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

Objectives:To investigate the clinical value of cardiac magnetic resonance imaging(CMR)feature-tracking strain analysis in risk stratification of diabetic heart failure with preserved ejection fraction(HFpEF).Methods:In this retrospective study,a total of 215 patients with diabetic HFpEF who underwent CMR at Chinese Academy of Medical Sciences Fuwai Hospital from January 2012 to December 2018 were included.Myocardial strain parameters were calculated using CMR feature-tracking technology.Patients were followed up by medical records or telephone calls.Composite endpoint event,all-cause death or heart failure hospitalization during follow-up were recorded.Patients were divided into event group and event-free group.Univariable and multivariable Cox proportional hazard regression analyses were performed to determine the risk factors for the outcomes in diabetic HFpEF.The effects of hypertension and obesity on the prognosis of diabetic HFpEF patients and whether they affect the prognostic value of CMR feature-tracking strain analysis were also analyzed.Results:During a follow-up of(7.1±1.8)years,93(43.3%)patients had endpoint events(event group),including 28 all-cause deaths and 65 heart failure hospitalization.Compared with the event-free group(n=122),patients in the event group had significantly lower left ventricular ejection fraction,higher prevalence and extent of late gadolinium enhancement,and significantly reduced global longitudinal strain(GLS),global circumferential strain,global radial strain,and global systolic longitudinal strain rate(all P<0.05).The absolute GLS value was significantly lower in event group than in event-free group,regardless of the presence of hypertension and obesity.Multivariate Cox regression analysis showed that estimated glomerular filtration rate(HR=0.983,95%CI:0.972-0.993,P=0.001),left atrial volume index(HR=1.015,95%CI:1.005-1.026,P=0.004),and GLS(HR=1.142,95%CI:1.060-1.231,P<0.001)were independent risk factors for adverse cardiovascular events in diabetic HFpEF patients.However,adjusted N-terminal pro-brain natriuretic peptide was not an independent prognostic factor.The cut-offvalue of GLS to predict outcome was-14.09%from ROC curve analysis.The Kaplan-Meier curve showed that in patients with and without hypertension and obesity,patients with the GLS>-14.09%had lower event-free survival compared to patients with GLS≤-14.09%(all P<0.05),and the ability of GLS to predict adverse outcomes was not affected by hypertension and obesity.Conclusions:GLS obtained by CMR feature-tracking strain analysis is an independent predictor of adverse outcomes in diabetic HFpEF,and its ability to predict adverse outcomes is independent of hypertension and obesity.

Objectives:To investigate the clinical value of cardiac magnetic resonance imaging(CMR)feature-tracking strain analysis in risk stratification of diabetic heart failure with preserved ejection fraction(HFpEF).Methods:In this retrospective study,a total of 215 patients with diabetic HFpEF who underwent CMR at Chinese Academy of Medical Sciences Fuwai Hospital from January 2012 to December 2018 were included.Myocardial strain parameters were calculated using CMR feature-tracking technology.Patients were followed up by medical records or telephone calls.Composite endpoint event,all-cause death or heart failure hospitalization during follow-up were recorded.Patients were divided into event group and event-free group.Univariable and multivariable Cox proportional hazard regression analyses were performed to determine the risk factors for the outcomes in diabetic HFpEF.The effects of hypertension and obesity on the prognosis of diabetic HFpEF patients and whether they affect the prognostic value of CMR feature-tracking strain analysis were also analyzed.Results:During a follow-up of(7.1±1.8)years,93(43.3%)patients had endpoint events(event group),including 28 all-cause deaths and 65 heart failure hospitalization.Compared with the event-free group(n=122),patients in the event group had significantly lower left ventricular ejection fraction,higher prevalence and extent of late gadolinium enhancement,and significantly reduced global longitudinal strain(GLS),global circumferential strain,global radial strain,and global systolic longitudinal strain rate(all P<0.05).The absolute GLS value was significantly lower in event group than in event-free group,regardless of the presence of hypertension and obesity.Multivariate Cox regression analysis showed that estimated glomerular filtration rate(HR=0.983,95%CI:0.972-0.993,P=0.001),left atrial volume index(HR=1.015,95%CI:1.005-1.026,P=0.004),and GLS(HR=1.142,95%CI:1.060-1.231,P<0.001)were independent risk factors for adverse cardiovascular events in diabetic HFpEF patients.However,adjusted N-terminal pro-brain natriuretic peptide was not an independent prognostic factor.The cut-offvalue of GLS to predict outcome was-14.09%from ROC curve analysis.The Kaplan-Meier curve showed that in patients with and without hypertension and obesity,patients with the GLS>-14.09%had lower event-free survival compared to patients with GLS≤-14.09%(all P<0.05),and the ability of GLS to predict adverse outcomes was not affected by hypertension and obesity.Conclusions:GLS obtained by CMR feature-tracking strain analysis is an independent predictor of adverse outcomes in diabetic HFpEF,and its ability to predict adverse outcomes is independent of hypertension and obesity.

