Drug development remains a critical issue in the field of biomedicine.With the rapid advancement of information technologies such as artificial intelligence(AI)and the advent of the big data era,AI-assisted drug development has become a new trend,particularly in predicting drug-target associations.To address the challenge of drug-target prediction,AI-driven models have emerged as powerful tools,of-fering innovative solutions by effectively extracting features from complex biological data,accurately modeling molecular interactions,and precisely predicting potential drug-target outcomes.Traditional machine learning(ML),network-based,and advanced deep learning architectures such as convolutional neural networks(CNNs),graph convolutional networks(GCNs),and transformers play a pivotal role.This review systematically compiles and evaluates AI algorithms for drug-and drug combination-target predictions,highlighting their theoretical frameworks,strengths,and limitations.CNNs effectively identify spatial patterns and molecular features critical for drug-target interactions.GCNs provide deep insights into molecular interactions via relational data,whereas transformers increase prediction accu-racy by capturing complex dependencies within biological sequences.Network-based models offer a systematic perspective by integrating diverse data sources,and traditional ML efficiently handles large datasets to improve overall predictive accuracy.Collectively,these AI-driven methods are transforming drug-target predictions and advancing the development of personalized therapy.This review summa-rizes the application of AI in drug development,particularly in drug-target prediction,and offers rec-ommendations on models and algorithms for researchers engaged in biomedical research.It also provides typical cases to better illustrate how AI can further accelerate development in the fields of biomedicine and drug discovery.

BACKGROUND: Inflammation plays a critical role in severe cerebral venous thrombosis (CVT) pathogenesis, but the benefits of anti-inflammatory therapies remain unclear. This study aimed to investigate the association between steroid therapy combined with anticoagulation and the prognosis of acute/subacute severe CVT patients. METHODS: A prospective cohort study enrolled patients with acute/subacute severe CVT at Xuanwu Hospital (July 2020-January 2024). Patients were allocated into steroid and non-steroid groups based on the treatment they received. Functional outcomes (modified Rankin scale [mRS]) were evaluated at admission, discharge, and 6 months after discharge. Serum high-sensitivity C-reactive protein (hs-CRP), interleukin-6 (IL-6), cerebrospinal fluid (CSF) IL-6, and intracranial pressure were measured at admission and discharge in the steroid group. Fundoscopic Frisén grades were assessed at admission and 6 months after discharge. Univariate and multivariate logistic regression were used to evaluat associations between steroid use and favorable outcomes (mRS ≤2) at the 6-month follow-up. Paired tests assessed changes in hs-CRP and other variables before and after treatment, and Spearman's correlations were used to analyze relationships between these changes and functional improvements. RESULTS: A total of 107 and 58 patients in the steroid and non-steroid groups, respectively, were included in the analysis. Compared with the non-steroid group, the steroid group had a higher likelihood of achieving an mRS score of 0-2 (93.5% vs . 82.5%, odds ratio [OR] = 2.98, P  = 0.037) at the 6-month follow-up. After adjusting for confounding factors, the result remained consistent. Pulsed steroid therapy did not increase mortality during hospitalization or follow-up, nor did it lead to severe steroid-related complications (all P  >0.05). Patients in the steroid group showed a significant reduction in serum hs-CRP, IL-6, CSF IL-6, and intracranial pressure at discharge compared to at admission, as well as a significant reduction in the fundoscopic Frisén grade at the 6-month follow-up compare to at admission (all P  <0.001). A reduction in serum inflammatory marker levels during hospitalization positively correlated with improvements in functional outcomes ( P  <0.05). CONCLUSION: Short-term steroid use may be an effective and safe adjuvant therapy for acute/subacute severe CVT when used alongside standard anticoagulant treatments, which are likely due to suppression of the inflammatory response. However, these findings require further validation in randomized controlled trials. TRAIL REGISTRATION ClinicalTrials.gov , NCT05990894.
Adult ; Aged ; Female ; Humans ; Male ; Middle Aged ; Anticoagulants/therapeutic use* ; C-Reactive Protein/metabolism* ; Interleukin-6/metabolism* ; Intracranial Thrombosis/drug therapy* ; Prospective Studies ; Steroids/therapeutic use* ; Venous Thrombosis/drug therapy*

