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.

Traditional Chinese medicine (TCM) demonstrates distinctive advantages in disease prevention and treatment. However, analyzing its biological mechanisms through the modern medical research paradigm of "single drug, single target" presents significant challenges due to its holistic approach. Network pharmacology and its core theory of network targets connect drugs and diseases from a holistic and systematic perspective based on biological networks, overcoming the limitations of reductionist research models and showing considerable value in TCM research. Recent integration of network target computational and experimental methods with artificial intelligence (AI) and multi-modal multi-omics technologies has substantially enhanced network pharmacology methodology. The advancement in computational and experimental techniques provides complementary support for network target theory in decoding TCM principles. This review, centered on network targets, examines the progress of network target methods combined with AI in predicting disease molecular mechanisms and drug-target relationships, alongside the application of multi-modal multi-omics technologies in analyzing TCM formulae, syndromes, and toxicity. Looking forward, network target theory is expected to incorporate emerging technologies while developing novel approaches aligned with its unique characteristics, potentially leading to significant breakthroughs in TCM research and advancing scientific understanding and innovation in TCM.
Artificial Intelligence ; Medicine, Chinese Traditional ; Humans ; Network Pharmacology/methods* ; Drugs, Chinese Herbal/pharmacology* ; Animals ; Multiomics

The activation proteins released by fibroblasts in the tumor microenvironment regulate tumor growth, migration, and treatment response, thereby influencing tumor progression and therapeutic outcomes. Owing to the proliferation and metastasis of tumors, fibroblast activation protein (FAP) is typically highly expressed in the tumor stroma, whereas it is nearly absent in adult normal tissues and benign lesions, making it an attractive target for precision medicine. Radiolabeled agents targeting FAP have the potential for targeted cancer diagnosis and therapy. This comprehensive review aims to describe the evolution of FAPI-based radiopharmaceuticals and their structural optimization. Within its scope, this review summarizes the advances in the use of radiolabeled small molecule inhibitors for tumor imaging and therapy as well as the modification strategies for FAPIs, combined with insights from structure-activity relationships and clinical studies, providing a valuable perspective for radiopharmaceutical clinical development and application.

Objective To investigate the prevalence and the risk factors of heart disease(HD)in adults aged ≥80 years old in China based on the data from the 8th round of the Chinese Longitudinal Healthy Longevity Survey(CLHLS).Methods A total of 7 675 adults aged ≥80 years old were enrolled from the 8th round of CLHLS dataset.Chi-square tests were employed to examine associations between cardiovascular disease and demographic characteristics,socioeconomic status,social support,lifestyle factors,and health indicators.Logistic regression models were developed to analyze significant predictors of heart disease in the elderly.Results The prevalence of heart disease was 16％(n=1 228)in 7 675 elderly people.Aged 90-99 years old(odds ratio[OR]=0.816),≥100 years old(OR=0.641),female(OR=0.833),and low body mass index(BMI)(＜18.5 kg/m2,OR=0.778)were the protective factors for cardiovascular disease in the elderly;and high BMI(24.0 to 27.9 kg/m2,OR=1.209),rural residence(OR=2.384),health examination(OR=1.164),dysfunction of daily living activities(OR=1.401),hypertension(OR=2.143),diabetes mellitus(OR=1.719),and history of cerebrovascular accident(OR=2.080)were risk factors.Conclusion Male,overweight,rural residence,health examination,dysfunction of daily living activities,hypertension,diabetes mellitus,and a history of cerebrovascular accident are the risk factors for heart disease in the elderly.

