Objective:To analyze the mechanism of Danpi-Chishao in treatment of sepsis based on network pharmacology.Methods:The corresponding targets of Danpi-Chishao and sepsis were carried out through TCMSP database, OMIM database and Genecards database. Cystoscope 3.8.2 software was used to construct the " Chinese medicine-active components-target-disease" network diagram. Gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analysis were carried out by DAVID database. Weisheng cloud platform was used to draw bubble map.Results:A total of 36 effective components of Danpi-Chishao was obtained, mainly including quercetin, kaempferol, baicalin, β-sitosterol, stigmasterol, paeoniflorin and so on. There were 96 potential common key targets between Danpi-Chishao and sepsis, such as prostaglandin-endoperoxide synthase 2 (PTGS2), transcription factor p65 (RELA), phosphatidylinositol-4, 5-bisphosphate 3-kinase catalytic subunit gamma (PIK3CG), B-cell lymphoma 2 (BCL-2)-associated X (BAX), BCL-2, Caspase-3 (CASP3) with a degree value>4.9. The result of protein-protein interaction (PPI) network analysis showed that there were 10 important target proteins, including alpha serine/threonine-protein kinase (AKT1), interleukin-6 (IL-6), tumor necrosis factor (TNF), interleukin-1β (IL-1β), vascular endothelial growth factor A (VEGFA), cellular tumor antigen p53 (TP53), matrix metalloproteinase-9 (MMP9), CASP3, PTGS2, C-C motif chemokine ligand 2 (CCL2). The pathways obtained by GO and KEGG enrichment analysis included atherosclerosis pathway, advanced glycation end products (AGE)-receptor for advanced glycation end products (RAGE) signal pathway, cancer pathway, tumor necrosis factor signal pathway, hypoxia-inducible factor (HIF) signal pathway, IL-17 signal pathway and other pathway.Conclusions:The mechanism of the intervention effect of Danpi-Chishao on sepsis may be that the active components such as quercetin, kaempferol, paeoniflorin act on target proteins such as PTGS2, RELA, PIK3CG, BAX, BCL2, CASP3, and through TNF-related signal pathway, HIF-1 signal pathway, IL-17 signal pathway, etc. Nonetheless, the conclusion needs further experimental verification.

Objective:To propose a deep learning network model 2D-PE-GAN to automatically delineate the target area of nasopharyngeal carcinoma and improve the efficiency of target area delineation.Methods:The model adopted the architecture of generative adversarial networks which used a UNet similar structure as the generator, and 2D-PE-block was added after each layer of convolution operation of the generator to improve the accuracy of delineation. The experimental data included CT images from 130 cases of nasopharyngeal carcinoma. The images were preprocessed before model training. In addition, three models of UNet, GAN, and GAN with an attention mechanism were compared, and Dice similarity coefficient, Hausdorff distance, accuracy, Matthews correlation coefficient, Jaccard distance were employed to evaluate network performance.Results:Compared with UNet, GAN and GAN with the attention mechanism, the average Dice similarity coefficient of 2D-PE-GAN network segmentation of CTV was increased by 26%, 4% and 2%. The average Dice similarity coefficient of GTV segmentation was increased by 21%, 4%, 2%, respectively. Compared with the GAN network with the attention mechanism, the parameters and time of 2D-PE-GAN were reduced by 0.16% and 18%, respectively.Conclusions:Compared with the above three networks, 2D-PE-GAN network can increase the segmentation accuracy of nasopharyngeal carcinoma target area delineation. At the same time, compared with the attention mechanism with similar reasons, 2D-PE-GAN network can reduce the occupation of computing resources when the segmentation accuracy is not much different.