Drug development remains a critical issue in the field of biomedicine. With the rapid advancement of information technologies such as artificial intelligence (AI) and the advent of the big data era, AI-assisted drug development has become a new trend, particularly in predicting drug-target associations. To address the challenge of drug-target prediction, AI-driven models have emerged as powerful tools, offering innovative solutions by effectively extracting features from complex biological data, accurately modeling molecular interactions, and precisely predicting potential drug-target outcomes. Traditional machine learning (ML), network-based, and advanced deep learning architectures such as convolutional neural networks (CNNs), graph convolutional networks (GCNs), and transformers play a pivotal role. This review systematically compiles and evaluates AI algorithms for drug- and drug combination-target predictions, highlighting their theoretical frameworks, strengths, and limitations. CNNs effectively identify spatial patterns and molecular features critical for drug-target interactions. GCNs provide deep insights into molecular interactions via relational data, whereas transformers increase prediction accuracy by capturing complex dependencies within biological sequences. Network-based models offer a systematic perspective by integrating diverse data sources, and traditional ML efficiently handles large datasets to improve overall predictive accuracy. Collectively, these AI-driven methods are transforming drug-target predictions and advancing the development of personalized therapy. This review summarizes the application of AI in drug development, particularly in drug-target prediction, and offers recommendations on models and algorithms for researchers engaged in biomedical research. It also provides typical cases to better illustrate how AI can further accelerate development in the fields of biomedicine and drug discovery.

OBJECTIVE To investigate the effects of renally inappropriate medication （RIM） on the frailty of elderly patients with diabetes. METHODS The data of elderly patients with diabetes mellitus admitted to a third-grade class A hospital in Yunnan province from January to December 2022 were collected， and Beers criteria （2019 edition） and Chinese version of FRAIL scale were used to evaluate RIM and the frailty of the patients； the patients were divided into the trial group （with RIM） and the control group （without RIM） according to whether there was RIM. The propensity score matching was used to balance confounding factors between two groups， and the influence of RIM on the frailty of elderly diabetic patients was analyzed by the Logistic regression model. RESULTS Among the 367 patients， 80 patients （21.80%） had RIM， the drugs involved RIM were spironolactone （82.56%）， rivaroxaban （13.95%） and gabapentin （3.49%）. After reaching the balance between groups using the propensity score matching method， the incidence of frailty was 77.94% in trial group and 27.94% in control group （P＜0.001）； the difference was not statistically significant in other confounding factors between the two groups （P＞0.05）. Results of Logistic regression analysis showed that the risk of frailty in the experimental group was 3.118 times that of the control group （odds ratio was 3.118，95% confidence interval was 1.758-5.530， P＜0.001）. CONCLUSIONS RIM is a risk factor for the frailty of elderly patients with diabetes， which can be considered as an indicator for early identification and screening of the frailty of elderly diabetes patients.

Objective To compare the effects of intratracheal instillation by lumbar spinal needle and intratracheal atomization on bleomycin-induced pulmonary fibrosis modeling in mice,to determine the optimal modeling method.Methods Seventy-two C57BL/6J mice were divided randomly into control,lumbar spinal needle and aerosolization groups,according to body weight(n=24 mice per group).Mice in the control and lumbar spinal needle groups received intratracheal instillation of saline or bleomycin,respectively,and mice in the aerosolization group received aerosolized bleomycin intracheally by microsprayer aerosolizer.Micro-computed tomography(CT),histopathological changes,hydroxyproline(HYP)levels,Collagen Ⅰ(COL Ⅰ)and α-smooth muscle actin(α-SMA)protein expression were examined on days 14 and 21 to evaluate the degree of pulmonary fibrosis in each group.Results Mice in the two model groups showed listlessness,slow responses,and decreased body weights on days 14 and 21,compared with the control group(P＜0.001).Micro-CT showed white shadows surrounding the trachea in the lumbar spinal needle group,while the shadows were more diffuse in the aerosol group.The degrees of alveolitis and pulmonary fibrosis were highest in the aerosolization group,with a time-dependent trend.The hydroxyproline contents were significantly increased in the two model groups on days 14 and 21 after modeling(P＜0.05),with the increase on day 21 being more significant and stable(P＜0.001).COL Ⅰ expression was significantly increased in both the lumbar spinal needle group and aerosolization group on days 21 after modeling,especially in the aerosolization group(P＜0.001).Expression levels of α-SMA were significantly higher in the lumbar spinal needle group and aerosolization group compared with the control group on days 21(P＜0.001);however,there was no significant difference between the two model groups.Conclusions intratracheal atomization of bleomycin is the optimal method for establishing a mouse model of pulmonary fibrosis.

