RESUMO
@#In recent years, artificial intelligence (AI) has been widely applied in the field of drug discovery and development.In particular, natural language processing technology has been significantly improved after the emergence of the pre-training model.On this basis, the introduction of graph neural network has also made drug development more accurate and efficient.In order to help drug developers more systematically and comprehensively understand the application of artificial intelligence in drug discovery, this article introduces cutting-edge algorithms in AI, and elaborates on the various applications of AI in drug development, including drug small molecule design, virtual screening, drug repurposing, and drug property prediction, finally discusses the opportunities and challenges of AI in future drug development.
RESUMO
Objective:To investigate the efficacy and safety of a novel modified Blumgart pancreaticojejunostomy in laparoscopic pancreaticoduodenectomy (LPD).Methods:Between May 2021 and January 2022, 13 successive cases from Lihuili Hospital Affiliated to Ningbo University who underwent LPD were enrolled in this retrospective study. The study retrospectively analyzed the demographic characteristics, perioperative outcomes, and pathological results of these cases.Results:Twenty patients underwent LPD success-fully and one required conversion to open surgery. The operative time was (308.6 ± 61.7) min. The duration for PJ was (26.7 ± 4.3) min. The estimated blood loss was (188.1 ± 94.2) ml. The postoperative hospital stay was (14.2 ± 3.5) d. There was one case of biochemical leakage and no case of grade B or grade C pancreatic fistula.Conclusions:The new method is safe, simple and feasible. The novel method could reduce the incidence of pancreatic fistula and other complications after LPD.
RESUMO
<p><b>OBJECTIVE</b>To investigate the effect of GEPT extracts on spatial learning ability of the APPV717I transgenic mice at the early stage of dementia and its possible mechanism.</p><p><b>METHOD</b>Thirty APPV717I transgenic mice were randomly divided into three GEPT groups by intragastric administration at doses of 0.075, 0.15, 0.3 g x kg(-1) x d(-1), and a donepezil group by intragastric administration of 0.92 mg x kg(-1) x d(-1), a APPV717I transgenic model group and a normal group by intragastric administration of distilled water. A four-month treatment regimen with GEPT extracts was administered to APPV717I transgenic mice. Results showed that Spatial memory ability was measured in Morris water maze. The total area covered by shank1 and integral optical density in CA1 subfield within the hippocampus were determined using immunohistochemical stains and Image-Pro plus analysis. The ultrastructure of synapses in the hippocampal CA1 region was observed by electronic microscope.</p><p><b>RESULT</b>After a four-month of GEPT treatment regimen, the mean escape latency period were significantly shortened (P < 0.05), and the target quadrant search time were significantly increased (P < 0.05) compared to the APPV717I transgenic model mice. There was a significant higher level in the expression of shank1 detected in the hippocampal CA1 area of APPV717I transgenic mice associated with an increase in the number of synapses treated with GEPT than the levels in the APPV717I transgenic model mice alone. The total area of positive cells covered by shank1 and their integral optical density in the hippocampal CA1 area of the APPV717I transgenic mice treated with GEPT were significantly increased more than those of the APPV717I transgenic model mice.</p><p><b>CONCLUSION</b>GEPT extracts can obviously improve the spatial memory ability of APPV717I transgenic mice at the early stage of dementia through enhancing the number of synapses and the expression of shank1, and this might lead to development of novel treatment therapies for the memory loss associated with AD.</p>