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 screen and identify the key active molecules, signaling pathways, and therapeutic targets of Shuxuening (SXN) injection for treating liver cirrhosis (LC) and to evaluate its therapeutic potential using a mouse model. Methods: Target genes of SXN and LC were retrieved from public databases, and enrichment analysis was performed. A protein–protein interaction (PPI) network was constructed using the Search Tool for the Retrieval of Interacting Genes/Proteins (STRING), and hub genes were identified using Molecular Complex Detection (MCODE). LC was induced in rats and mice via intraperitoneal injections of diethylnitrosamine and carbon tetrachloride (CCl4) for 12 weeks. Starting at week 7, SXN was administered intraperitoneally to the mice in the treatment group. Serum and liver tissues of the mice were collected for the detection of indicators, pathological staining, and expression analysis of hub targets using quantitative real-time polymerase chain reaction (qRT-PCR). Results: We identified 368 overlapping genes (OLGs) between SXN and LC targets. These OLGs were subsequently used to build a PPI network and to screen for hub genes. Enrichment analysis showed that these genes were associated with cancer-related pathways, including phosphoinositide-3-kinase/Akt and mitogen-activated protein kinase signaling and various cellular processes, such as responses to chemicals and metabolic regulation. In vivo experiments demonstrated that SXN treatment significantly improved liver function and pathology in CCl4-induced LC mice by reducing inflammation and collagen deposition. Furthermore, qRT-PCR demonstrated that SXN regulated the expression of MAPK8, AR and CASP3 in the livers of LC mice. Conclusion This study highlighted the therapeutic effects of SXN in alleviating LC using both bioinformatics and experimental methods. The observed effect was associated with modulation of hub gene expression, particularly MAPK8, and CASP3.

Objective To investigate the potential beneficial predictors for endovascular treatment(EVT)in case of acute anterior circulation large vessel occlusion with large-core infarction.Methods We made a retrospective inclusion of 92 patients with anterior circulation large vessel occlusion and core infarct volume ranging from 50 to 100 mL,who underwent EVT at Zhangzhou Municipal Hospital of Fujian Province from March 2018 to February 2021.All the patients were confirmed as anterior circulation large infarction and large infarct volume using computed tomography(CT),computed tomography angiography(CTA),and computed tomography perfusion(CTP)before EVT.All clinical and imaging data were collected to observe the postoperative recurrence rate,incidence of symptomatic intracranial hemorrhage(sICH),and functional prognosis 90 days.Then the patients were divided into favorable outcomes group(mRS≤3)and unfavorable outcomes group(mRS＞3)based on Rankin scores 90 days post-stroke.Univariate and multivariate Logistic analysis were conducted to analyze factors influencing the patients'prognosis.By combining the results of multivariate analysis,we constructed receiver operating characteristic(ROC)curves and identified the cut-off value to evaluate the predictive value of age for post-vascular treatment prognosis.Results Among the included patients,the postoperative revascularization rate(mTIICI≥2b)was 95％(88 cases),the rate of favorable outcomes at 90 days postoperatively(mRS≤3)was 32.61％(30 cases),the incidence of sICH was 13％,and the mortality rate was 31.5％.Compared with the unfavorable outcomes group,the favorable outcomes group had a younger age and a higher proportion of males.Multivariate analysis indicated that older age was an independent risk factor for adverse outcomes following endovascular treatment(OR=4.97,95％CI:1.78-13.90,P=0.002).The ROC curve indicated that the area under the curve was maximized at the age of 72.5 years(AUC=0.763,95％CI:0.661-0.864,P＜0.001).Its sensitivity and specificity was 0.565 and 0.833,respectively.Conclusion Age is an independent predictor of the prognosis of acute procirculatory large core stroke.Patients with large core infarction older than 72.5 years may not benefit from endovascular therapy,which needs to be confirmed by a multicenter large sample prospective randomized controlled trial.

In the non-acute phase, when the collateral circulation is poorly compensated due to atherosclerotic occlusion of the middle cerebral artery, it can lead to significant neurological dysfunction and a higher recurrence rate of stroke. Traditional treatments primarily involve managing risk factors and administering symptomatic pharmacotherapy, yet the outcomes are often unsatisfactory. In recent years, with the development of endovascular interventional techniques and interventional materials, microsurgical anastomosis, techniques, and the present of distal ischemic modulation, the treatment of symptomatic arteriosclerosis occlusion of the non-acute middle cerebral artery is attracting more and more attention in the field. This article reviews the progress of the treatment of symptomatic arteriosclerosis occlusion of the non-acute middle cerebral artery. For the surgical treatment of symptomatic non-acute middle cerebral artery atherosclerosis occlusion (SNMCAO) in non-acute phase, the superior temporal artery middle cerebral artery (STA-MCA) low flow bypass and intravascular interventional recanalization have their own advantages. For patients with short expected occlusion time, short occlusion segment, straight blood vessels, and good distal vascular bed, they may be more inclined to undergo endovascular recanalization treatment, otherwise they may choose STA-MCA low flow bypass surgery. Regardless of which treatment method is chosen, precise individualized evaluation must be conducted before surgery to select an individualized surgical approach that can maximize the benefits for patients with SNMCAO.

