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

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.

The rapid development of artificial intelligence (AI), especially generative AI (GenAI), has already brought, and will continue to bring, revolutionary changes to our daily production and life, as well as create new opportunities and challenges for diagnostic and therapeutic practices in the medical field. Haihe Hospital of Tianjin University collaborates with the National Supercomputer Center in Tianjin, Tianjin University, and other institutions to carry out research in areas such as smart healthcare, smart services, and smart management. We have conducted research and development of a full-process disease diagnosis and treatment assistance system based on GenAI in the field of smart healthcare. The development of this project is of great significance. The first goal is to upgrade and transform the hospital's information center, organically integrate it with existing information systems, and provide the necessary computing power storage support for intelligent services within the hospital. We have implemented the localized deployment of three models: Tianhe "Tianyuan", WiNGPT, and DeepSeek. The second is to create a digital avatar of the chief physician/chief physician's voice and image by integrating multimodal intelligent interaction technology. With generative intelligence as the core, this solution provides patients with a visual medical interaction solution. The third is to achieve deep adaptation between generative intelligence and the entire process of patient medical treatment. In this project, we have developed assistant tools such as intelligent inquiry, intelligent diagnosis and recognition, intelligent treatment plan generation, and intelligent assisted medical record generation to improve the safety, quality, and efficiency of the diagnosis and treatment process. This study introduces the content of a full-process disease diagnosis and treatment assistance system, aiming to provide references and insights for the digital transformation of the healthcare industry.
Artificial Intelligence ; Humans ; Delivery of Health Care ; Generative Artificial Intelligence

Objective To explore the dynamic changes and mechanisms of neurological and cognitive functions in mice with traumatic brain injury (TBI). Methods Totally 60 12⁃month⁃old Balb/ c mice were divided into control group (10 in group) and TBI group (50 in group). TBT model mice were divided into 5 subgroups according to the time of model construction, including model 1 day, model 1 day, model 3 day, model 7 day, model 14 days and model 28 days group with 10 in each group. At the 29th day of the experiment, neurological scores and step down tests were carried out. After the test, the mice were sacrificed for brains which were detected by immunohistochemistry staining, inflammatory cytokine tests and Western blotting. Results Compared with the control group, the neurological scores of mice in TBI group increased, and then decreased after the 7th day when the scores reached the peak. However, the latency of step down errors was lower than control group, and the number of step down errors was higher than control group which had no changes. Compared with the control group, the expression of lonized calcium⁃binding adapter molecule 1(IBA1), chemokine C⁃X3⁃C⁃motif ligand1 (CX3CL1), C⁃X3⁃C chemokine receptor 1(CX3CR1), NOD⁃like receptor thermal protein domain associated protein 3 (NLRP3), and phosphorylation nuclear factor(p⁃NF)⁃κB in TBI group increased and reached to the peak at the 7th day, and then started to decrease. At the same time, the levels of inflammatory cytokines interleukin⁃6(IL⁃6) and tumor necrosis factor⁃α(TNF⁃α) first increased to the peak, and then began to decrease. However, compared with the control group, the expression of amyloid β(Aβ) protein and p⁃Tau protein in the model group continued to increase at all time. Conclusion The TBI model caused continuous activation of microglia along with inflammatory response, which first increased and then decreased, resultsing in neurological scores changes. In addition, the inflammatory response may act as a promoter of Aβ protein deposition and Tau protein phosphorylation, leading to cognitive impairment in mice.

Epigenomic imbalance drives abnormal transcriptional processes,promoting the onset and progression of cancer.Although defective gene regulation generally affects carcinogenesis and tumor suppression networks,tumor immunogenicity and immune cells involved in antitumor responses may also be affected by epigenomic changes,which may have significant implications for the development and application of epigenetic therapy,cancer immunotherapy,and their combinations.Herein,we focus on the impact of epigenetic regulation on tumor immune cell function and the role of key abnormal epigenetic processes,DNA methylation,histone post-translational modification,and chromatin structure in tumor immunogenicity,and introduce these epigenetic research methods.We emphasize the value of small-molecule inhibitors of epigenetic modulators in enhancing antitumor immune responses and discuss the challenges of developing treatment plans that combine epigenetic therapy and immuno-therapy through the complex interaction between cancer epigenetics and cancer immunology.