Objective:To investigate the efficacy of self-prescribed Huoxue Shengjing Prescription as adjuvant therapy for varicocele-induced infertility and its impact on the outcomes of in vitro fertilization-embryo transfer/intracytoplasmic sperm injection (IVF-ET/ICSI).Methods:A randomized controlled trial was conducted. A total of 99 patients with varicocele-induced infertility in our hospital from January 2022 to July 2023 were selected as observation subjects and divided into three groups using a random number table method, with 33 patients in each group. The low ligation group received low ligation of varicocele under a microscope, the low ligation + conventional Western medicine treatment group received low ligation + conventional Western medicine therapy, and the combined group received low ligation + conventional Western medicine therapy + a self-prescribed Huoxue Shengjing Prescription. Among them, the low ligation of varicocele under a microscope was followed by IVF-ET/ICSI assisted reproductive technology 3 months after surgery; the conventional Western medicine therapy involved continuous administration of L-carnitine oral solution for 3 months; the self-prescribed Huoxue Shengjing Prescription was started on the first day after surgery and continued for 3 months. TCM syndrome scores were assessed before and after treatment, and semen routine analysis was performed using an automated semen quality analyzer. Mitochondrial activity of granulosa cells was measured using the Hrudka extraction method, and sperm nuclear DNA integrity was assessed using a modified alkaline single-cell gel electrophoresis method. Follow-up was conducted for 1 year to observe and record the outcomes of IVF-ET/ICSI and evaluate the clinical efficacy.Results:The total effective rate was 93.9% (31/33) in the combined group, 69.7% (23/33) in the low ligation group, and 75.8% (25/33) in the low ligation + conventional Western medicine treatment group, with statistical significance ( χ 2=6.52, P=0.039). After treatment, the scores for mild abdominal pain, testicular heavy pain, impotence, mental fatigue, and the total score in the combined group were lower than those in the low ligation + conventional Western medicine treatment group and the low ligation group ( F values were 89.29, 97.51, 136.36, 155.06, and 311.13, respectively, P<0.001). The sperm survival rate, sperm concentration, normal morphology rate, and progressive motility rate in the combined group were higher than those in the low ligation + conventional Western medicine treatment group and the low ligation group ( F values were 19.23, 11.85, 35.97, and 52.21, respectively, P<0.001). Mitochondrial grade I cell activity of granulosa cells was higher than that of the low ligation + conventional treatment group and low ligation group ( F=23.23, P<0.001), and grade Ⅲ cell activity was lower than that of the low ligation + conventional treatment group and low ligation group ( F=20.28, P<0.001). After treatment, the detection of grade Ⅰ and Ⅱ sperm nuclear DNA integrity in the combined group were higher than those in the low ligation + conventional Western medicine treatment group and the low ligation group ( F values were 17.73 and 18.39, respectively, P<0.001), while grades Ⅲ and Ⅳ were lower than those in the low ligation + conventional Western medicine treatment group and the low ligation group ( F values were 29.07 and 10.36, respectively, P<0.001). During follow-up, the excellent embryo rate and the spouse's clinical pregnancy rate in the combined group were higher than those in the low ligation + conventional Western medicine treatment group and the low ligation group ( χ2 values were 14.92 and 8.38, respectively; P values were 0.001 and 0.015, respectively). Conclusion:The adjuvant treatment with a self-prescribed Huoxue Shengjing Prescription can enhance sperm quality in patients with varicocele-related infertility, maintain DNA integrity, regulate seminal plasma mitochondrial function, increase the rate of high-quality embryos, and improve the spouse's pregnancy outcomes.

Objective:To elucidate the expression of angiopoietin-like protein 4 (ANGPTL4) in LPS-induced septic cardiomyopathy tissue and cardiomyocyte, and to explore the mechanism of ANGPTL4 in septic cardiomyopathy.Methods:Fifty C57BL/6 mice, aged 8 weeks, were randomly(random number) divided into a treatment group (LPS) and a control group ( n = 25 each). The mice in the treatment group were intraperitoneally injected with LPS (10 mg/kg) to establish a sepsis model. After 24 h, the myocardial tissues of the mice in the sepsis group and the control group, which were caused by LPS, were collected for RNA sequencing to pick out the differentially expressed gene of ANGPTL4.Ventricular myocytes of neonatal mice were taken, and the silencing and overexpression vectors of ANGPTL4 were transfected. After 48 hours of transfection, the cells were collected for subsequent detection. Western blot method was used to detect the expression of apoptotic factors Bax, Bcl-2, and Caspase 3 in mouse ventricular myocytes; CCK8 method was used to detect the activity of ventricular myocytes; using the Annexin V-FITC and PI double staining method, the apoptosis of ventricular myocytes was detected. Results:RNA-seq analysis revealed a statistically significant upregulation of ANGPTL4 expression at both transcriptional and translational levels in the ventricular tissue of septic mice, as compared to the control group ( P<0.05). The results of qRT-PCR and Western blot indicated that the mRNA and protein levels of ANGPTL4 in the ventricular tissues and cardiomyocytes of mice treated with LPS were significantly increased ( P<0.05). After transfection of the silencing and overexpression vectors of ANGPTL4 in cardiomyocytes, it was found that compared with NC, the mRNA and protein expression levels of ANGPTL4 in the si-ANGPTL4 group significantly decreased ( P<0.05), the vitality of ventricular myocytes increased ( P<0.05), the expressions of apoptosis-related factors Bax and Caspase 3 significantly decreased ( P<0.05), and the expression of Bcl-2 significantly increased ( P<0.05), and the number of apoptotic cells significantly decreased ( P<0.05); while the transfection of the overexpression vector of ANGPTL4 showed an opposite trend. Conclusions:In septic myocardial tissue and cardiomyocyte, the expression of ANGPTL4 is elevated, resulting in the inhibition of ventricular myocyte viability and the promotion of cardiomyocyte apoptosis.

Eye diagnosis is a method for inspecting systemic diseases and syndromes by observing the eyes.With the development of intelligent diagnosis in traditional Chinese medicine(TCM),artificial intelligence(AI)can improve the accuracy and efficiency of eye diagnosis.However,the research on intelligent eye diagnosis still faces many challenges,including the lack of standardized and precisely labeled data,multi-modal information analysis,and artificial in-telligence models for syndrome differentiation.The widespread application of AI models in medicine provides new insights and opportunities for the research of eye diagnosis intelli-gence.This study elaborates on the three key technologies of AI models in the intelligent ap-plication of TCM eye diagnosis,and explores the implications for the research of eye diagno-sis intelligence.First,a database concerning eye diagnosis was established based on self-su-pervised learning so as to solve the issues related to the lack of standardized and precisely la-beled data.Next,the cross-modal understanding and generation of deep neural network models to address the problem of lacking multi-modal information analysis.Last,the build-ing of data-driven models for eye diagnosis to tackle the issue of the absence of syndrome dif-ferentiation models.In summary,research on intelligent eye diagnosis has great potential to be applied the surge of AI model applications.

