Regional variations are found in the incidence and severity of the COVID‐19 infection. Human leukocyte antigen (HLA) polymorphism is one of the genetic factors that might have an impact on the outcome of the disease. This study explored the association between the HLA genotype and the severity of COVID‐19 among patients from South Asia. Blood samples from 95 Asians (Bangladeshis, Indians, and Pakistanis) with COVID‐19 were collected. The patients were divided according to the severity of their infection: mild (N = 64), severe (N = 31), and fatal (N = 20). DNA was extracted from all samples, and HLA genotyping was performed for both class I (A, B, and C) and class II (DRB1, DQA1, and DQB1) using the PCR‐rSSO (polymerase chain reaction–reverse sequence‐specific oligonucleotide) molecular method. The frequency of HLA‐B*51 was significantly higher among patients in the fatal group than among those in the mild infection group (15% vs. 4.7%, p = 0.027). Additionally, the frequency of HLA‐B*35 was significantly higher in the mild infection group than in the fatal group (21.1% vs. 7.5%, p = 0.050 [a borderline p‐value]). In terms of HLA class II, DRB1*13 was significantly observed in the fatal group than in the mild infection group (17.5% vs. 11.3%, p = 0.049). However, the p‐value for all alleles became insignificant after a statistical correction for the p‐values (p_c = 0.216, p_c = 0.4, and p_c = 0.49, respectively). Compared with all published data, this study highlights that the association between the HLA system and the COVID‐19 outcome might be ethnic‐dependent. Genetic variation between populations must be examined on a wider scale to assess infection prognosis and vaccine effectiveness.

(1) Background: Globally, the kidney donor shortage has made the allocation process critical for patients awaiting a kidney transplant. Adopting Machine Learning (ML) models for donor–recipient matching can potentially improve kidney allocation processes when compared with traditional points-based systems. (2) Methods: This study developed an ML-based approach for donor–recipient matching. A comprehensive evaluation was conducted using ten widely used classifiers (logistic regression, decision tree, random forest, support vector machine, gradient boosting, boost, CatBoost, LightGBM, naive Bayes, and neural networks) across three experimental scenarios to ensure a robust approach. The first scenario used the original dataset, the second used a merged version of the dataset, and the last scenario used a hierarchical architecture model. Additionally, a custom ranking algorithm was designed to identify the most suitable recipients. Finally, the ML-based donor–recipient matching model was integrated into a web-based platform called Nephron. (3) Results: The gradient boost model was the top performer, achieving a remarkable and consistent accuracy rate of 98% across the three experimental scenarios. Furthermore, the custom ranking algorithm outperformed the conventional cosine and Jaccard similarity methods in identifying the most suitable recipients. Importantly, the platform not only facilitated efficient patient selection and prioritisation for kidney allocation but can be flexibly adapted for other solid organ allocation systems built on similar criteria. (4) Conclusions: This study proposes an ML-based approach to optimize donor-recipient matching within the kidney allocation process. Successful implementation of this methodology demonstrates significant potential to enhance both efficiency and fairness in kidney transplantation.

Sirtuin 2 (SIRT2), an NAD+-dependent deacetylase, is crucial for regulating vital physiological processes, including aging, DNA repair, and cell cycle progression. Its abnormal activity is linked to diseases such as Parkinson’s disease, cancer, and metabolic disorders, making it a potential target for therapeutic intervention. While small molecule inhibitors have been studied, peptide-based inhibitors offer a promising alternative due to their selectivity and bioavailability. This study explores the effects of converting the naturally occurring cyclic inhibitor peptide of SIRT2 (S2iL5) into a non-cyclic form by replacing a residue with FAK (LYS + CF3CO⁻). The new peptide sequence, Tyr-His-Thr-Tyr-His-Val-FAK (LYS)-Arg-Arg-Thr-Asn-Tyr-Tyr-Cys, was modeled to confirm its stable conformation. Docking studies and MM/GBSA calculations showed that the non-cyclic peptide had a better binding free energy (−50.66 kcal/mol) compared to the cyclic S2iL5 (−49.44 kcal/mol). Further mutations generated 160,000 unique peptides, screened using a machine learning-based QSAR model. Three promising peptides (Peptide 1: YGGNNVKRRTNYYC, Peptide 2: YMGEWVKRRTNYYC, and Peptide 3: YGGNGVKRRTNYYC) were selected and further modeled. Molecular dynamics (MD) analyses demonstrated that Peptide 1 and Peptide 2 had significant potential as SIRT2 inhibitors, showing moderate stability and some structural flexibility. Their best binding free energies were −59.07 kcal/mol and −46.01 kcal/mol, respectively. The study aimed to enhance peptide flexibility and binding affinity, suggesting that optimized peptide-based inhibitors can interact effectively with SIRT2. However, further experimental validation is necessary to confirm these computational predictions and evaluate the therapeutic potential of the identified peptides.

An elevation in serum ferritin levels through an unknown mechanism was observed in COVID-19 infected patients. This study examined the association between patients’ HLA genotype and serum ferritin level modulation and also assessed the effect of serum ferritin levels on infection severity/mortality. One hundred and thirty-six COVID-19 Saudi patients were divided into two groups according to their ferritin levels: group 1 (500 ng/mL, N = 69). HLA genotyping (class I and II) was carried out through the rPCR-SSO method. High serum ferritin levels were associated with a significant increase in infection severity, as 75% of ICU patients showed high levels of ferritin compared to 43% of patients with moderate symptoms, p = .002. This elevation indicated a gender skew in that 56% of the infected male patients displayed high ferritin levels compared to 36.6% of the female patients, p = .03. In terms of mortality, 74% of patients with fatal outcomes had a high level of serum ferritin compared to 47% of recovered patients, p = .039. There was a significant difference in the HLA frequency between the two groups, with a predominance of HLA-A*01 in the low-ferritin group (19.4 vs. 6.5%, p = .002, p_c = .016) and predominance of C*03 in the high ferritin group (10.9 vs. 3%, p = .047, p_c = .27). High serum ferritin levels are associated with an increase in COVID-19 severity, which may be affected by HLA polymorphism.

Background/Objectives: Chronic kidney disease (CKD) remains a major public health challenge due to its silent progression and late clinical detection. Recent advances in machine learning have demonstrated promising performance in CKD detection; however, most existing approaches focus primarily on binary classification or rely on longitudinal or specialized biomarkers that are not routinely available in clinical practice. While several studies attempt risk stratification, few integrate risk modeling with stage-aware hierarchical decision frameworks suitable for routine clinical workflows. This study proposes a risk-oriented, explainable, and hierarchical machine learning framework for CKD classification using real-world laboratory data from 746 patients in a Saudi population. Methods: The proposed framework is designed as a hierarchical machine learning pipeline that mirrors clinical practice by sequentially identifying CKD presence, performing disease staging only for confirmed cases, and estimating risk for individuals without overt CKD. Specifically, an XGBoost model with recursive feature elimination (RFE) was employed for binary CKD detection, followed by a multilayer perceptron (MLP) model with SelectKBest for stage classification. A unified preprocessing pipeline, clinically informed feature selection, and validated machine learning models were employed to develop the hierarchical prediction system. Results: The system achieved 97% accuracy and F1-score in binary CKD classification, and up to 85% accuracy and 86% F1-score in stage classification. In addition, an interpretable risk scoring mechanism and SHAP-based explanations enabled early identification of CKD-like laboratory patterns using routine laboratory tests. Conclusions: The proposed system provides a transparent and deployable framework that supports preventive nephrology and clinically meaningful decision-making.