Alzheimer's disease(AD)is gradually increasing in prevalence and the complexity of its pathogenesis has led to a lengthy process of developing therapeutic drugs with limited success.Faced with this challenge,we proposed using a state-of-the-art drug screening algorithm to identify potential therapeutic com-pounds for AD from traditional Chinese medicine formulas with strong empirical support.We developed four deep neural network(DNN)models for AD drugs screening at the disease and target levels.The AD model was trained with compounds labeled for AD activity to predict active compounds at the disease level,while the acetylcholinesterase(AChE),monoamine oxidase-A(MAO-A),and 5-hydroxytryptamine 6(5-HT6)models were trained for specific AD targets.All four models performed excellently and were used to identify potential AD agents in the Kaixinsan(KXS)formula.High-scoring compounds underwent experimental validation at the enzyme,cellular,and animal levels.Compounds like 2,4-di-tert-butyl-phenol and elemicin showed significant binding and inhibitory effects on AChE and MAO-A.Additionally,13 compounds,including α-asarone,penetrated the blood-brain barrier(BBB),indicating potential brain target binding,and eight compounds enhanced microglial β-amyloid phagocytosis,aiding in clearing AD pathological substances.Our results demonstrate the effectiveness of deep learning models in devel-oping AD therapies and provide a strong platform for AD drug discovery.

Objective To establish high performance liquid chromatography(HPLC)characteristic chromatograms of Xinqingduyin Granules(composed of Taraxaci Herba,Lonicerae Japonicae Flos,Chrysanthemi Indici Flos,etc.)and content determination of chicory acid and glycyrrhizic acid,and to optimize the preparation process of Xinqingduyin Granules.Methods Using the characteristic chromatograms of Xinqingduyin and the retention rate of chicory acid and glycyrrhizic acid as indexes,we carried out orthogonal experiment to optimize the extraction process of Xinqingduyin,and studied the concentration process.The molding process of Xinqingduyin Granules was conducted by screening the types and dosage of auxiliary materials,then three batches of pilot experiments were carried out.Results HPLC characteristic chromatograms of Xinqingshuyin Granules and the determination methods of chicory acid and glycyrrhizic acid were established.The optimal preparation technology was as follows:8 times amount of water was added,the drug was decocted for 3 times,with 1 hour per time.After the extract was concentrated under reduced pressure at 80℃,the appropriate amount of steviol glycoside and lactose was added into the extract and mixed.One-step granulation and packaging were adopted.The retention rates of chicoric acid and glycyrrhizic acid in the 3 batches of Xinqingduyin Granules,which were prepared on the pilot scale,were(54.56±1.63)%and(54.96±1.08)%,and the rate of finished product was(87.47±0.49)%,respectively.The quality is uniform,and the characteristic map of Xinqingduyin Granules showed high similarity with that of decoction prepared from the same batch of slices.Conclusion The optimized preparation technology is reasonable,feasible and reproducible.This preparation can be used to obtain the granule with similar materials of Xinqingduyin decoction.

Objective The reactivity of the PICC comprehensive maintenance model and the ward maintenance model was evaluated.The differences between these two models were compared so that the better maintenance model could be chosen for improving the service of the PICC comprehensive maintenance model. Methods Four hundred and fifty patients with the PICC catheter were chosen randomly.Three hundred and forty patients received the PICC comprehensive maintenance model (mainly in the out-patient department and combined with the network maintenance ).One hundred and ten patients received the ward maintenance model (mainly in the in-patient ward).The WHO reactivity questionnaires of health system were provided.The results of the valid questionnaires were calculated and analyzed.Results Four hundred and twenty-nine questionnaires (326 for the comprehensive maintenance model and 1 03 for the ward maintenance model)were collected.The reactivity evaluation of confidentiality,communication,autonomy,timeliness,basic facilities and selective dimension in the comprehensive maintenance model were significantly higher than those in the ward maintenance model (P <0.05).There were no significant differences in the reactivity evaluation of dignity and social support dimension between the two groups (P >0.05).Conclusions The reactivity evaluation of healthy system in the comprehensive maintenance model is higher.It can provide timely and convenient PICC service and meet the expects and demands of patients.

Objective: To evaluate the clinical performance of HPV genotyping with cytology for detecting cervical precancer among women attending co-testing. Methods: A total of 2 883 females who participated in cervical cancer screening program were recruited from Erdos in 2016. All the participants were tested by cytology and HPV genotyping. In 2017, women with abnormal cytology results or HPV positive were followed up. Pathological cervical intraepithelial neoplasia (CIN) 2+ was the study end-point. Clinical performance indexes were calculated, including sensitivity, specificity, positive predictive value, negative predictive value, referral rate and missed cases. Results: INNO-LiPA resulted in a detection rate of 18.87%(544/2 883) for the 14-type high risk HPV. HPV16 was the most common infectious genotype (4.06%), followed by HPV52 (3.61%), HPV51 (2.50%), HPV58 (1.98%), and HPV18 (1.56%). With more HPV genotypes added into the group, sensitivity increased and the specificity decreased. Addition of HPV16, 58, 33, 39, 52, 18, 31 for detection lead to the maximun value of area under the curve (AUC)=0.913 (95%CI: 0.882-0.944). Compared with traditional screening method by cytology, cotesting decreased the number of missed diagnosis. Meanwhile, the fifth method (co-testing: triage of women with HPV16/18+ , cytological minor abnormalities and HPV58, 33, 39, 52, 31+ or cytological high grade abnormalities) did not increase referral rate (8.99% vs. 8.71%, P=0.525), with five cases of missed diagnosis (sensitivity of 92.1% and specificity of 93.2%). Conclusions Co-testing with triage of women with HPV16/18+ , cytological minor abnormalities and HPV58, 33, 39, 52, 31+ or cytological high grade abnormalities would provide better clinical performance. In co-testing, triage of HPV16/18 was used in women with normal cytology; triage of HPV58, 33, 39, 52 and 31 was used in women with low-grade abnormal cytology; referral colposcopy was used in women with high-grade abnormal cytology, which would provide better clinical performance.