Objective In traditional laboratory animal centers, there are issues such as low efficiency in cage scheduling, insufficient supervision of personnel behavior, and difficulty in upgrading aging equipment. This study aims to upgrade the information system of existing laboratory animal centers by applying multimodal large language model technology. This upgrade intends to achieve real-time perception of the status of animal cages, intelligent supervision of experimental personnel behavior, and automated processing of business workflows, thereby improving management efficiency and precision. Methods An AI-based approach for upgrading laboratory animal center informatization was proposed by the First Affiliated Hospital of Zhejiang University School of Medicine,compatible with different breeding equipments. The system architecture, from the bottom up, consisted of three layers: hardware layer, core algorithm layer, and application layer. The hardware layer was equipped with cameras and high-speed network transmission devices for collecting information on cages and personnel. The core algorithm layer utilized multi-stage image preprocessing technology and multimodal large language model recognition technology to extract and identify image information. The application layer integrated the recognition results with the existing information of the animal center to generate real-time cage occupancy heatmaps, which visually and clearly showed the density distribution of cage usage in the laboratory animal center. Results The AI-based management system achieved a cage recognition accuracy of 98.5% and a correct wearing identification rate of laboratory coats of 98.8%. The average image processing time was 3.7 seconds per image, the effective utilization rate of cages increased by 23%, and the turnover efficiency improved by 35%. In addition, the management system could track and warn against non-compliant behaviors in real time. After intelligent recognition, the system detected more violations, with the violation detection rate increasing by 90.6%. After continuous use for three months, the weekly average number of violations decreased by 54.0% compared to the baseline period. Conclusion This study applies multimodal large language model to the field of laboratory animal management, achieving real-time monitoring and automated management of cage identification, thereby improving management efficiency and precision. The system integrates multi-source data such as visual recognition and behavior analysis, establishing a comprehensive intelligent supervision system for experimental personnel. It provides research institutions with efficient, accurate, and cost-effective management tools, promoting the intelligent development of laboratory animal management.

Hypertension is a common chronic disease with elevated arterial pressure as the main clinical manifestation，which can cause lesions in important organs such as heart，brain and kidney. In recent years，the prevalence of hypertension has increased，and its incidence is also increasing year by year. Combining the theory of traditional Chinese medicine （TCM） with personal clinical experience，Academician TONG Xiaolin put forward the specific pathogenesis of "disease-stage-state" of hypertension based on the state-target theory. Lipophagy plays an important role in the pathogenesis of hypertension by interfering with lipid metabolism，atherosclerosis，arterial plaque formation，vascular remodeling，vascular endothelial injury and other aspects of hypertension. Through modern medical and biological research，on the one hand，it is believed that the dynamic pathological changes in lipophagy are closely related to the "stage" of hypertensive state-target differentiation and treatment，corresponding to the time points of disease occurrence and development in the three stages of hypertension. On the other hand，it is believed that lipophagy is an important microscopic manifestation of the "state" of hypertensive state-target differentiation and treatment. From the perspective of lipophagy，this paper discusses the biological connotation of the 'disease-stage-state' model of state-target differentiation and treatment of hypertension and draws on the modern medicine to understand the law of disease development，matching the macro differentiation and treatment of TCM and the micro physico-chemical indicators of modern medicine to achieve precise TCM treatment. This study provides new ideas for the early prevention and treatment of hypertension and its complications.

A case of spinal cord abscess caused by Nocardia cyriacigeorgica is reported. The patient is an elderly man with a history of nephritic syndrome who presented with aggravating lower back pain and then gradually developed urinary retention, weakness and numbness in both lower extremities. Operative intervention was performed, and postoperative pathological findings suggested spinal cord abscess formation. Metagenomic next-generation sequencing of the cerebrospinal fluid identified Nocardia cyriacigeorgica as the causative pathogen. Although appropriate antibiotics were prescribed, the patient died 3 months later.

It is believed that children bronchiolitis obliterans （BO） is located at the lung and closely related to the spleen and kidney. Phlegm， stasis， block and deficiency are the main pathogenesis. This article promotes staged differentiation and treatment of BO considering the clinical manifestations and pathogenesis characteristics. The attack stage is dominated by phlegm and stasis blocking the lung， for which the method of dissolving phlegm and dispelling stasis， relieving cough and calming panting should be used； Xiaoqinglong Decoction（小青龙汤） and Sanzi Yangqin Decoction （三子养亲汤） with modifications and selfmade Modified Wuhu Decoction （五虎汤加味） are recommended for cold-phlegm blocking the lung syndrome and phlegm heat blocking the lung syndrome， respectively. In sustained stage， the upper excess and lower deficiency together with phlegm-stasis blocking the lung are the pathogenesis， for which the method of dissolving phlegm and dispelling stasis， reopening the block and supplementing deficiency is suggested， and Xiaoqinglong Decotion （小青龙汤） and Duqi pills （都气丸） with modifications can be used. In convalescent stage， the pathogenesis is lung-spleen-kidney depletion with residual pathogen. It suggested to supplement the deficiency and consolidate the root， as well as clear the residual pathogen， for which Baogen NO.1 Decoction （宝根1号方） with modifications can be used.