Patients with severe trauma require an extremely timely treatment and transfusion plays an irreplaceable role in the emergency treatment of such patients. An increasing number of evidence-based medicinal evidences and clinical practices suggest that patients with severe traumatic bleeding benefit from early transfusion of low-titer group O whole blood or hemostatic resuscitation with red blood cells, plasma and platelet of a balanced ratio. However, the current domestic mode of blood supply cannot fully meet the requirements of timely and effective blood transfusion for emergency treatment of patients with severe trauma in clinical practice. In order to solve the key problems in blood supply and blood transfusion strategies for emergency treatment of severe trauma, Branch of Clinical Transfusion Medicine of Chinese Medical Association, Group for Trauma Emergency Care and Multiple Injuries of Trauma Branch of Chinese Medical Association, Young Scholar Group of Disaster Medicine Branch of Chinese Medical Association organized domestic experts of blood transfusion medicine and trauma treatment to jointly formulate Chinese expert consensus on blood support mode and blood transfusion strategies for emergency treatment of severe trauma patients ( version 2024). Based on the evidence-based medical evidence and Delphi method of expert consultation and voting, 10 recommendations were put forward from two aspects of blood support mode and transfusion strategies, aiming to provide a reference for transfusion resuscitation in the emergency treatment of severe trauma and further improve the success rate of treatment of patients with severe trauma.

Objective:To explore the risk factors of recurrence after resection of thigh soft tissue malignant tumors and the evaluation of the postoperative lower limb function.Methods:A total of 211 patients who underwent thigh soft tissue malignant tumor resection in the Department of Orthopaedics of the second affiliated Hospital of Medical College of Zhejiang University from May 2011 to May 2021 were retrospectively analyzed, including 117 males and 94 females, aged 53 (43, 65) years. There were 59 cases of atypical/well-differentiated liposarcoma, 30 cases of other types of liposarcoma, 33 cases of malignant fibrous histiocytoma, 19 cases of fibrosarcoma, 12 cases of rhabdomyosarcoma, 12 cases of leiomyosarcoma, 9 cases of synovial sarcoma, and 37 cases of others. The tumor involvement of muscle, bone, blood vessel, nerve tissue and intermuscular compartment, postoperative Musculoskeletal Tumor Society (MSTS) functional score and recurrence were recorded. The relationship between anatomical structure and postoperative recurrence was analyzed by Cox logistic regression to determine risk factors; the cumulative recurrence rate of different compartment groups (medial compartment, anterior compartment, and posterior compartment) were compared; The Box plot was used to compare the postoperative function of patients with resection of different anatomical structures (e.g., vastus lateralis, biceps femoris, femur, etc.).Results:A total of 34 out of 211 patients relapsed, with a recurrence rate of 16.1%. The recurrence time ranged from 2.6 months to 91.6 months after operation, with a median recurrence time of 37.0 (18.2, 52.8) months. Three independent risk factors were found to be associated with recurrence, namely: pathological grade [ HR=3.86, 95% CI(1.75, 8.51)], involvement of vastus intermedius [ HR=3.05, 95% CI(1.53, 6.06)], and involvement of vastus medialis [ HR=3.17, 95% CI(1.56, 6.41)]. The recurrence rate of patients with anterior chamber tumor resection was 35.3%, which was higher than that of patients without tumor resection (16.2%), and the difference was statistically significant ( P=0.020). There was no significant difference in recurrence rate between patients with medial chamber tumor resection and patients without tumor resection ( P>0.05). The recurrence rate of patients with posterior compartment tumor resection was 12.3%, which was lower than that of unresectable patients (37.6%), and the difference was statistically significant ( P=0.002).The postoperative MSTS score of 167 patients averaged 26±3.2 points (9-30 points). After intraoperative resection of part of the femur, vastus intermedius, vastus medialis, and rectus femoris, the patient's function was relatively poor [corresponding median MSTS score: 25 (23, 28), 26 (24 28), 26 (24,28), 26(24, 27)]. Conclusion:The risk factors for local recurrence after resection of thigh soft tissue malignant tumors include: pathological grade of the tumor, and whether the vastus intermedius or vastus medialis is involved. Anterior compartment tumors have a higher recurrence rate after surgery. If the tumor involves the above-mentioned anatomical structures, more attention should be paid to the risk of local recurrence after surgery.

