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.

Objective To investigate the stroke occurrence of chronic kidney disease (CKD) and its related factors, especially the carotid atherosclerosis. Methods The data of stroke occurrence in 700 CKD patients hospitalized in Renji Hospital during 2007 were analyzed retrospectively. The incidences of stroke were compared among CKD [Ⅰ-Ⅱ, CKD Ⅲ-Ⅴ non-dialysis patients and dialysis patients. Carotid atherosclerosis of 409 CKD patients was examined by color Doppler ultrasound. The related factors were selected by Spearmnan correlation analysis and Logistic regression analysis. Results Of 700 CKD patients, 67 cases (9.57%) experienced at least one episode of stroke, which was much higher than that of general population. The related factors of stroke in CKD included GFR, age, SBP, CRP, Lpa, serum glucose, pre-albumin, HDL and carotid atherosclerosis. Logistic regression revealed that SBP (β=1.021, P=0.042), CRP (β=1.008, P=0.024) and carotid atherosclerosis (β =3.456, P=0.025) were risk factors of stroke in CKD. Incidence of carotid atherosclerosis was high (50.37%) in CKD patients, besides it was significantly higher in CKD patients with stroke history as compared to those without stroke history (80.0% vs 47.4%, P<0.01). Conclusions The incidence of stroke is quite high in CKD patients, which is closely associated with hypertension, inflammation and glyeolipid metabolism disorder. Carotid atherosclerosis is common in CKD patients with stroke, which may be helpful in screening cerebrovascular diseases in CKD patients.

OBJECTIVETo evaluate the diagnostic value of dobutamine stress magnetic resonance imaging (MRI) for myocardial viability.

METHODSTen male miniswines underwent left ventriculography and coronary angiography, followed by stenosis of the left circumflex coronary artery (LCX) using ameroid constrictor. More than one month later, left ventriculography and coronary angiography were performed again, followed by cine-MRI at rest and during stress with incremental dose of dobutamine 5 - 20 micro g.kg(-1).min(-1). Traditional and/or breath-hold cine-MRI were used to evaluate regional left ventricular wall motion, corresponding to basal, midventricular and apical short-axis tomograms. Regional wall motion score index (WMSI) was calculated. The miniswines were finally sacrificed for pathological examination. Triphenyl tetrazolium chloride (TTC) delineated myocardial infarction. Microscopy was used to identify myocardial cellular changes.

RESULTSOne pig died, one pig suffered from aneurysm and another showed no negative findings. The other seven pigs were found with hypokinetic (n = 4) or akinetic (n = 3) myocardial regions related to stenosed LCX. Their mean WMSI at rest for the lateral and posteroinferior walls (ischemic regions) of the left ventricle was 2.27 +/- 0.32, as compared with 1.00 +/- 0.00 (P < 0.01) for the corresponding nonischemic anteroseptal regions. Further, the mean WMSI for the ischemic regions was 2.27 +/- 0.32 at rest compared with 1.40 +/- 0.39 (P < 0.01) at the dose of dobutamine 5 micro g.kg(-1).min(-1). However, the mean WMSI at the doses of dobutamine 10 and 20 micro g.kg(-1). min(-1) were 1.70 +/- 0.76 and 1.75 +/- 0.83, respectively, with no significant difference as compared with the mean WSCI at rest (P > 0.05). The pathologic examination showed viable myocardium at the ischemic regions.

CONCLUSIONLow-dose dobutamine (5 micro g.kg(-1).min(-1)) recovers hypokinetic or akinetic myocardial regions, and dobutamine stress MRI can be used to detect myocardial viability.

Animals ; Dobutamine ; Magnetic Resonance Imaging, Cine ; methods ; Male ; Swine ; Swine, Miniature ; Ventricular Function, Left