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

The αPD-L1 antibody-based immune checkpoint blockade therapy is still limited by the poor clinical response rate as it is mainly utilized to block surface PD-L1 on tumor cells while ignoring abundant PD-L1 exosomes secreted in the environment, causing tumor immune evasion. Here, we proposed an exosome biogenesis inhibition strategy to suppress tumor exosomes secretion from the source, reducing the inhibitory effect on T cells and enhancing chemo-immunotherapy efficacy. We developed sulfafurazole homodimers (SAS) with disulfide linkages, effectively releasing the drug in response to glutathione (GSH) and inhibiting 4T1 tumor-derived exosomes secretion. Subsequently, gemcitabine (Gem) was encapsulated to induce immunogenic cell death (ICD). Consequently, Gem@SAS inhibited the secretion of tumor exosomes by more than 70%, increased proliferation and granzyme B secretion ability of T cells by more than 2 times, and showed superior efficacy in breast cancer treatment as well as lung metastasis of breast cancer.

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.

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.

The study was conducted among 120 general practitioners (GPs) in Shanghai Fengxian District from August 2022 to March 2024, the participants were randomly divided into two age-matched groups with 60 GPs in each group. The intervention group completed a 3-month SPOC (Small Private Online Course)program, including two weeks of narrative medicine theory (concepts, questioning skills, parallel medical record writing, and professionalism) followed by monthly writing practices (three parallel records per month) and group discussions. Both groups performed routine clinical tasks, while the control group received no narrative medicine training. Baseline data were collected, Jefferson Empathy Scale scores, and Doctor-Patient Communication Skills Evaluation Scale scores were evaluated pre- and post-intervention. There were no significant differences in empathy ( P>0.05) or communication skills ( P>0.05) between two groups before the intervention. Post-intervention, both groups showed improved empathy (both P<0.05) and communication skills (both P<0.05) after intervention, while the intervention group were outperforming the control group in both measures ( P<0.05). These findings suggest that SPOC-based narrative competence training effectively enhances the empathy and doctor-patient communication abilities of general practitioners.

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.

Objective:To analyze the occurrence of metabolic dysfunction-associated fatty liver disease (MAFLD) and related inflammatory indicators in obstructive sleep apnea hypopnea syndrome (OSAHS) and explore the risk factors of MAFLD.Methods:A cross-sectional study. From January 2022 to October 2024,172 patients with sleep disorders were enrolled in the First Affiliated Hospital of Soochow University,including 38 patients with non-OSAHS,53 patients with mild OSAHS,37 patients with moderate OSAHS,and 44 patients with severe OSAHS. The occurrence of MAFLD was comprehensively judged from three aspects: metabolic dysfunction-associated fatty liver (MAFL),elevated liver enzymes,and liver fibrosis. The situation of MAFLD and the level of related inflammatory markers were compared among the four groups. Binary logistic regression was used to analyze the risk factors for MAFLD in OSAHS.Results:There were significant differences in the prevalence of MAFL,the percentage of elevated liver enzymes,and interleukin-6 and tumor necrosis factor-alpha levels among the four groups ( P<0.05). The differences of fibrosis-4 index and C-reactive protein among the four groups were not statistically significant ( P>0.05). Binary logistic regression showed that BMI,triglycerides,longest time of sleep apnea and tumor necrosis factor-alpha were the risk factors for MAFL ( P<0.05). BMI,glucose,and apnea-hypopnea index were the risk factors for elevated liver enzymes ( P<0.05). Conclusions:OSAHS is strongly associated with MAFLD,and the involvement of OSAHS in the occurrence and development of MAFLD may be related to obesity,lipid metabolism disorders,insulin resistance,inflammatory responses,and intermittent hypoxia.

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.

Hemoglobin, the principal protein in red blood cells, is crucial for oxygen transport in the bloodstream. The quantification of hemoglobin concentration is indispensable in medical diagnostics and health management, which encompass the diagnosis of anemia and the screening of various blood disorders. Immunological methods, based on antigen-antibody interactions, are distinguished by their high sensitivity and accuracy. Consequently, it is necessary to develop hemoglobin-specific antibodies characterized by high specificity and affinity to enhance detection accuracy. In this study, we immunized a Bactrian camel (Camelus bactrianus) with human hemoglobin and subsequently constructed a nanobody library. Utilizing a solid-phase screening method, we selected nanobodies and evaluated the binding activity of the screened nanobodies to hemoglobin. Initially, human hemoglobin was used to immunize a Bactrian camel. Following four immunization sessions, blood was withdrawn from the jugular vein, and a nanobody library with a capacity of 2.85×10⁸ colony forming units (CFU) was generated. Subsequently, ten hemoglobin-specific nanobody sequences were identified through three rounds of adsorption-elution-enrichment assays, and these nanobodies were subjected to eukaryotic expression. Finally, enzyme-linked immunosorbent assay and biolayer interferometry were employed to evaluate the stability, binding activity, and specificity of these nanobodies. The results demonstrated that the nanobodies maintained robust binding activity within the temperature range of 20-40 ℃ and exhibited the highest binding activity at pH 7.0. Furthermore, the nanobodies were capable of tolerating a 10% methanol solution. Notably, among the nanobodies tested, VHH-12 displayed the highest binding activity to hemoglobin, with a half maximal effective concentration (EC₅₀) of 10.63 nmol/L and a equilibrium dissociation constant (K_D) of 2.94×10^-7 mol/L. VHH-12 exhibited no cross-reactivity with a panel of eight proteins, such as ovalbumin and bovine serum albumin, while demonstrating partial cross-reactivity with hemoglobin derived from porcine, goat, rabbit, and bovine sources. In this study, a hemoglobin-specific high-affinity nanobody was successfully isolated, demonstrating potential applications in disease diagnosis and health monitoring.
Animals ; Camelus/immunology* ; Single-Domain Antibodies/immunology* ; Hemoglobins/immunology* ; Humans ; Peptide Library