Precise estimation of pharmaceutical solubility in supercritical carbon dioxide (scCO ₂ ) is essential for optimizing pharmaceutical applications, including particle size reduction, the development of solid dispersions, and controlled-release formulations. In this research, we present a comparative analysis of three machine learning regression models—Lasso Regression, Gaussian Process Regression (GPR), and Nu-Support Vector Regression (Nu-SVR)—for predicting the solubility of exemestane (EXE), a poorly water-soluble anticancer drug, in scCO ₂ under varying temperature and pressure conditions. The dataset used in this work consists of 45 experimental measurements encompassing temperature (T in K), pressure (P in MPa), and solubility (in g/L) of EXE. The dataset was divided into training and testing data subsets to facilitate reliable model validation. Model performance was thoroughly evaluated using metrics such as the R², RMSE, MAE, and AARD%. Additionally, decision surfaces and observed-versus-predicted plots were generated to visually assess model accuracy. Among the applied models, Gaussian Process Regression demonstrated superior predictive capability with an R² score of 0.996, Maximum error of 3.27, significantly outperforming both Lasso and Nu-SVR models. These results indicate that GPR effectively captures the nonlinear relationship between process variables and drug solubility, offering high generalization and precision. Feature importance analysis confirmed that pressure has the most significant influence on solubility behavior, while temperature also contributes positively to solubility trends. Residual analysis further validated the consistency and reliability of the GPR-based model. This work contributes to the growing application of machine learning techniques in pharmaceutical process modeling, particularly in supercritical fluid-based drug delivery systems. The proposed GPR model provides a reliable and efficient tool for predicting solubility, supporting the design and optimization of scCO ₂ -assisted drug formulation methods.

One of the most common forms of dementia and a neurodegenerative illness is Alzheimers disease (AD), which is distinguished by impaired memory and cognitive dysfunction. Decades of research have been devoted to determining its etiology, pathogenic processes, and biomarkers to facilitate early identification and clinical investigations for therapy. Neural atrophy and broken connections between neurons are the outcomes of the illness. The amyloid beta (Aβ) cascade is among the most widely recognized and important hypotheses of the numerous hypotheses regarding the pathogenesis of AD. This theory suggests that the breakdown of the amyloid precursor protein (APP) produces Aβ monomers. These monomers are then converted into hazardous oligomers, which in turn form β-sheets, fibrils, and plaques after being formed. The amyloid cascade theory was covered in this review, along with a summary of how it is used to diagnose and treat Alzheimers. Specifically, we covered the drawbacks, potential, and significant unsolved issues with the anti-Aβ therapy that is now in use, as well as plans for more research and the creation of more workable Aβ-targeted methods to optimize AD early detection and management.

Background: Postmenopausal women are at high risk of Alzheimer’s disease (AD) incidence and progression. Irisin, an exercise-induced myokine, has neuroprotective and antiaging effects against AD, especially in menopausal women suffering from insulin resistance (IR). For the first time, the novel role of irisin induced by melatonin (MTN) or/and physical exercise (PHE) was investigated in the current ovariectomized (OVX)/AD rat model by modulating brain neuroinflammation and IR-related markers. Methods: Fifty female Wistar rats were divided into five groups, with one representing a sham group. AD was induced in the other four bilateral OVX rat groups by daily intraperitoneal injection of D-galactose/AlCl₃ (60 and 10 mg/kg, respectively) for 42 days. Group III–V: Animals were exposed to MTN (10 mg/kg/day; i.p.), PHE, and a combination of these, respectively, in the final 14 days of the experiment. Results: The OVX/AD rats showed significant deterioration in learning, memory, neurochemical, and histopathological examinations, while the MTN or/and PHE treatments significantly increased serum and brain irisin, improving memory in a Y-maze assessment. Thus, hippocampal histopathological alterations and IR-related markers decreased. In addition, suppressed hippocampal amyloid-beta protein expression and neuroinflammatory content of tumor necrosis factor-alpha (TNF-α), p38 mitogen-activated protein kinase (p38 MAPK), and NOD-like receptor protein-3 (NLRP3) were associated with an increase in peroxisome proliferator-activated receptor-gamma (PPAR-γ) protein expression and insulin-like growth factor-1 content in hippocampal tissues, collectively suppressing glial fibrillary acidic protein (GFAP) content, leading to an increase in brain-derived neurotrophic factor expression. Conclusions: Irisin induction may serve as a novel avenue in AD/menopause treatment and prevention via modulating the TNF-α/p38 MAPK/PPAR-γ/NLRP3/GFAP pathway.