BACKGROUND:Exosomes play a role in all stages of wound repair,and there is currently a large body of research on exosomes in skin wound repair,which has been shown to have great potential for clinical applications. OBJECTIVE:To summarize and discuss the main mechanisms and clinical applications of exosomes in the treatment of skin wounds,in order to promote the clinical translation of exosomes. METHODS:PubMed,clinicaltrials.gov,China National Knowledge Infrastructure,Food and Drug Administration database,and Chinese Clinical Trial Register were searched from inception to March 2023.The English search terms were"exosomes,wound healing,stem cells,chronic wound,immunoregulation,inflammation,skin,therapeutic use,isolation,characterization,infections".The Chinese search terms were"exosomes,wound healing,stem cells,immunomodulation,clinical applications".A total of 79 articles were included for the summary. RESULTS AND CONCLUSION:(1)Exosomes can improve and accelerate wound healing through inflammation regulation,immune protection,angiogenesis,cell proliferation and migration,and collagen remodeling.(2)Exosomes derived from stem cells have mature preparation techniques and related mechanism research,which is currently the mainstream research direction.Non-stem cell-derived exosomes have the advantages of convenience,economy,and easy production,and can be used as a supplement for clinical applications.(3)The clinical application of exosomes is still in its infancy,but has great potential for application.Various exosome modification techniques have laid the foundation for the future development of clinically personalized services and require further research.(4)The clinical translation of exosomes faces many challenges,such as low yield,high heterogeneity,lack of unified standards for isolation,purification,and quality control,and difficulties in storage.

Objective To analyze the relationship between the common clinical indicators and diabetic foot ulcer(DFU)in type 2 diabetes mellitus(T2DM)patients by using the cross-sectional study and to provide the reference indicators for clinical DFU monitoring and prognosis evaluation.Methods A total of 115 T2DM patients admitted to the Department of Endocrinology,the Second Affiliated Hospital of Kunming Medical University from June 2021 to June 2023 were selected as the study objects and were divided into group A(with DFU)and group B(without DFU)according to whether they had DFU.Those in group A were then divided into group A1(Wagner0-1),group A2(Wagner2-3)and group A3(Wagner4)according to Wagner classification.The differences of general data,blood pressure,blood glucose,blood lipids and other common clinical indicators among all of the groups were compared,and the correlation between DFU and the above indicators was explored.Results Diabetes duration,D-dimer(DD),systolic blood pressure and other indexes in group A were higher than those in group B and there was a statistically significant difference(P<0.05).DD was the main risk factor for DFU in T2DM patients.Diabetic course in patients with DFU was positively correlated with the age(r>0,P<0.05),and negatively correlated with fasting blood glucose(FPG)level and 2hPG level at 2 hours after meals(r<0,P<0.05).The levels of interleukin-6(IL-6)and C-reactive protein(CRP)in A1 and A2 groups were lower than those in A3 group,the levels of neutrophils and leukocytes in A1 group were lower than those in A3 group,and the high density lipoprotein cholesterol(HDL-C)in A1 group was higher than that in A2 group and there was a statistically significant difference(P<0.05).Conclusion DD and systolic blood pressure are the main risk factors for DFU,and DD is closely related to DFU.The older the patients with T2DM,the later the onset of DFU.The worse the blood glucose control,the earlier the onset of DFU.HDL-C is a protective factor for peripheral vascular disease in T2DM patients.

