Abstract: With the rapid development of artificial intelligence technology, small molecule generation models have emerged as a significant research direction in the field of drug discovery. These models, including Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and diffusion models, have proven to possess remarkable capabilities in optimizing drug properties and generating complex molecular structures. This article comprehensively analyzes the application of the aforementioned advanced technologies in the drug discovery process, demonstrating how they supplement and enhance traditional drug design methods. At the same time, it addresses the challenges facing current methods in terms of data quality, model complexity, computational cost, and generalization ability, with a prospect of future research directions.

Objective Trauma-induced coagulopathy (TIC)is an acute coagulopathy in which coagulation,fibrinolysis,and anticoagulant pathways are activated after trauma due to massive hemorrhage and tissue damage.TIC is caused by hypothermia,acidosis,blood dilution,hyperfusion,tissue injury,etc.To diagnose TIC,we mainly rely on traditional coagulation function analysis and thrombelastogram (TEG).At present,the key to treat TIC is quick hemostasis.The basic treatment procedure includes transfusion of packed red blood cells and fresh frozen plasma by appropriate proportion,and timely infusion of platelets and coagulant material so as to stabilize blood pressure and reconstruct the blood coagulation mechanism.In this paper,we reviewed recent advances in the pathophysiological and treatment of TIC in order to provide references for further research in related fields.

ObjectiveTo describe the characteristics of treatment outcomes of multidrug-resistant tuberculosis （MDR-TB） patients enrolled in second-line treatment in Shanghai from 2017 to 2018， and to analyze the influencing factors of treatment outcomes. MethodsTotally 182 MDR-TB patients were analyzed by using data collected from the China tuberculosis management information system， the hospital's electronic medical record information system， whole genome sequencing results and a questionnaire survey， and logistic regression analysis was used to analyze the factors affecting the success of treatment. ResultsIn 182 MDR-TB patients， the success rate of treatment was 65.4%， the loss to follow-up rate was 8.2%， the mortality rate was 4.9%， the unassessable rate was 13.7%， and the drug withdrawal rate was 7.7%. The factors affecting the success of treatment in MDR-TB patients included age （35‒ years old， OR=5.28， 95%CI： 1.58‒17.59， P=0.007； 55‒ years old， OR=16.30， 95%CI： 4.36‒60.92， P<0.001） and compliance to medication （OR=0.55， 95%CI： 0.42‒0.72， P<0.001）. ConclusionThe treatment success rate of MDR-TB patients in Shanghai from 2017 to 2018 is significantly higher than the average level in China. Older patients and patients with less compliant are at higher risk of adverse treatment outcomes.

ObjectiveTo obtain the status of latent tuberculosis infection （LTBI） among tuberculosis （TB）-related health-care workers （HCWs） in Shanghai， and to explore the risk factors related to TB infection. MethodsA multi-center cross-sectional study was conducted by recruiting medical workers from multiple designated TB hospitals， centers for disease control and prevention， and community health service centers in Shanghai. Each subject was required to complete a questionnaire and to provide a blood sample for TB infection test. Univariate and multivariate analysis ware made in order to find risk factors relating to TB infection. ResultsA total of 165 medical workers were recruited， and the proportion of TB infection was 16.36% （95%CI： 11.49%‒22.76%）. Multivariate logistic analysis showed that clinical doctors and nurses （adjusted OR=9.756， 95%CI： 1.790‒53.188）， laboratory staffs （adjusted OR=78.975， 95%CI： 8.749‒712.918）， and nursing and cleaning workers （adjusted OR=89.920， 95%CI： 3.111‒2 598.930） had higher risk of TB infection. ConclusionThe overall LTBI prevalence among TB-related HCWs is low. However， working as doctors， nurses， laboratory staffs， nursing workers and cleaning workers are risk factors of TB infection. TB-related HCWs who work at hospitals are at risk of TB infection comparing to medical staffs who work outside hospitals.