Objective:To investigate the relationship between long non-coding RNA (lncRNA) DHRS4-AS1 and disease-free survival in osteosarcoma patients and the mechanisms of its effect on proliferation and migration of osteosarcoma cells in vitro.Methods:The data of DHRS4-AS1 transcriptome levels and survival status of osteosarcoma patients in GEPIA database were collected since the database was established, and the patients were divided into high DHRS4-AS1 expression group and low DHRS4-AS1 expression group based on the median DHRS4-AS1 transcriptome level, with 59 cases in each group, and the Kaplan-Meier method was used to analyze the disease-free survival of the two groups. Real-time fluorescence quantitative polymerase chain reaction (qRT-PCR) was used to detect the expression of DHRS4-AS1 in osteosarcoma cell lines MG-63, HOS, 143B, U-2OS, Saos2 and normal osteoblast cell line hFOB1.19, and the osteosarcoma cell line with the lowest DHRS4-AS1 expression level was selected for subsequent experiments. The plasmid carrying DHRS4-AS1 sequence and the plasmid carrying negative control sequence were transfected into the selected osteosarcoma cells as DHRS4-AS1 group and control group. CCK-8 method was used to detect the proliferation of each group of cells, and the absorbance value was used as the cell proliferation ability; cell scratch assay was used to detect the migration of each group of cells. The bioinformatics website starBase V2.0 was used to predict the target genes of DHRS4-AS1, and the dual luciferase reporter gene assay was used to verify the targeting relationship between DHRS4-AS1 and the target genes. The expression levels of target genes and downstream genes of osteosarcoma cells in control group and DHRS4-AS1 group were detected by qRT-PCR and Western blotting.Results:Survival analysis showed that the disease-free survival of osteosarcoma patients in the high DHRS4-AS1 expression group in GEPIA database was superior to that of the low DHRS4-AS1 expression group ( P < 0.001). Compared with normal osteoblastic hFOB1.19 cells, the expression level of DHRS4-AS1 was low in all osteosarcoma cells (all P < 0.01), with the lowest expression level of DHRS4-AS1 in U-2OS cells ( P < 0.001). Cell proliferation ability was reduced in U-2OS cells of the DHRS4-AS1 group after 1, 2, 3 and 4 d of culture compared with the control group (all P < 0.05). The migration rate of U-2OS cells in the DHRS4-AS1 group was lower than that in the control group [(31±6)% vs. (63±4)%, t = 4.38, P = 0.005]. starBase V2.0 website predicted that DHRS4-AS1 complementarily bound to miRNA-411-3p (miR-411-3p); dual luciferase reporter gene assay showed that miR-411-3p overexpression reduced the luciferase activity of the wild-type DHRS4-AS1 reporter gene ( P < 0.001), but had no effect on the luciferase activity of the mutant DHRS4-AS1 reporter gene ( P > 0.05). qRT-PCR showed that the relative expression of miR-411-3p in U-2OS cells of the DHRS4-AS1 group was low (0.22±0.06 vs. 1.06±0.23, t = 3.55, P = 0.012) and the relative expression of metastasis suppressor MTSS1 mRNA was high (5.58±1.03 vs. 1.06±0.22, t = 4.28, P = 0.005) compared with the control group; Western blotting showed that MTSS1 expression was elevated, and the expression levels of cell proliferation phenotype proteins CDK3 and cyclin C and cell migration phenotype proteins ZEB2 and KLF8 were low. Conclusions:Osteosarcoma patients with high expression of lncRNA DHRS4-AS1 have better disease-free survival, and its expression is low in osteosarcoma cell lines. DHRS4-AS1 may promote MTSS1 gene expression and inhibit cell proliferation and migration by targeting and down-regulating miR-411-3p expression in osteosarcoma cells.