Objective: To investigate the willingness to accept preventive treatments and its related factors among college freshmen with latent tuberculosis infection (LTBI), so as to provide the evidence for preventive treatment intervention measures for students with LTBI. Methods: Cluster sampling method was used to select 368 LTBI freshmen from 8 colleges and universities in Changzhou in September 2023, who conducted a questionnaire survey on the willingness to receive preventive treatment. General demographic data were collected and relevant data were collected using tuberculosis knowledge scale, General Anxiety Disorder-7 (GAD-7), Patient Health Questionnaire-9 (PHQ-9), Adaptation, Partnership, Growth, Affection and Resolve (APGAR), and a self developed Stigma Scale. A binary Logistic regression model was constructed with the willingness to accept preventive treatment as the dependent variable to analyze the willingness to accept preventive treatment and the influencing factors. Results: A total of 253 LTBI college freshmen were willing to take preventive treatment, the acceptance rate was 68.75%. The rate of willingness to accept preventive treatment for LTBI was higher among students whose fathers had an education level of high school, compared to those whose fathers had an education level of junior high school or below ( OR =2.16, P <0.05). LTBI students whose per capita family income was >5 000-10 000 yuan and >10 000 yuan were more willing to accept LTBI preventive treatment than those whose per capita family income was <3 000 yuan ( OR =2.72, 4.46, P <0.05). LTBI students who engaged in physical exercise for more than 2 hours per week were more willing to accept than those who exercised less than 0.5 hours per week ( OR =1.91, P <0.05). LTBI students with high levels of tuberculosis knowledge and stigma were more likely to receive preventive treatment ( OR =1.18, 1.11, P < 0.05). LTBI students with high PHQ-9 ( OR =0.85) and GAD-7 ( OR =0.92) scores were more likely to refuse preventive treatment ( P <0.05). Conclusion The present study revealed a moderate level of willingness of LTBI students to preventive treatment in Changzhou City, and the acceptance is affected by family factors, healthy lifestyles, tuberculosis knowledge and psychological status.

Diabetic foot(DF)is one of the most severe chronic complications of diabetes mellitus(DM),and it is an important cause of disability and mortality inpatients with DM.Changes in proteins in the tissues,organs and circulation of organisms can serve as microscopic reflections of the disease development process.Proteomics is an important technologyto explore the pathogenesis and treatment mechanism of dis-ease,and to find potential therapeutic targets and prognostic biomarkers of diseases.This article reviews the progress of proteomics research in DF.

OBJECTIVE To explore the therapeutic effect and safety of Maiwei Yangfei Decoction(MWYF)in the treatment of idiopathic pulmonary fibrosis of qi-yin deficiency type.METHODS A total of 58 patients with idiopathic pulmonary fibrosis of qi-yin deficiency type were randomly divided into an experimental group and a control group with 29 cases in each group according to a 1:1 ratio.Two cases dropped out of the experimental group and three cases dropped out of the control group.The control group received standardized treatment of Western medicine,and the experimental group received MWYF on the basis of the treatment of the control group.The treatment course of both groups was 3 months.The TCM syndrome score,lung function,6-minute walking distance(6MWD),transcutaneous blood oxygen saturation(SpO2),high-resolution computed tomography(HRCT)score,St.George's respir-atory questionnaire(SGRQ)score and serum sialoglycoprotein antigen(KL-6)level of the two groups were compared before and after treatment.Blood routine and liver and kidney function of the two groups were detected before and after treatment,and the occurrence of adverse reactions during treatment was recorded.RESULTS After treatment,the total score of TCM syndrome of the two groups was significantly improved(P<0.01),and the experimental group was better than the control group(P<0.01);the DLCO%of the experi-mental group increased(P<0.05),and the experimental group was higher than the control group(P<0.05).The experimental group showed significant improvement in 6MWD,HRCT grid shadow,SGRQ symptom score and total score,and serum KL-6 level(P<0.05,P<0.01),which was better than the control group(P<0.05,P<0.01).No serious adverse events occurred in either group dur-ing the treatment.CONCLUSION MWYF combined with standardized Western medicine treatment can effectively improve the clini-cal symptoms of patients with idiopathic pulmonary fibrosis of qi-yin deficiency type,reduce the expression level of serum KL-6,and has a definite effect and good safety.