Objective To study the clinical efficacy of temporal small bone window microscopic craniot-omy in treating cerebral hemorrhage in basal ganglia region.Methods The retrospective analysis was adopt-ed.A total of 130 patients with intracerebral hemorrhage in the basal ganglia region treated in the Department of Neurosurgery of this hospital from January 2020 to January 2023 were selected as the study subjects.The patients treated by traditional frontotemporal large bone flap craniotomy hematoma removal were included in-to the control group (n=82) and the patients adopting temporal straight incision small bone window hemato-ma removal were included into the study group (n=48).The general data,surgical indicators,clinical efficacy,degree of neurological impairment,postoperative complications and postoperative quality of life of the patients were statistically analyzed.Results There were no statistically significant differences in preoperative Glasgow (GCS) score,gender,age and hematoma volume between the two groups (P>0.05);there was no statistically significant difference in the average hematoma clearance rate between the two groups (P>0.05);compared with the control group,the operation time and hospital stay of the study group were shorter,the incidence of severe edema and suboccipital fluid accumulation were lower,and the good prognosis rate was higher,with sta-tistical significance (P<0.05).Conclusion Temporal straight incision small bone window microscopic hema-toma removal in treating cerebral hemorrhage in basal ganglia region has mild edema reaction of brain tissue in operative area,the neurological function obtains the better protection and the good prognostic rate of the pa-tients is significantly increased.

The new generation of artificial intelligence technology,represented by deep learning,has emerged as a crucial driving force in the advancement of new drug research and development.This article creatively proposes a workflow named"Molecular Factory"for the design and optimization of drug molecules based on artificial intelligence technology.This workflow integrates intelligent molecular generation models,high-performance molecular docking algorithms,and accurate protein-ligand binding affinity prediction methods.It has been integrated as a core module into DrugFlow,a one-stop drug design software platform,providing a comprehensive set of mature solutions for the discovery and optimization of lead compounds.Utilizing the"Molecular Factory"module,we conducted the research of second-generation inhibitors against Menin that can combat drug resistance.Through the integration of computational and experimental approaches,we rapidly identified multiple promising compounds.Among them,compound RG-10 exhibited the IC50 values of 9.681 nmol/L,233.2 nmol/L,and 40.09 nmol/L against the wild-type Menin,M327I mutant,and T349M mutant,respectively.Compared to the positive reference molecule SNDX-5613,which has entered Phase Ⅱ clinical trials,RG-10 demonstrated significantly enhanced inhibitory activity against the M327I and T349M mutants.These findings fully demonstrate the unique advantages of the"Molecular Factory"technology in practical drug design and development scenarios.It can rapidly and efficiently generate high-quality active molecules targeting specific protein structures,holding significant value and profound implications for advancing new drug discovery.

Objective To study the effects of the intelligent hearing-assistive system incorporated in Nuro-tron cochlear implants(CI),including the autonomic acoustic scene recognition(ASR),intelligent strategy config-uration as well as the objective and subjective hearing improvements on recipients.Methods ① To evaluate the per-formance of the ASR matule,in a sound-proof room,the preset five kinds of test audios,including speech,noise,speech in noise,pure music(without human voice)and non-pure Music(with human voice)were played.Each type of scenes included 6 to 9 5 min test files.The prediction accuracy and scene switching times were calculated.② In order to evaluate the noise-reduction performance of the ABeam technology in the speech enhancement module,13 Nurotron? CI recipients were recruited and their speech recognition rate when ABeam was"ON"and"OFF"with noise coming from 90°,180°or 270°were tested,individually.Also,their subjective hearing feedback was evaluated through visual analogue scale(VAS)evaluation.Results The ASR module achieved high prediction performance,with prediction accuracy 99％±4％,96％±9％,94％±12％,94％±15％,92％±13％for speech,noise,noisy speech,pure music and non-pure music,respectively.The scene transation times for each individual scene were 1.1 ±0.3,1.4±0.7,1.3±0.5,1.4±0.8 and 1.3±0.5,indicating that the prediction was also stable.When noise came from the sides and behind of recipients and speech signal from the front,the adaptive dual microphone noise re-duction algorithm ABeam significantly increased the speech recognition score(SRS)in 5 dB signal-to-noise(SNR)environment(P＜0.001),with an average increase of 15.92％.Especially when the noise came from 180 degree backward,the SRS increased 28.68％when ABeam was"0N",which was significantly higher than when ABeam was"OFF"(P＜0.01).Conclusion The intelligent hearing-assistive system can help CI recipients automatically configure appropriate SPSs under different environments,improving the speech intelligibility and hearing comfort.

