Purpose: Drug-induced liver injury (DILI) is one of the most common and serious adverse drug reactions related to first-line anti-tuberculosis drugs in pediatric tuberculosis patients. This study aims to develop an automatic machine learning (AutoML) model for predicting the risk of anti-tuberculosis drug-induced liver injury (ATB-DILI) in children. Methods: A retrospective study was performed on the clinical data and therapeutic drug monitoring (TDM) results of children initially treated for tuberculosis at the affiliated Changsha Central Hospital of University of South China. After the features were screened by univariate risk factor analysis, AutoML technology was used to establish predictive models. The area under the receiver operating characteristic curve (AUC) was used to evaluate model’s performance, and then the TreeShap algorithm was employed to interpret the variable contributions. Results: A total of 184 children were enrolled in this study, of whom 19 (10.33%) developed ATB-DILI. Univariate analysis showed that seven variables were risk factors for ATB-DILI, including the plasma peak concentration (C_max) of rifampicin, body mass index (BMI), alanine aminotransferase, total bilirubin, total bile acids, aspartate aminotransferase and creatinine. Among the numerous predictive models constructed by the “H2O” AutoML platform, the gradient boost machine (GBM) model exhibited the superior performance with AUCs of 0.838 and 0.784 on the training and testing sets, respectively. The TreeShap algorithm showed that C_max of rifampicin and BMI were important features that affect the AutoML model’s performance. Conclusion: The GBM model established by AutoML technology shows high predictive accuracy and interpretability for ATB-DILI in children. The prediction model can assist clinicians to implement timely interventions and mitigation strategies, and formulate personalized medication regimens, thereby minimizing potential harm to high-risk children of ATB-DILI.

Tannic acid (TA) is the primary bioactive component in the gallnut (Galla chinensis) and has exhibited the anticancer effects. However, the mechanism of its anti-cancer activity in nasopharyngeal carcinoma (NPC) remains unclear. This research aims to explore the underlying mechanism of TA in the treatment of nasopharyngeal cancer using network pharmacology, molecular docking and experimental validation. Firstly, the targets of TA and NPC were predicted and collected through databases, and the intersection targets were identified. Subsequently, protein-protein interaction (PPI) network analysis, Gene Ontology (GO) enrichment, Kyoto Encyclopedia of Genes Genomes (KEGG) pathway enrichment analysis, molecular docking and molecular dynamics (MD) simulation were conducted to uncover the potential mechanisms of TA in treatment of NPC. Finally, in vitro experiments were utilized to verify the mechanism of TA with anticancer activity in NPC. The results of network pharmacology revealed 42 intersection targets between NPC-related targets and TA-related targets. The phosphoinositide 3-kinase (PI3K)/protein kinase B (AKT) signaling was identified as the main target pathway of TA against NPC. Additionally, molecular docking and MD simulation confirmed the closely binding affinities of TA with AKT1. Furthermore, the results of in vitro experiments demonstrated that TA exerts anticancer activity against NPC by targeting the PI3K/AKT signaling pathway, leading to the suppression of cell proliferation. TA is a promising therapeutic candidate for NPC through PI3K/AKT signaling pathway. These results provide insights into the clinical application of TA, particularly when considered in combination with other therapeutic modalities.

Background: Tuberculous meningitis (TBM) is a severe central nervous system infection with high disability and mortality rates. However, during TBM treatment, anti-tuberculosis drug-induced liver injury (ATB-DILI) often precipitates treatment interruption and contributes to poor clinical outcomes. This study aims to develop an automatic machine learning (AutoML) model for predicting the risk of ATB-DILI in TBM patients. Methods: A retrospective cohort study was conducted in adult TBM patients. After feature selection via least absolute shrinkage and selection operator (LASSO) regression, AutoML was employed to construct predictive models. The bootstrap resampling method was used for internal validation. Furthermore, feature importance, partial dependence plots, and SHapley Additive exPlanations (SHAP) analysis were utilized for model interpretation. Results: A total of 253 TBM patients were included in this study, of whom 54 (21.34%) developed ATB-DILI. LASSO regression analysis identified four characteristic factors, including cerebrospinal fluid (CSF) chloride, blood platelet, hypertension, and total bilirubin. Among the candidate models generated by AutoML, the optimal gradient boosting machine (GBM) model demonstrated superior performance. It achieved an optimism-corrected area under the receiver operating characteristic curve (AUC) of 0.828 (95% CI: 0.794–0.861) and an optimism-corrected area under the precision-recall curve (PR-AUC) of 0.711 (95% CI: 0.628–0.782). In addition, interpretability analysis revealed that CSF chloride was the most important variable for the optimal GBM model. Conclusion: The ATB-DILI prediction model, developed using AutoML technology, demonstrated high predictive ability and interpretability. It can assist clinicians in identifying TBM patients at risk of ATB-DILI, thereby optimizing patient management and facilitating the formulation of personalized medication regimens.

Zexie Decoction (ZXD) is a classical traditional Chinese medicine prescription that has long been used for the treatment of hyperlipidemia. However, its material basis and underlying mechanisms remain unclear. This research aims to explore the effective compounds and lipid-lowering mechanism of ZXD in the treatment of hyperlipidemia by integrating serum pharmacochemistry, network pharmacology and targeted lipidomics. A high-fat diet-induced hyperlipidemia mouse model was established for evaluating the therapeutic efficacy of ZXD. The absorbed components of ZXD in serum were identified using ultra-high performance liquid chromatography quadrupole time-of-flight mass spectrometry (UHPLC-QTOF-MS/MS). Network pharmacology analysis based on in vivo absorbed components was subsequently performed to construct molecular networks and predict potential mechanisms. Furthermore, targeted lipidomics was employed to characterize lysophospholipid metabolic changes associated with ZXD treatment for hyperlipidemia. Pharmacodynamic evaluation demonstrated that ZXD exerted significant lipid-lowering effects on hyperlipidemic mice. Serum pharmacochemistry analysis identified twelve absorbed constituents, including 3 prototype compounds and 9 metabolites. Network pharmacology analysis demonstrated that ZXD primarily modulated lipid metabolism-associated pathways, particularly the peroxisome proliferator-activated receptor (PPAR) signaling pathway and the lipid and atherosclerosis pathways. Molecular docking further revealed strong binding affinities between the major bioactive compounds of ZXD and key targets PPARA and PPARG. In addition, targeted lipidomics identified 36 lysophospholipid biomarkers associated with ZXD-mediated amelioration of hyperlipidemia. Integrated analysis indicates that ZXD alleviates hyperlipidemia in association with modulation of the PPAR signaling pathway and lysophospholipid metabolism, highlighting a potential lysophospholipid-PPAR regulatory mechanism.