Objectives:To evaluate the tricuspid valve(TV)geometric remodeling in patients with idiopathic pulmonary arterial hypertension(IPAH)by three-dimensional transthoracic echocardiography. Methods:Two-dimensional and three-dimensional transthoracic echocardiography were performed in 30 IPAH patients and 15 healthy controls,and the geometry parameters of TV were obtained by four-dimensional auto tricuspid valve quantitative(4D Auto-TVQ)in the right ventricular-focused apical view.Pulmonary arterial hypertension was determined by right heart catheterization within 48 hours of echocardiography. Results:The 4-chamber diameter,tricuspid annular(TA)perimeter,TA area,maximal tenting height,coaptation point height and tenting volume were larger in IPAH patients than those in healthy controls(all P＜0.05),2-chamber diameter was similar between two groups.In IPAH group,maximal tenting height and coaptation point height were moderately correlated with right ventricular end-diastolic volume(r=0.710,r=0.515,both P＜0.05),while TA perimeter,4-chamber diameter and TA area were moderately correlated with right atrial end-systolic volume(r=0.712,r=0.558,r=0.545,all P＜0.05). Conclusions:IPAH patients have larger maximal tenting height,coaptation point height and tenting volume,TA enlargement is mainly visible in 4-chamber diameter.TV tenting height is associated with right ventricular volume,but TA size is associated with right atrial volume in IPAH patients.

Objectives:To analyze the consistency of evaluating left ventricular hemodynamics (HDF) based on single plane and multi plane cine sequences of magnetic resonance mitral valve orifice.Methods:A prospective study was conducted on 48 healthy adults, and two methods were used to measure the mitral valve diameter and calculate HDF parameters. The first method was to measure the diameter of the mitral valve opening in the left ventricular three chamber cine sequence; The second method is to measure the mitral valve diameter using cine sequences of two chamber, three chamber, and four chamber hearts, and then take the average value. Paired t-tests were used to compare the differences in HDF measured by two methods, and Pearson correlation coefficient ( r), intra group correlation coefficient ( ICC), and Bland-Altman analysis were used to test the consistency and reproducibility of the two methods. Results:The root mean square (RMS) of longitudinal HDF calculated using single plane and multi plane mitral valve diameters were [(17.28±4.41)% vs (17.21±4.61)%] ( P=0.379) for the entire cardiac cycle, [(21.45±5.54)% vs (21.49±5.68)%] ( P=0.646) for systolic phase, and [(12.78±4.10)% vs (12.54±4.24)%] ( P=0.106) for diastolic phase, respectively. The difference in the calculation results of HDF parameters related to ventricular function was not statistically significant (all P>0.05), and there was good consistency ( r=0.924-0.996, ICC=0.924-0.995). The two HDF parameters related to atrial function were sensitive to the measurement method of mitral valve orifice diameter [RMS of longitudinal HDF during active atrial emptying: (3.26±1.51)% vs (3.32±1.55)%, P=0.006; longitudinal HDF pulse during active atrial emptying: (-2.60±1.28)% vs (-2.76±1.30)%, P<0.001]. Conclusions:The ventricular function related HDF parameters obtained from the analysis of mitral valve orifice diameter using single plane and multi plane methods have good consistency, and can be evaluated using relatively simple single plane methods for left ventricular HDF.

Recently, small nucleolar RNAs (snoRNAs) have transcended the genomic "noise" to emerge as pivotal molecular markers due to their essential roles in tumor progression. Substantial evidence indicates a strong association between snoRNAs and critical clinical features such as tumor pathology and drug resistance. Historically, snoRNA research has concentrated on two classical mechanisms: 2'-O-ribose methylation and pseudouridylation. This review specifically summarizes the novel regulatory mechanisms and functional patterns of snoRNAs in tumors, encompassing transcriptional, post-transcriptional, and post-translational regulation. We further discuss the synergistic effect between snoRNA host genes (SNHGs) and snoRNAs in tumor progression. More importantly, snoRNAs extensively contribute to the development of tumor cell resistance as oncogenes or tumor suppressor genes. Accordingly, we provide a comprehensive review of the clinical diagnosis and treatment associated with snoRNAs and explore their significant potential as novel drug targets.