Prediction of the interactions between small molecules and their targets play important roles in various applications of drug development, such as lead discovery, drug repurposing and elucidation of potential drug side effects. Therefore, a variety of machine learning-based models have been developed to predict these interactions. In this study, a model called auxiliary multi-task graph isomorphism network with uncertainty weighting (AMGU) was developed to predict the inhibitory activities of small molecules against 204 different kinases based on the multi-task Graph Isomorphism Network (MT-GIN) with the auxiliary learning and uncertainty weighting strategy. The calculation results illustrate that the AMGU model outperformed the descriptor-based models and state-of-the-art graph neural networks (GNN) models on the internal test set. Furthermore, it also exhibited much better performance on two external test sets, suggesting that the AMGU model has enhanced generalizability due to its great transfer learning capacity. Then, a naïve model-agnostic interpretable method for GNN called edges masking was devised to explain the underlying predictive mechanisms, and the consistency of the interpretability results for 5 typical epidermal growth factor receptor (EGFR) inhibitors with their structure‒activity relationships could be observed. Finally, a free online web server called KIP was developed to predict the kinome-wide polypharmacology effects of small molecules (http://cadd.zju.edu.cn/kip).

Objective To investigate the effect of imatinib on the growth of A549 non-small cell lung cancer transplanted tumors and the expression of PDGFB and PDGFRβ proteins in tumor tissues and stroma in nude mice and to explore the underlying tumor suppression mechanism. Methods A transplantation tumor model of A549 non-small cell lung cancer was established in nude mice. The mice were then randomly divided into four groups: control group (0.9%NaCl), low-dose imatinib group (50 mg/(kg·d)), medium-dose imatinib group (100 mg/(kg·d)), and high-dose imatinib group (200 mg/(kg·d)). The effect of different concentrations of imatinib administered by continuous gavage on tumor growth was observed for 28 days. HE staining was performed to observe the pathological changes of tumor tissues. The expression of PDGF/PDGFR pathway-related proteins and the phosphorylation levels of AKT and ERK1/2 proteins in tumor tissues were detected by Western blot analysis. Double immunofluorescence staining was used to detect the expression of PDGFB and PDGFRβ proteins in the tumor stroma. Results Imatinib inhibited the growth of A549 non-small cell lung cancer cells in nude mice, suppressed the expression of PDGFB in tumor tissues, and decreased the phosphorylation levels of PDGFRβ, AKT, and ERK1/2. The expression of PDGFB and PDGFRβ in tumor stromal fibroblasts of the administered group was significantly lower than that of the control group. Conclusion Imatinib exhibits a pronounced inhibitory effect on A549 xenografts of nude mice with non-small cell lung cancer, and its antitumor mechanism may involve the downregulation of PDGFB and PDGFRβ expression in tumor stromal fibroblasts.

Objective:To retrospectively analyze the independent risk factors of complicated appendicitis(CA)in children under five years old and establish a clinical prediction model, and to evaluate the clinical application of this model.Methods:A retrospective analysis was performed on children under five years old who underwent appendectomy at Children′s Hospital of Shanghai Jiao Tong University School of Medicine from January 2018 to December 2021.The children were divided into CA group and uncomplicated appendicitis group according to whether there was sign of perforation or gangrene in appendiceal tissue after operation.The differences in clinical features and preoperative laboratory test results between two groups were compared.The independent risk factors of CA were identified and a clinical prediction model was established.The clinical prediction model was verified by receiver operating characteristic curve.Results:A total of 140 children were enrolled in this study, including 84 cases in the CA group and 56 cases in uncomplicated appendicitis group.Univariate and binary Logistic regression analysis showed that the duration of symptoms>23.5 h( OR=6.650, 95% CI 2.469-17.912, P<0.05), abdominal muscle tension( OR=3.082, 95% CI 1.190-7.979, P<0.05) and C-reactive protein>41 mg/L ( OR=3.287, 95% CI 1.274-8.480, P<0.05) were independent risk factors for CA( P<0.05). The clinical prediction model of CA was constructed by the above mentioned three independent risk factors.The area under the receiver operating characteristic curve of the clinical prediction model was 0.881(95% CI 0.825-0.936), the sensitivity was 77.4%, the specificity was 87.5%, the positive predictive value was 91.3% and the negative predictive value was 70.0%. Conclusion:Acute appendicitis in children under five years old is more likely to progress to CA if the duration of symptoms>23.5 h, the level of C-reactive protein is increased, and the abdominal muscle tension is accompanied.The clinical prediction model of CA constructed by common clinical information in pediatric clinics has good prediction efficiency, which provides a simple and feasible reference method for clinicians to distinguish CA from uncomplicated appendicitis.