Natural product-based drug combinations (NPDCs) present distinctive advantages in treating complex diseases. While high-throughput screening (HTS) and conventional computational methods have partially accelerated synergistic drug combination discovery, their applications remain constrained by experimental data fragmentation, high costs, and extensive combinatorial space. Recent developments in artificial intelligence (AI), encompassing traditional machine learning and deep learning algorithms, have been extensively applied in NPDC identification. Through the integration of multi-source heterogeneous data and autonomous feature extraction, prediction accuracy has markedly improved, offering a robust technical approach for novel NPDC discovery. This review comprehensively examines recent advances in AI-driven NPDC prediction, presents relevant data resources and algorithmic frameworks, and evaluates current limitations and future prospects. AI methodologies are anticipated to substantially expedite NPDC discovery and inform experimental validation.
Artificial Intelligence ; Biological Products/chemistry* ; Humans ; Drug Combinations ; Drug Discovery/methods* ; Machine Learning ; Algorithms

Mesenchymal stem cells (MSCs) have been widely used in the treatment of various autoimmune and inflammation-related diseases due to their potent immunomodulatory properties. Several studies have demonstrated that MSC-mediated immunomodulation is complex and bidirectional, with the in vivo microenvironment influencing the direction of this modulation. Indoleamine-2,3-dioxygenase (IDO), an immunosuppressive factor, has been identified as a key "switch" in the immunomodulatory role of MSCs. In this review, we explore how IDO functions as a critical regulator of MSC immunoregulatory plasticity. We delve into the mechanisms by which changes in IDO expression affect the function of various immune cells, summarize relevant research and clinical advances regarding the role of IDO expression in MSC-based therapies for various diseases, and discuss potential therapeutic strategies that target IDO to enhance the stability of MSC therapeutic effects. This provides a theoretical foundation for optimizing MSCs as safer and more effective clinical therapeutic agents.

Advancements in artificial intelligence (AI) and emerging technologies are rapidly expanding the exploration of chemical space, facilitating innovative drug discovery. However, the transformation of novel compounds into safe and effective drugs remains a lengthy, high-risk, and costly process. Comprehensive early-stage evaluation is essential for reducing costs and improving the success rate of drug development. Despite this need, no comprehensive tool currently supports systematic evaluation and efficient screening. Here, we present druglikeFilter, a deep learning-based framework designed to assess drug-likeness across four critical dimensions: 1) physicochemical rule evaluated by systematic determination, 2) toxicity alert investigated from multiple perspectives, 3) binding affinity measured by dual-path analysis, and 4) compound synthesizability assessed by retro-route prediction. By enabling automated, multidimensional filtering of compound libraries, druglikeFilter not only streamlines the drug development process but also plays a crucial role in advancing research efforts towards viable drug candidates, which can be freely accessed at https://idrblab.org/drugfilter/.

Increasing evidence showed that histone deacetylase 6 (HDAC6) dysfunction is directly associated with the onset and progression of various diseases, especially cancers, making the development of HDAC6-targeted anti-tumor agents a research hotspot. In this study, artificial intelligence (AI) technology and molecular simulation strategies were fully integrated to construct an efficient and precise drug screening pipeline, which combined Voting strategy based on compound-protein interaction (CPI) prediction models, cascade molecular docking, and molecular dynamic (MD) simulations. The biological potential of the screened compounds was further evaluated through enzymatic and cellular activity assays. Among the identified compounds, Cmpd.18 exhibited more potent HDAC6 enzyme inhibitory activity (IC₅₀ = 5.41 nM) than that of tubastatin A (TubA) (IC₅₀ = 15.11 nM), along with a favorable subtype selectivity profile (selectivity index ≈ 117.23 for HDAC1), which was further verified by the Western blot analysis. Additionally, Cmpd.18 induced G2/M phase arrest and promoted apoptosis in HCT-116 cells, exerting desirable antiproliferative activity (IC₅₀ = 2.59 μM). Furthermore, based on long-term MD simulation trajectory, the key residues facilitating Cmpd.18's binding were identified by decomposition free energy analysis, thereby elucidating its binding mechanism. Moreover, the representative conformation analysis also indicated that Cmpd.18 could stably bind to the active pocket in an effective conformation, thus demonstrating the potential for in-depth research of the 2-(2-phenoxyethyl)pyridazin-3(2H)-one scaffold.