The toxic pathogen theory, an important part of the theories of traditional Chinese medicine(TCM), began in the Qin and Han dynasties, formed in the Jin, Sui, Tang, and Song dynasties, developed rapidly in the Ming and Qing dynasties, and conti-nued to develop in contemporary times based on the achievements of its predecessors. The continuous exploration, practice, and inheri-tance of many medical practitioners over the generations have facilitated the enrichment of its connotation. The toxic pathogen is violent, fierce, dangerous, prolonged, rapid in transmission, easy to hurt the internal organs, hidden, and latent, with many changes, and it is closely related to the development of tumor diseases. TCM has a history of thousands of years in the prevention and treatment of tumor diseases. It is gradually realized that the etiology of tumor is mainly attributed to the deficiency of healthy Qi and excess of to-xic pathogen, and the struggle between healthy Qi and toxic pathogen runs through the whole course of tumor, with the deficiency of healthy Qi as the prerequisite and the invasion of toxic pathogen as the root of the occurrence. The toxic pathogen has a strong carcinogenic effect and is involved in the whole process of tumor development, which is closely related to the malignant behaviors of tumors, including proliferation, invasion, and metastasis. This study discussed the historical origin and modern interpretation of the toxic pathogen theory in the prevention and treatment of tumors, with aims of sorting out the theoretical system based on the toxic pathogen theory in the treatment of tumor diseases, and illustrating the importance of the toxic pathogen theory in the treatment of tumors in the context of modern research on pharmacological mechanisms and the development and marketing of relevant anti-tumor Chinese medicinal preparations.
Medicine, Chinese Traditional ; Cell Movement ; China

Liraglutide is an analog of glucagon⁃like peptide⁃1 and plays an important role in the treatment of diabetes. But the specific mechanism of liraglutide in improving the function of pancreatic β cells is still unclear. Therefore, high glucose (33 mmol/ L) was used to induce islet MIN6 cells for 48 hours to establish a high glucose injury model in this study. The CCK⁃8 assay was used to detect cell viability, and the results showed that the viability of MIN6 cells in the high glucose group decreased (P<0. 05) compared with the control group, and the cell viability increased after liraglutide treatment (P<0. 05). Using the mouse insulin detection kit and ATP content detection kit, we found that both the insulin re⁃ lease (P<0. 01) and ATP content decreased (P<0. 001) in the high glucose group compared with the control group, and after liraglutide treatment both insulin release (P < 0. 05) and ATP content (P < 0. 001) increased. We used the mitochondrial membrane channel pore (MPTP) fluorescence detection kit in MIN6 cells and found that the green fluorescence intensity of the high glucose group was significant⁃ ly decreased (P<0. 001) compared with the control group, and after liraglutide treatment the green fluo⁃ rescence intensity was significantly increased (P<0. 001). The DCFH⁃DA probe combined with flow cy⁃ tometry was used to detect the level of reactive oxygen species (ROS). We found that compared with the control group, the ROS level in the high glucose group was significantly increased (P<0. 001), and de⁃ creased by liraglutide treatment (P<0. 01). Intracellular malondialdehyde (MDA) contents, superoxide dismutase (SOD) and catalase (CAT), and lactate dehydrogenase (LDH) activities in the cell superna⁃ tant were measured, and the levels of MDA and LDH were significantly increased (P<0. 05), and the levels of SOD and CAT were significantly decreased (P<0. 01) in the high glucose group compared with the control group. After liraglutide treatment, the levels of MDA and LDH were decreased (P<0. 05), and the levels of SOD and CAT were increased (P<0. 05). The results of Western blotting showed that the expression of UCP2 was upregulated in the high glucose group (P<0. 01) compared with the control group, and after liraglutide treatment the expression of UCP2 decreased (P<0. 05). The results indica⁃ ted that liraglutide has significant effects in high⁃glucose induced mitochondrial damage, oxidative stress and insulin secretion in MIN6 cells, which will provide a theoretical basis for clinical utilization of liraglu⁃ tide.