observed in the triblock. Cell viability in ISFG formulation in the first days was more than ISFI due to the gradual release of NMP to the release medium. Pharmacokinetic data displayed that optimal PLGA-PEG-PLGA creates a consistent serum level in vitro and in vivo through 30 days, and histopathology results revealed nearly slight to moderate pathological signs in the rabbit's organs. The shelf life of the accelerated stability test didn't affect the results of the release rate test and demonstrated stability in 24 months. This research confirms the better potential of the ISFG system compared with ISFI and Risperdal CONSTA®, which would increase patients' compliance and avoid problems of further oral therapy.

Computer-aided Drug Design and Drug Pharmacokinetic Prediction: A Mini-review.

Prediction of pharmacokinetics and drug targeting is a challenge in drug design. There are different types of software that can help to predict the pharmacokinetic profile of a drug. Quantitative structure-activity relationship (QSAR) modeling is used for drug design with less cost. Drug-excipient interactions are predicted by docking tools. Computerized drug target prediction and docking programs offer additional options to predict potential effects and adverse reactions of a given candidate as well as the best orientation of the compound on the receptor active site. Information on the absorption, distribution, metabolism and excretion of the drug in the body can enhance prediction of drug release and distribution in the blood and central nervous system (CNS). Computer- aided drug design and delivery can help to save the time and cost in the process of rational drug development.