Objective:To investigate the clinical characteristics and cardiac magnetic resonance (CMR) features of cardiac sarcoidosis (CS).Methods:This retrospective study included 8 consecutive patients with pathologically confirmed CS by endomyocardial biopsy from Fuwai Hospital, Chinese Academy of Medical Sciences, between January 2012 and September 2024. All patients underwent comprehensive CMR examinations including cine imaging and late gadolinium enhancement (LGE) imaging. Clinical data, including electrocardiographic findings, were collected. CMR phenotyping was performed based on imaging characteristics, and cardiac structure and function parameters were evaluated. LGE analysis was conducted using the American Heart Association 17-segment model to assess the distribution patterns and involvement sites.Results:The most common clinical symptoms were chest tightness (4 patients), palpitations (4 patients), and shortness of breath (6 patients). Electrocardiographic abnormalities included atrioventricular block in 4 patients, right bundle branch block in 2 patients, left bundle branch block in 2 patients, frequent premature ventricular contractions in 4 patients, and non-sustained ventricular tachycardia in 5 patients. CMR phenotyping revealed hypertrophic cardiomyopathy pattern in 3 patients, with 2 patients maintaining normal biventricular function and 1 patient showing significantly reduced biventricular systolic function. Dilated cardiomyopathy pattern was identified in 4 patients, all demonstrating significantly impaired biventricular systolic function. One patient exhibited another phenotype with preserved biventricular systolic function. LGE analysis demonstrated that the anterior wall and anterior septum (segments 1, 2, 7, 8) were the most frequently involved regions, followed by the lateral and inferior walls (segments 5, 6, 11, 12). Subepicardial involvement was the predominant pattern of myocardial enhancement.Conclusions:Cardiac sarcoidosis exhibits diverse clinical manifestations and heterogeneous imaging characteristics. CMR not only provides a comprehensive assessment of cardiac structure and function but also reveals distinctive myocardial tissue characteristics, particularly the extent and distribution patterns of LGE involvement. These findings have significant reference value for early identification of CS and differential diagnosis from other cardiomyopathies.

Objective:To explore the feasibility and effectiveness of full free-breathing cardiac magnetic resonance (CMR) in clinical practice.Methods:The study prospectively included patients who underwent full free-breathing CMR and traditional breath-holding cine imaging between June 1 and June 30, 2024. An analysis and comparison were conducted on the image acquisition time, image quality, and left ventricular function parameters under two scanning methods, including left ventricular ejection fraction (LVEF), left ventricular cardiac output (LVCO),left ventricular end diastolic volume (LVEDV), left ventricular end diastolic volume index (LVEDVI), left ventricular end systolic volume (LVESV), left ventricular end systolic volume index (LVESVI), left ventricular stroke volume (LVSV), and left ventricular mass (LVM). In addition, the study conducted both quantitative and qualitative analyses of other sequences in full free-breathing CMR, including T 1 mapping, T 2 mapping, flow imaging, and late gadolinium enhancement (LGE). Group comparisons were performed using the Wilcoxon signed-rank test or paired t-test. Consistency assessments included Bland-Altman analysis, intraclass correlation coefficient ( ICC), and linear regression analysis. Results:Totally, 150 patients were recruited into the study. The average acquisition time of full free-breathing CMR was (22.1±3.1) min, with an average short axis cine sequence examination time of (2.7±0.4) min; The average acquisition time of short axis images in a breath-holding state was (4.9±1.4) min, which was significantly longer than the cine scan in the free-breathing state ( P0.001). The cine and LGE images quality scores obtained from full free-breathing CMR were 4 (4, 4) points and 5 (4, 5) points, respectively, while the cine image quality score obtained in a breath-holding state was 5 (4, 5) points. Compared with traditional breath-hold CMR, free-breathing CMR measurements showed slightly higher LVESV, and LVESVI, while LVEDV, LVEDVI, LVSV, LVCO, LVEF, and LVM were slightly lower, except for LVSV and LVCO, which showed no statistically significant difference, the differences in other cardiac function parameters were statistically significant ( P0.05). However, the two methods demonstrated good consistency( ICC0.947) and correlation (0.808 r0.993, P0.001). The Bland-Altman analysis showed that the bias for all cardiac function parameters was within 8.0%. The Native T 1 and T 2 values for free-breathing CMR were (1 277.5±57.0) ms and 40.1 (38.5, 41.4) ms, respectively, and the results of flow imaging and echocardiography were basically consistent. Conclusions:Free-breathing CMR is feasible and effective in clinical practice, showing a high level of consistency with left ventricular functional parameters obtained from traditional breath-hold scanning. It significantly shortens examination time and holds great clinical value for the promotion and widespread use of CMR.

Frequent occurrence of disaster rescue and public health emergencies has increased demand for rapidly and efficiently emergent medical rescue.This study modified a closed van which equipped a rapid testing module for physiological indicators,clinical blood transfusion module,detection and sampling module of etiology,and module for health and epidemic prevention.This research designed one kind of emergent vehicle for rapidly comprehensive detection,which integrated test vehicle,blood transfusion vehicle,biosafety testing vehicle,and vehicle for health and epidemic prevention in one vehicle.This vehicle can meet various demands of emergently medical rescue and other tasks in clinical test,which can improve the response capability and emergency handling capability for disasters and public health emergencies,at the same time,it also can save manpower.