Objective:To explore the medication law of TCM compounds used in the treatment of non-small cell lung cancer (NSCLC).Methods:Clinical literature about TCM compounds in the treatment of NSCLC was retrieved from CNKI, Wanfang Data, PubMed and Web of Science core collection database from January 1st, 2003 to May 1st, 2023. The Python and the ancient and modern medical record cloud platform V2.3.7 were used to analyses frequency statistics and properties, and clustering analysis, factor analysis and association rule analysis were performed.Results:A total of 866 articles were included, with 660 effective TCM compounds, 647 kinds of Chinese materia medica. There were 36 kinds of high-frequency Chinese materia medica, such as Astragali Radix, Atractylodis Macrocephalae Rhizoma and Poria; the efficacy categories of Chinese materia medica mainly included tonics and phlegm resolving cough relieving and asthma relieving drugs. Cluster analysis obtained 4 clusters, factor analysis extracted 11 common factors, and association rule analysis obtained 37 highly supported combinations of Chinese materia medica. The most reliable triple drug combination among them was Astragali Radix-Atractylodis Macrocephalae Rhizoma-Hedyotis diffusa willd, and the double drug combination was Astragali Radix-Ligustri Lucidi Fructus.Conclusion:TCM for the treatment of NSCLC mainly focuses on strengthening the healthy qi, clearing heat, resolving phlegm and detoxifying toxins, supplemented by tonifying qi and activating blood circulation, dispelling dampness and resolving phlegm.

Objective:To investigate the factors affecting the change of serum calcium and phosphorus after total parathyroidectomy for secondary hyperparathyroidism(SHPT).Method:Sixty patients with secondary hyperparathyroidism undergoing total parathyroidectomy were selected.Gender, age, hemodialysis time, bone pain time, intravenous calcium supplementation time, blood parathyroid hormone(PTH), parathyroid mass, blood calcium, phosphorus and alkaline phosphatase at admission were tested to compare the correlation between postoperative calcium and phosphorus changes.Result:Blood calcium was: (2.50±0.02), (2.27±0.03), (1.97±0.03), (1.95±0.03), (1.95±0.03), (2.03±0.02) mmol/L at admission, 6 hours after surgery, 1, 2, 3 days after surgery, and when discharged. Blood phosphorus was: (2.32±0.07), (1.95±0.05), (1.65±0.06), (1.44±0.05), (1.35±0.36), (1.14±0.04) mmol/L and when discharged.There are differences between pairwise comparisons ( F=100.979, P<0.05; F=118.910, P<0.05). The blood PTH was (1 791±760) pg/ml, and the postoperative intravenous calcium supplementation time was (7.13±2.34) days. Blood PTH was positively correlated with bone pain time, blood phosphorus and parathyroid mass at admission ( t=-2.199, P<0.05; t=4.718, P<0.05; t=2.507, P<0.05). The time of intravenous calcium supplementation was positively correlated with ALP at admission ( t=3.098, P<0.05). Preoperative serum PTH > 1 430 pg/ml or ALP > 191 mmol/L were prone to hypocalcemia on the first day after surgery. Conclusions:The longer bone pain time, the higher blood phosphorus and the more obvious parathyroid hyperplasia were, the higher PTH was. The higher the ALP, the longer the time of intravenous calcium supplementation. Preoperative serum PTH and ALP values can be used as predictors of hypocalcemia on the first day after surgery.

Objective To investigate the reliability and validity of the assessment tools of Brief ICF Core Sets for Arthroplasty of Knee Osteoarthritis in Perioperative Period(ICSAKOPP). Methods From May,2022 to April,2023,320 patients undergoing knee arthroplasty were selected in Peking University Third Hospital,China-Japan Friendship Hospital,Peking University First Hospital and Chinese PLA General Hospital.Trained assessors used Brief ICSAKOPP to evaluate all enrolled patients before arthroplasty,three days(±one day)after arthroplasty,three weeks(±one week)after arthroplasty,and three months(±one month)after ar-throplasty.Western Ontario and McMaster Universities Osteoarthritis Index(WOMAC)scores were recorded at the same time.Five professionals were asked to score all the items of Brief ICSAKOPP,and the content validity index(CVI)was caculated. Results A total of 64 cases were dropped down.CVI of all the items of the Brief ICSAKOPP were above 0.8,with a av-erage CVI of the scale of 0.938.The Cronbach's α coefficient of the Brief ICSAKOPP was 0.813.There was a moderate correlation(r=0.681,P<0.001)between the overall Brief ICSAKOPP and WOMAC scores,as well as body functional dimension score(r=0.668,P<0.001)and activities and participation dimension score(r=0.657,P<0.001). Conclusion Brief ICSAKOPP is good in content validity,internal consistency reliability and criterion validity.