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.

Traditional Chinese medicine (TCM) is characterized by complex, multicomponent herbal formulations that challenge the conventional“one drug, one target” paradigm. Network pharmacology, through the construction of multilayered drug-target-disease networks, provides a systematic framework for unraveling TCM’s multitarget and multipathway mechanisms. Recent advancements in artificial intelligence, particularly large language models (LLMs), further enhance data integration, target identification, and clinical decision-making. This review synthesizes current progress in the application of network pharmacology and LLMs in TCM, highlighting their potential to deepen mechanistic insights and optimize drug discovery. By bridging traditional medical wisdom with modern computational tools, this integrative approach aims to advance the scientific validation of TCM and foster innovative healthcare solutions.

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*

In the non-acute phase, when the collateral circulation is poorly compensated due to atherosclerotic occlusion of the middle cerebral artery, it can lead to significant neurological dysfunction and a higher recurrence rate of stroke. Traditional treatments primarily involve managing risk factors and administering symptomatic pharmacotherapy, yet the outcomes are often unsatisfactory. In recent years, with the development of endovascular interventional techniques and interventional materials, microsurgical anastomosis, techniques, and the present of distal ischemic modulation, the treatment of symptomatic arteriosclerosis occlusion of the non-acute middle cerebral artery is attracting more and more attention in the field. This article reviews the progress of the treatment of symptomatic arteriosclerosis occlusion of the non-acute middle cerebral artery. For the surgical treatment of symptomatic non-acute middle cerebral artery atherosclerosis occlusion (SNMCAO) in non-acute phase, the superior temporal artery middle cerebral artery (STA-MCA) low flow bypass and intravascular interventional recanalization have their own advantages. For patients with short expected occlusion time, short occlusion segment, straight blood vessels, and good distal vascular bed, they may be more inclined to undergo endovascular recanalization treatment, otherwise they may choose STA-MCA low flow bypass surgery. Regardless of which treatment method is chosen, precise individualized evaluation must be conducted before surgery to select an individualized surgical approach that can maximize the benefits for patients with SNMCAO.

Objective To investigate the potential beneficial predictors for endovascular treatment(EVT)in case of acute anterior circulation large vessel occlusion with large-core infarction.Methods We made a retrospective inclusion of 92 patients with anterior circulation large vessel occlusion and core infarct volume ranging from 50 to 100 mL,who underwent EVT at Zhangzhou Municipal Hospital of Fujian Province from March 2018 to February 2021.All the patients were confirmed as anterior circulation large infarction and large infarct volume using computed tomography(CT),computed tomography angiography(CTA),and computed tomography perfusion(CTP)before EVT.All clinical and imaging data were collected to observe the postoperative recurrence rate,incidence of symptomatic intracranial hemorrhage(sICH),and functional prognosis 90 days.Then the patients were divided into favorable outcomes group(mRS≤3)and unfavorable outcomes group(mRS＞3)based on Rankin scores 90 days post-stroke.Univariate and multivariate Logistic analysis were conducted to analyze factors influencing the patients'prognosis.By combining the results of multivariate analysis,we constructed receiver operating characteristic(ROC)curves and identified the cut-off value to evaluate the predictive value of age for post-vascular treatment prognosis.Results Among the included patients,the postoperative revascularization rate(mTIICI≥2b)was 95％(88 cases),the rate of favorable outcomes at 90 days postoperatively(mRS≤3)was 32.61％(30 cases),the incidence of sICH was 13％,and the mortality rate was 31.5％.Compared with the unfavorable outcomes group,the favorable outcomes group had a younger age and a higher proportion of males.Multivariate analysis indicated that older age was an independent risk factor for adverse outcomes following endovascular treatment(OR=4.97,95％CI:1.78-13.90,P=0.002).The ROC curve indicated that the area under the curve was maximized at the age of 72.5 years(AUC=0.763,95％CI:0.661-0.864,P＜0.001).Its sensitivity and specificity was 0.565 and 0.833,respectively.Conclusion Age is an independent predictor of the prognosis of acute procirculatory large core stroke.Patients with large core infarction older than 72.5 years may not benefit from endovascular therapy,which needs to be confirmed by a multicenter large sample prospective randomized controlled trial.