OBJECTIVE To explore the construction path and effectiveness of dynamic zoning management model during dengue fever pandemic,and to provide evidence for optimizing hospital-acquired infection control strategies.METHODS Retrospective analysis method was conducted,the practical data of dengue fever epidemic prevention and control in a tertiary general hospital in 2024 as the sample,to evaluate the application effect of the"zoned treatment-dynamic allocation-environmental coordination"trinity prevention and control model.Based on the optimized infection prevention and control strategies implemented during the epidemic,such as the"core ward-specialist collaboration"dynamic zoning,flexible ward expansion,hierarchical disinfection,real-time dynamic re-source allocation mechanism,and precise environmental intervention,a comprehensive evaluation of prevention and control efficiency was conducted across key dimensions including infection control,resource utilization,pre-vention and control costs and patient outcomes.RESULTS Through the construction of flexible wards,the number of expanded isolation beds accounted for 44.13％(331/750)of the total beds,including 144 beds(19.20％)in core wards and 187 beds(24.93％)in specialist collaborative wards.The expansion of specialist collaborative wards increased the isolation admission capacity by 129.86％.The two types of wards admitted 57.27％of single-disease dengue patients and 42.73％of isolated patients with combined diagnosis and treatment needs from inter-nal medicine,surgery,obstetrics,gynecology,and pediatrics.The minimum ratio of flexible buffer isolation beds was 6.34％(21/331),with a maximum daily treatment capacity of 310 patients.Data showed:hospital infec-tion incidence rate was 0,peak adult mosquito density was 0.13 mosquitoes/trap·night,prevention and control cost was 95.22 yuan per case,and patient satisfaction increased by 1.98％(95.09 vs.93.24,P=0.014).CONCLUSIONS The"dynamic zoning"model achieves rapid spatial elastic reconstruction of inpatient wards for"peace-epidemic conversion"through the coordination of three links.Based on effectively blocking in-hospital transmission,it ensures the needs of multi-specialty treatment,enabling the hospital to strike a balance between the bottom line of prevention and control safety and the fulfillment of diversified medical service requirements dur-ing the epidemic outbreak period.It can provide standardized prevention and control solutions for medical institu-tions to respond to public health emergencies of vector-borne infectious diseases,and achieve the goal of zero cross infection of hospital-acquired Dengue.

Objective:To investigate the feasibility and clinical effects of ultra early enteral nutrition (≤24 h) in critically ill children supported by extracorporeal membrane oxygenation (ECMO).Methods:A retrospective cohort study was conducted. Clinical data of 43 critically ill children who received ECMO support in the pediatric intensive care unit (PICU) of Shanghai Children′s Hospital from January 2016 to December 2023 were collected, including general information, nutritional support modalities, and enteral nutrition tolerance. Based on the timing of enteral nutrition initiation, patients were divided into the within 24 h enteral nutrition group and the after 24 h enteral nutrition group. Nutritive indicators, nutritional intake, duration of ECMO support, duration of mechanical ventilation duration, and mortality rates were compared between the 2 groups using the two independent sample t test, Mann-Whitney U test, χ2 test and Fisher′s exact test. Results:Among the 43 children, 25 were male and 18 were female, with an age of 47 (18, 97) months. There were no statistically significant differences between the within 24 h enteral nutrition group (21 cases) and the after 24 h enteral nutrition group (22 cases) in terms of age, body mass index Z score, total protein, albumin, hemoglobin levels before ECMO support, duration of ECMO support, duration of mechanical ventilation, length of PICU stay, number of enteral nutrition intolerance events, number of enteral nutrition interruption, or mortality rate (all P>0.05). The protein intake adequacy rate during ECMO support was higher in the within 24 h enteral nutrition group than in the after 24 h enteral nutrition group (0 (0, 21%) vs. 0 (0, 0), U=175.00, P<0.05). Conclusions:Ultra early enteral nutrition is safe for children supported by ECMO. Initiating enteral nutrition within 24 h can increase the proportion of days with adequate protein intake in ECMO children without increasing the occurance of enteral nutrition intolerance or interruptions.

Aim To explore the potential mechanism of metformin on ATP-binding cassette transport A1(ABCA1)expression.Methods J774A.1 macrophages were treated with metformin and cycloheximide,and ABCA1 expression was determined by Western blot.His-tagged ABCA1 and HA-tagged Ub plasmids were co-transferred into HEK293 cells and stimulated with metformin.Co-immunoprecipitation(Co-IP)was used to test the binding ability of ABCA1 and ubiquitin.Candidate E3 ubiquitin-protein ligases(CE3)of ABCA1 were identified through Co-IP-based pro-teomics.The MIB1 plasmid was constructed and transferred into HEK293 cells,and Western blot was used to determine the effect of metformin and MIB1 on ABCA1 expression.Results Metformin increased the expression of ABCA1 in J774A.1 cells(P<0.01),and inhibited ABCA1 degradation(P<0.05).Metformin disrupted the binding of ABCA1 to ubiquitin(P<0.05).The proteins regulated by metformin in ABCA1 expression were primarily enriched in pathways re-lated to cell development,inflammation and immune defense.Metformin may upregulate ABCA1 protein expression via MIB1(P<0.05).Conclusion Metformin inhibits the degradation of ABCA1 by blocking the ubiquitin-proteasome system(UPS),and MIB1 might act as a candidate E3 ubiquitin-protein ligase(CE3)for ABCA1.