Comprehensive machine learning models for predicting therapeutic targets in type 2 diabetes utilizing molecular and biochemical features in rats.

Introduction: With the increasing prevalence of type 2 diabetes mellitus (T2DM), there is an urgent need to discover effective therapeutic targets for this complex condition. Coding and non-coding RNAs, with traditional biochemical parameters, have shown promise as viable targets for therapy. Machine learning (ML) techniques have emerged as powerful tools for predicting drug responses. Method: In this study, we developed an ML-based model to identify the most influential features for drug response in the treatment of type 2 diabetes using three medicinal plant-based drugs (Rosavin, Caffeic acid, and Isorhamnetin), and a probiotics drug (Z-biotic), at different doses. A hundred rats were randomly assigned to ten groups, including a normal group, a streptozotocin-induced diabetic group, and eight treated groups. Serum samples were collected for biochemical analysis, while liver tissues (L) and adipose tissues (A) underwent histopathological examination and molecular biomarker extraction using quantitative PCR. Utilizing five machine learning algorithms, we integrated 32 molecular features and 12 biochemical features to select the most predictive targets for each model and the combined model. Results and discussion: Our results indicated that high doses of the selected drugs effectively mitigated liver inflammation, reduced insulin resistance, and improved lipid profiles and renal function biomarkers. The machine learning model identified 13 molecular features, 10 biochemical features, and 20 combined features with an accuracy of 80% and AUC (0.894, 0.93, and 0.896), respectively. This study presents an ML model that accurately identifies effective therapeutic targets implicated in the molecular pathways associated with T2DM pathogenesis.

Rosavin improves insulin resistance and alleviates hepatic and kidney damage via modulating the cGAS-STING pathway and autophagy signaling in HFD/STZ-induced T2DM animals.

Background: Inflammation-mediated insulin resistance in type 2 diabetes mellitus (T2DM) increases complications, necessitating investigation of its mechanism to find new safe therapies. This study investigated the effect of rosavin on the autophagy and the cGAS-STING pathway-related signatures (ZBP1, STING1, DDX58, LC3B, TNF-α) and on their epigenetic modifiers (miR-1976 and lncRNA AC074117.2) that were identified from in silico analysis in T2DM animals. Methods: A T2DM rat model was established by combining a high-fat diet (HFD) and streptozotocin (STZ). After four weeks from T2DM induction, HFD/STZ-induced T2DM rats were subdivided into an untreated group (T2DM group) and three treated groups which received 10, 20, or 30 mg per kg of R. rosea daily for 4 weeks. Results: The study found that rosavin can affect the cGAS-STING pathway-related RNA signatures by decreasing the expressions of ZBP1, STING1, DDX58, and miR-1976 while increasing the lncRNA AC074117.2 level in the liver, kidney, and adipose tissues. Rosavin prevented further weight loss, reduced serum insulin and glucose, improved insulin resistance and the lipid panel, and mitigated liver and kidney damage compared to the untreated T2DM group. The treatment also resulted in reduced inflammation levels and improved autophagy manifested by decreased immunostaining of TNF-α and increased immunostaining of LC3B in the liver and kidneys of the treated T2DM rats. Conclusion: Rosavin has shown potential in attenuating T2DM, inhibiting inflammation in the liver and kidneys, and improving metabolic disturbances in a T2DM animal model. The observed effect was linked to the activation of autophagy and suppression of the cGAS-STING pathway.

The Diagnostic Value of Cadherin 17 and CDX2 Expression as Immunohistochemical Markers in Colorectal Adenocarcinoma.

BACKGROUND: Colorectal cancer is a major cause of morbidity and mortality throughout the world. Although the diagnosis of colorectal cancer is straightforward in primary site, yet it may represent a diagnostic problem in metastatic tumor of unknown primary origin. Hence, immunohistochemical analysis in combination with morphologic assessment and correlation with clinical data becomes crucial, because it is important to specify the primary site of metastasis since some specific tumor types may respond well to targeted molecular therapies. Therefore, establishment of reliable diagnostic markers that confirm or rule out colorectal origin is mandatory. AIM: To study the expression of cadherin 17 and CDX2 in colorectal carcinoma and to evaluate their diagnostic roles in identifying metastatic colonic from non-colonic adenocarcinomas in cancer of unknown primary site. DESIGN AND METHODS: This retrospective study included 65 cases of adenocarcinomas: 35 cases of colorectal adenocarcinoma (primary or metastatic) and 30 cases of non-colorectal adenocarcinoma. They were retrieved from the archives of Pathology Department of Ain Shams University and Ain Shams University Specialized Hospitals during the period from 2010 to 2015. Immunohistochemical study was performed using cadherin 17 and CDX2 antibodies. RESULTS: The sensitivity and specificity of CDX2 and cadherin 17 are 97.1% and 53.3% and 100% and 50% in detecting colonic adenocarcinoma respectively. The PPV, NPV, and overall accuracy of CDX2 versus cadherin 17 were 70.8%, 94.1%, and 76.9% versus 70%, 100%, and 76.9% respectively. CONCLUSION: Cadherin 17 is a more sensitive marker than CDX2 in diagnosis of carcinoma of unknown primary site especially when colorectal carcinoma is suspected.