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

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.

Assessment is an indispensable and critical activity in the educational process. In the recent decades, with the birth and development of competence-based educational paradigm, the rationale behind assessment is shifting from "assessment of learning" to "assessment for learning". Workplace-based assessment (WPBA), which aims to improve the quality of both learning and teaching through assessment in real workplace circumstances, is a set of assessment tools that conforms to the new concepts of medical education. In this article, with the purpose to promote the application of WPBA and thus enhance the quality of dental education in our country, a thorough discussion is performed regarding the core principles, tools, advantages of WPBA as well as attentions that should be noted when applying WPBA. It is recommended to establish a longitudinal assessment system which employs various WPBA tools and assesses the development of students' competencies through the whole educational process. Such a dynamic assessment system may be helpful to provide all-rounded and competent dental talents who can eventually benefit the society.

Aim To investigate the behavioral changes of the pain related neuromodulation and neurotransmission in peripheral and central nervous systems in rats with trigeminal neuralgia (TN)and provide a disease relevant animal model for mecha-nism study of TN.Methods The male SD rats were randomly divided into sham operation group and TN surgical group.The latter group was further divided into model group and gabapentin group (100 mg · kg-1 ). TN was induced by intravenous erythrosine B injection and laser irradiation.The pain behavior of rats was evaluated using mechanical pain threshold measured with Von Frey hairs.Fluorescence quantitative PCR technique was deployed to study the change of Tac1 mRNA expressions in trigeminal ganglia.Utilizing microdialysis technique followed by high performance liquid chromatography fluorescence detection (HPLC-FLD),the extracellular striatum fluid was collected and glutamate(Glu)concentration was determined.Results In the model group,the average mechanical pain threshold in facial ar-ea innervated by the trigeminal nerve remained below 4g after 7 days post surgery.The mechanical threshold of the model group (1.63 ±1.27)g was significantly lower (P<0.01)than the control group (24.17 ±4.49)g on day10 post surgery.In gen-eral,the mechanical withdraw threshold was decreased from the preoperative value of 26g to the postoperative value of (1.60 ± 1.74)g (P<0.01),and maintained stable at (0.71 ±1.24) g during the whole dynamic monitoring period from day7 to day60.The successful rate of this model was 63%.After sur-gery,Tac1 mRNA expression in trigeminal ganglia and extracel-lular Glu levels in striatum were significantly up-regulated (P<0.05 ) in the model group. Animals receiving Gabapentin showed significant improvement in pain symptoms,as well as re-ductions of Tac1 mRNA expression in trigeminal ganglia and ex-tracellular Glu concentration in striatum (P<0.05 ).Conclu-sions The above described photochemically induced TN rat model can partially mimic the clinical TN symptoms and its pathophysiology.Considering its overall high stability,it is very likely that this model could be used in preclinical mechanism study or drug screening of TN.