Background/aims: The persistent existence of pathological cardiac remodeling, resulting from aortic stenosis, is related to poor clinical prognosis after successful transcatheter aortic valve replacement (TAVR). Sacubitril/valsartan (Sac/Val), comprising an angiotensin receptor blocker and a neprilysin inhibitor, has been demonstrated to have a beneficial effect against pathological cardiac remodeling, including cardiac fibrosis and inflammation in heart failure. The aim of this study was to determine whether Sac/Val exerts a cardioprotective effect after pressure unloading in mice. Methods and results: Male C57BL/6 J mice were subjected to debanding (DB) surgery after 8 weeks (wk) of aortic banding (AB). Cardiac function was assessed by echocardiography, which indicated a protective effect of Sac/Val after DB. After treatment with Sac/Val post DB, decreased heart weight and myocardial cell size were observed in mouse hearts. In addition, histological analysis, immunofluorescence, and western blot results showed that Sac/Val attenuated cardiac fibrosis and inflammation after DB. Finally, our data indicated that Sac/Val treatment could significantly suppress NF-κB signaling and NLRP3 inflammasome activation in mice after relief of pressure overload. Conclusion: Sac/Val exerted its beneficial effects to prevent maladaptive cardiac fibrosis and dysfunction in mice following pressure unloading, which was at least partly due to the inhibition of NLRP3 inflammasome activation.

Traditional Medicine (TM), especially Traditional Chinese Medicine (TCM), is renowned for its distinctive "multi-component-multi-target-multi-pathway" mode of action, which exhibits a unique overall regulatory therapeutic effect. However, the intricate nature of TCM poses significant challenges in identifying active components, elucidating mechanisms of action, and standardizing clinical practices. The advancement of modern science and technology has led to the gradual modernization of TCM research. Network pharmacology (NP) has emerged as a pivotal framework for comprehending the holistic mechanisms of TCM, offering a crucial avenue for unveiling intricate biological networks by integrating chemical information, omics data, and clinical efficacy evidence. Nevertheless, conventional NP approaches exhibit notable limitations, including substantial noise, high dimensionality, challenges in capturing dynamics and time series, and inadequate cross-scale integration, thereby constraining their utility in precise mechanism analysis and clinical translation. In recent years, artificial intelligence (AI), particularly machine learning (ML), deep learning (DL), and graph neural networks (GNN), have empowered NP in an unprecedented way, enabling it to systematically and accurately analyze the cross-scale mechanisms of TCM from molecular interactions to patient efficacy. This review will systematically examine the latest developments in artificial intelligence-network pharmacology (AI-NP) methodology, with a focus on typical research cases of multi-scale mechanism analysis at the molecular, cellular, tissue, and patient levels. It will systematically summarize the challenges currently faced and explore future development directions to fully unlock the systemic therapeutic wisdom of TCM.

The formula of Compound Centella mainly contains 3 traditional Chinese herbs: Centella asiatica (L.) Urb. (JiXueCao), Astragalus Membranaceus Fish. (HuangQi), and Tripterygium wilfordii Hook. f. (LeiGongTeng). Though this formula is effective for treating diabetic kidney disease (DKD) in clinic, the exact mechanism is still unclear. This study aims to investigate the effect and antioxidant mechanism of Compound Centella on DKD rats. High‐performance liquid chromatography (HPLC) was applied to analyse 3 herbs in Compound Centella. Sprague‐Dawley rats were divided into the normal group (NG), DKD group (DKDG), Compound Centella group (CCG), and losartan group (LG), with 8 rats in each group. On the first day of the experiment, rats in the NG were fed with ordinary –feed, while the other groups were fed with high‐fat and high‐sugar feed. On the 29^th day, except the NG, the other 3 groups received a single intraperitoneal injection of streptozocin (STZ, 35 mg/kg). Fasting blood glucose (FBG) was measured on the 1^st day, 32^nd day, 46^th day, 56^th day, 84^th day, and 112^th day. Total protein/creatinine ratio of urine was determined by the phenol red assay on the 1^st day and 112^th day. Serum creatinine (Scr) was determined by an automatic biochemical analyser on the 112^th day. Kidneys were collected on the 112^th day for analysis and evaluation. Periodic acid‐Schiff (PAS) staining, hematoxylin‐eosin (HE) staining, and transmission electron microscopy were used to observe kidney pathological changes. The mRNA and protein expressions of Kelch‐like ECH‐associated protein 1 (Keap1) and nuclear factor‐erythroid 2‐related factor 2 (Nrf2) in renal tissues were detected by RT‐qPCR, Western blot, and immunohistochemistry. Oxidative stress was evaluated by detecting the levels of malondialdehyde (MDA) and heme oxidase‐1 (HO‐1). The results showed that the content of asiaticoside, astragaloside, and triptolide in the herb was 5960, 809, and 2.42 μg/g and in the Compound Centella was 340, 64, and 0.1403 μg/mL by HPLC. Compound Centella reduced the urine protein/creatinine ratio and improved renal pathology in the kidneys of DKD rats. In addition, the mRNA and protein expressions of Keap1 and Nrf2 in kidneys were upregulated by Compound Centella. The expressions of MDA were downregulated but HO‐1 were upregulated by Compound Centella. Therefore, the protective effect of Compound Centella in the kidney of DKD rats may be related to regulating the Keap1‐Nrf2‐ARE pathway under oxidative stress, suggesting Compound Centella as a promising treatment against DKD.

