The mechanisms of Qizhu Tangshen formula in the treatment of diabetic kidney disease: Network pharmacology, machine learning, molecular docking and experimental assessment

AI empowering traditional Chinese medicine?

For centuries, Traditional Chinese Medicine (TCM) has been a prominent treatment method in China, incorporating acupuncture, herbal remedies, massage, and dietary therapy to promote holistic health and healing. TCM has played a major role in drug discovery, with over 60% of small-molecule drugs approved by the FDA from 1981 to 2019 being derived from natural products. However, TCM modernization faces challenges such as data standardization and the complexity of TCM formulations. The establishment of comprehensive TCM databases has significantly improved the efficiency and accuracy of TCM research, enabling easier access to information on TCM ingredients and encouraging interdisciplinary collaborations. These databases have revolutionized TCM research, facilitating advancements in TCM modernization and patient care. In addition, advancements in AI algorithms and database data quality have accelerated progress in AI for TCM. The application of AI in TCM encompasses a wide range of areas, including herbal screening and new drug discovery, diagnostic and treatment principles, pharmacological mechanisms, network pharmacology, and the incorporation of innovative AI technologies. AI also has the potential to enable personalized medicine by identifying patterns and correlations in patient data, leading to more accurate diagnoses and tailored treatments. The potential benefits of AI for TCM are vast and diverse, promising continued progress and innovation in the field.

Molecular mechanism of the treatment of lung adenocarcinoma by Hedyotis Diffusa: an integrative study with real-world clinical data and experimental validation

Background

With a variety of active ingredients, Hedyotis Diffusa (H. diffusa) can treat a variety of tumors. The purpose of our study is based on real-world data and experimental level, to double demonstrate the efficacy and possible molecular mechanism of H. diffusa in the treatment of lung adenocarcinom (LUAD).

Methods

Phenotype-genotype and herbal-target associations were extracted from the SymMap database. Disease-gene associations were extracted from the MalaCards database. A molecular network-based correlation analysis was further conducted on the collection of genes associated with TCM and the collection of genes associated with diseases and symptoms. Then, the network separation SAB metrics were applied to evaluate the network proximity relationship between TCM and symptoms. Finally, cell apoptosis experiment, Western blot, and Real-time PCR were used for biological experimental level validation analysis.

Results

Included in the study were 85,437 electronic medical records (318 patients with LUAD). The proportion of prescriptions containing H. diffusa in the LUAD group was much higher than that in the non-LUAD group (p < 0.005). We counted the symptom relief of patients in the group and the group without the use of H. diffusa: except for symptoms such as fatigue, palpitations, and dizziness, the improvement rate of symptoms in the user group was higher than that in the non-use group. We selected the five most frequently occurring symptoms in the use group, namely, cough, expectoration, fatigue, chest tightness and wheezing. We combined the above five symptom genes into one group. The overlapping genes obtained were CTNNB1, STAT3, CASP8, and APC. The selection of CTNNB1 target for biological experiments showed that the proliferation rate of LUAD A549 cells in the drug intervention group was significantly lower than that in the control group, and it was concentration-dependent. H. diffusa can promote the apoptosis of A549 cells, and the apoptosis rate of the high-concentration drug group is significantly higher than that of the low-concentration drug group. The transcription and expression level of CTNNB1 gene in the drug intervention group were significantly decreased.

Conclusion

H. diffusa inhibits the proliferation and promotes apoptosis of LUAD A549 cells, which may be related to the fact that H. diffusa can regulate the expression of CTNNB1.

"Qi Nan" agarwood restores podocyte autophagy in diabetic kidney disease by targeting EGFR signaling pathway

BACKGROUND

Diabetic kidney disease (DKD) is a microvascular complication of diabetes mellitus, contributing to end-stage renal disease with limited treatment options. The development of DKD is attributed to podocyte injury resulting from abnormal podocyte autophagy. Consequently, the restoration of podocyte autophagy is deemed a practicable approach in the treatment of DKD.

METHODS

Diabetic mice were induced by streptozotocin and high-fat diet feeding. Following 8 weeks of "QN" agarwood treatment, metrics such as albuminuria, serum creatinine (Scr), and blood urea nitrogen (BUN) were evaluated. Renal histological lesions were evaluated by H&E, PAS, Masson, and Sirius red staining. Evaluation of the effects of "QN" agarwood on renal inflammation and fibrosis in DKD mice through WB, q-PCR, and IHC staining analysis. Cytoscape 3.7.1 was used to construct a PPI network. With the DAVID server, the gene ontology (GO) functional annotation and the Kyoto encyclopedia of genes and genomes (KEGG) signaling pathways of the target enrichment were performed. Molecular docking and binding affinity calculations were conducted using AutoDock, while PyMOL software was employed for visualizing the docking results of active compounds and protein targets.