Objective To develop and evaluate a fine-tuned large language model(LLM)for traditional Chinese medicine(TCM)prescription recommendation named TCMLLM-PR.Methods First,we constructed an instruction-tuning dataset containing 68 654 samples(ap-proximately 10 million tokens)by integrating data from eight sources,including four TCM textbooks,Pharmacopoeia of the People's Republic of China 2020(CHP),Chinese Medicine Clinical Cases(CMCC),and hospital clinical records covering lung disease,liver disease,stroke,diabetes,and splenic-stomach disease.Then,we trained TCMLLM-PR using Chat-GLM-6B with P-Tuning v2 technology.The evaluation consisted of three aspects:(i)compari-son with traditional prescription recommendation models(PTM,TCMPR,and PresRecST);(ii)comparison with TCM-specific LLMs(ShenNong,Huatuo,and HuatuoGPT)and general-domain ChatGPT;(iii)assessment of model migration capability across different disease datasets.We employed precision,recall,and F1 score as evaluation metrics.Results The experiments showed that TCMLLM-PR significantly outperformed baseline models on TCM textbooks and CHP datasets,with F1@10 improvements of 31.80%and 59.48%,respectively.In cross-dataset validation,the model performed best when migrating from TCM textbooks to liver disease dataset,achieving an F1@10 of 0.155 1.Analysis of real-world cases demonstrated that TCMLLM-PR's prescription recommendations most closely matched actual doctors'prescriptions.Conclusion This study integrated LLMs into TCM prescription recommendations,leverag-ing a tailored instruction-tuning dataset and developing TCMLLM-PR.This study will pub-licly release the best model parameters of TCMLLM-PR to promote the development of the decision-making process in TCM practices(https://github.com/2020MEAI/TCMLLM).

Recently,small nucleolar RNAs(snoRNAs)have transcended the genomic"noise"to emerge as pivotal molecular markers due to their essential roles in tumor progression.Substantial evidence indicates a strong association between snoRNAs and critical clinical features such as tumor pathology and drug resistance.Historically,snoRNA research has concentrated on two classical mechanisms:2'-O-ribose methylation and pseudouridylation.This review specifically summarizes the novel regulatory mecha-nisms and functional patterns of snoRNAs in tumors,encompassing transcriptional,post-transcriptional,and post-translational regulation.We further discuss the synergistic effect between snoRNA host genes(SNHGs)and snoRNAs in tumor progression.More importantly,snoRNAs extensively contribute to the development of tumor cell resistance as oncogenes or tumor suppressor genes.Accordingly,we provide a comprehensive review of the clinical diagnosis and treatment associated with snoRNAs and explore their significant potential as novel drug targets.

Temporomandibular joint (TMJ) diseases are common clinical conditions. The number of patients with TMJ diseases is large, and the etiology, epidemiology, disease spectrum, and treatment of the disease remain controversial and unknown. To understand and master the current situation of the occurrence, development and prevention of TMJ diseases, as well as to identify the patterns in etiology, incidence, drug sensitivity, and prognosis is crucial for alleviating patients′suffering.This will facilitate in-depth medical research, effective disease prevention measures, and the formulation of corresponding health policies. Cohort construction and research has an irreplaceable role in precise disease prevention and significant improvement in diagnosis and treatment levels. Large-scale cohort studies are needed to explore the relationship between potential risk factors and outcomes of TMJ diseases, and to observe disease prognoses through long-term follw-ups. The consensus aims to establish a standard conceptual frame work for a cohort study on patients with TMJ disease while providing ideas for cohort data standards to this condition. TMJ disease cohort data consists of both common data standards applicable to all specific disease cohorts as well as disease-specific data standards. Common data were available for each specific disease cohort. By integrating different cohort research resources, standard problems or study variables can be unified. Long-term follow-up can be performed using consistent definitions and criteria across different projects for better core data collection. It is hoped that this consensus will be facilitate the development cohort studies of TMJ diseases.

Objective:To determine the karyotype of a patient with mosaicism complex structural aberration of chromosome 18.Methods:A male patient with a 2-year history of infertility presented at the Center of Reproductive Medicine of the Third Hospital of Peking University in October 2019 was selected as the study subject. Clinical data of the patient was collected. Peripheral blood sample was taken for chromosomal karyotyping, copy number variation (CNV) analysis and fluorescence in situ hybridization (FISH) assay. Semen sample was taken for single sperm CNV analysis. Results:The patient was found to have a karyotype of mos 47, XY, del(18)(q21q23), + r(18)(q21q23)[84]/46, XY, del(18)(q21q23)[9]/48, XY, del(18)(q21q23), + r(18)(q21q23)×2[6]/47, XY, del(18)(q21q23), + r(18)(q21q23×2)[1]. ish 47, XY, del(18)(q21q23), + r(18)(q21q23)[84]/46, XY, del(18)(q21q23)[9]/48, XY, del(18)(q21q23), + r(18)(q21q23)×2[6]/47, XY, del(18)(q21q23), + r(18)(q21q23×2)[1]del(18)(q21q23)( D18Z1+, 18p+, 18q+, WCP18+ ), r(18)(q21q23)(WCP18+ ), r(18)(q21q23×2)(WCP18+ ). No pathogenic CNV was identified. Sequencing of 20 single sperms showed that 1 sperm was normal, 1 had yielded no result, 9 had harbored del(18q), 7 had harbored dup(18q)×2, and 2 had harbored dup(18q)×3. The dup/del fragments had both spanned approximately 33 Mb. Conclusion:It is rare for carriers of complex structural and numerical abnormalities of chromosome 18 to have a normal phenotype. Based on the accurate cytogenetic and molecular analyses and the single sperm CNV analysis, the influence of the aberrant karyotype on the gametogenesis may be evaluated.