Diabetic kidney disease (DKD) is the most common microvascular complication of diabetes and a leading cause of end-stage renal disease (ESRD). Traditionally, its pathogenesis has been attributed to hyperglycemia-induced metabolic disturbances, glomerular hyperperfusion and hyperfiltration, activation of the renin–angiotensin–aldosterone system (RAAS), and oxidative stress. Recent evidence, however, indicates that chronic inflammation and immune dysregulation also play critical roles in DKD progression.Impaired macrophage cholesterol efflux (MCE) has emerged as a central pathogenic mechanism in DKD. Under hyperglycemic conditions, advanced glycation end-products (AGEs) suppress the LXR/PPARγ signaling pathway and downregulate downstream transporters ABCA1 and ABCG1, thereby reducing cholesterol efflux. This disruption promotes lipid accumulation and macrophage foam cell formation, leading to the sustained release of pro-inflammatory cytokines such as TNF-α, IL-1β, and MCP-1, which accelerate glomerulosclerosis and tubulointerstitial fibrosis. MCE dysfunction thus provides a mechanistic link bridging metabolic dysregulation and immune-mediated inflammation in DKD.Therapeutic strategies targeting MCE show promising potential. Pharmacological agents such as LXR/RXR agonists, PPARγ activators, sodium-glucose cotransporter 2(SGLT2) inhibitors, and glucagon-like peptide-1 receptor agonists(GLP-1RAs) enhance cholesterol transport, promote macrophage polarization toward the M2 anti-inflammatory phenotype, and ameliorate renal injury. In addition, natural bioactive compounds and nanodelivery systems can selectively modulate ABCA1/G1-mediated cholesterol efflux, attenuating lipid accumulation.In conclusion, this study highlights the pivotal role of macrophage cholesterol efflux in DKD pathogenesis beyond traditional metabolic factors and proposes novel MCE-targeted therapeutic strategies, offering new insights for the prevention and treatment of DKD.

Background: IgA nephropathy (IgAN) is a leading cause of renal failure, characterized by significant clinical and pathological heterogeneity. Accurate subtype classification remains challenging due to overlapping clinical manifestations and the multidimensional nature of data. Traditional methods often fail to fully capture IgAN’s complexity, limiting their clinical applicability. This study introduces MAL-Net, a deep learning framework for multi-label classification of IgAN subtypes, leveraging multidimensional clinical data and incorporating sensor-based inputs such as laboratory indices and symptom tracking. Methods: MAL-Net integrates Long Short-Term Memory (LSTM) networks with Multi-Head Attention (MHA) mechanisms to effectively capture sequential and contextual dependencies in clinical data. A memory network module extracts features from clinical sensors and records, while the MHA module emphasizes critical features and mitigates class imbalance. The model was trained and validated on clinical data from 500 IgAN patients, incorporating demographic, laboratory, and symptomatic variables. Performance was evaluated against six baseline models, including traditional machine learning and deep learning approaches. Results: MAL-Net outperformed all baseline models, achieving 91% accuracy and an AUC of 0.97. The integration of MHA significantly enhanced classification performance, particularly for underrepresented subtypes. The F1-score for the Ni-du subtype improved by 0.8, demonstrating the model’s ability to address class imbalance and improve precision. Conclusions: MAL-Net provides a robust solution for multi-label IgAN subtype classification, tackling challenges such as data heterogeneity, class imbalance, and feature interdependencies. By integrating clinical sensor data, MAL-Net enhances IgAN subtype prediction, supporting early diagnosis, personalized treatment, and improved prognosis evaluation.

Objective The aim of this study is to analyze the 5 year prognosis of IgA nephropathy (IgAN) patients with varying degrees of foot process effacement (FPE). Method We retrospectively analyzed the clinical and pathological data of 863 patients with primary IgAN confirmed by renal biopsy at Hangzhou Traditional Chinese Medicine Hospital from 1 January 2015 to 31 December 2018. According to the degree of FPE, the group was divided into extensive FPE group and segmental FPE group. After propensity score matching (PSM), the effect of different levels of FPE on the prognosis of IgAN was analyzed using Log-rank tests. Result Notably, 61(7.1%) of the 863 patients reached renal composite endpoint. 53 patients in the foot process extensive effacement group were matched with 100 patients in the segmental effacement group after propensity score matching. There were no significant differences in any of the baseline characteristics between the two groups (P > 0.05). Additionally, Kaplan–Meier survival analysis revealed that patients with extensive FPE (≥ 50%) exhibited a significantly poorer prognosis compared with those with segmental FPE (< 50%) (Log-rank test P = 0.030).In the Pearson correlation analysis, FPE was moderately positively associated with albuminuria and mildly negatively associated with eGFR. Conclusion Extensive foot process effacement is an independent risk factor for IgAN prognosis.