RESULTS

The results of this study show that "QN" agarwood reduced albuminuria, Scr, and BUN in DKD mice, and improved the renal pathological process. Additionally, "QN" agarwood was observed to downregulate the mRNA and protein expression levels of pro-inflammatory and pro-fibrotic factors in the kidneys of DKD mice. Network pharmacology predicts that "QN" agarwood modulates the epidermal growth factor receptor (EGFR) signaling pathway. "QN" agarwood can increase the expression of LC3B and Nphs1 in DKD mice while reducing the expression of EGFR.

CONCLUSION

The present study demonstrated that "QN" agarwood ameliorated renal injury in DKD by targeting EGFR and restoring podocyte autophagy.

Analysis of microRNA expression in rat kidneys after VEGF inhibitor treatment under different degrees of hypoxia

Previously, we found that the incidence of kidney injury in patients with chronic hypoxia was related to the partial pressure of arterial oxygen. However, at oxygen concentrations that contribute to kidney injury, the changes in the relationship between microRNAs (miRNAs) and the hypoxia-inducible factor-1α (HIF-1α)-vascular endothelial growth factor (VEGF) axis and the key miRNAs involved in this process have not been elucidated. Therefore, we elucidated the relationship between VEGF and kidney injury at different oxygen concentrations and the mechanisms mediated by miRNAs. Sprague-Dawley rats were exposed to normobaric hypoxia and categorized into six groups based on the concentration of the oxygen inhaled and injection of the angiogenesis inhibitor bevacizumab, a humanized anti-VEGF monoclonal antibody. Renal tissue samples were processed to determine pathological and morphological changes and HIF-1α, VEGF, and miRNA expression. We performed a clustering analysis of high-risk pathways and key hub genes. The results were validated using two Gene Expression Omnibus datasets (GSE94717 and GSE30718). As inhaled oxygen concentration decreased, destructive changes in the kidney tissues became more severe. Although the kidney possesses a self-protective mechanism under an intermediate degree of hypoxia (10% O2), bevacizumab injections disrupted this mechanism, and VEGF expression was associated with the ability of the kidney to repair itself. rno-miR-124-3p was identified as a crucial miRNA; a key gene target, Mapk14, was identified during this process. VEGF plays an important role in kidney protection from injury under different hypoxia levels. Specific miRNAs and their target genes may serve as biomarkers that provide new insights into kidney injury treatment.NEW & NOTEWORTHY Renal tolerance to hypoxic environments is limited, and the degree of hypoxia does not show a linear relationship with angiogenesis. VEGF plays an important role in the kidney's self-protective mechanism under different levels of hypoxia. miR-124-3p may be particularly important in kidney repair, and it may modulate VEGF expression through the miR-124-3p/Mapk14 signaling pathway. These microRNAs may serve as biomarkers that provide new insights into kidney injury treatment.

Increasing transparency in machine learning through bootstrap simulation and shapely additive explanations

Machine learning methods are widely used within the medical field. However, the reliability and efficacy of these models is difficult to assess, making it difficult for researchers to identify which machine-learning model to apply to their dataset. We assessed whether variance calculations of model metrics (e.g., AUROC, Sensitivity, Specificity) through bootstrap simulation and SHapely Additive exPlanations (SHAP) could increase model transparency and improve model selection. Data from the England National Health Services Heart Disease Prediction Cohort was used. After comparison of model metrics for XGBoost, Random Forest, Artificial Neural Network, and Adaptive Boosting, XGBoost was used as the machine-learning model of choice in this study. Boost-strap simulation (N = 10,000) was used to empirically derive the distribution of model metrics and covariate Gain statistics. SHapely Additive exPlanations (SHAP) to provide explanations to machine-learning output and simulation to evaluate the variance of model accuracy metrics. For the XGBoost modeling method, we observed (through 10,000 completed simulations) that the AUROC ranged from 0.771 to 0.947, a difference of 0.176, the balanced accuracy ranged from 0.688 to 0.894, a 0.205 difference, the sensitivity ranged from 0.632 to 0.939, a 0.307 difference, and the specificity ranged from 0.595 to 0.944, a 0.394 difference. Among 10,000 simulations completed, we observed that the gain for Angina ranged from 0.225 to 0.456, a difference of 0.231, for Cholesterol ranged from 0.148 to 0.326, a difference of 0.178, for maximum heart rate (MaxHR) ranged from 0.081 to 0.200, a range of 0.119, and for Age ranged from 0.059 to 0.157, difference of 0.098. Use of simulations to empirically evaluate the variability of model metrics and explanatory algorithms to observe if covariates match the literature are necessary for increased transparency, reliability, and utility of machine learning methods. These variance statistics, combined with model accuracy statistics can help researchers identify the best model for a given dataset.