This paper studied the correlation between traditional Chinese medicine (TCM) prescription and disease based on machine learning.This paper selected TCM literature abstract data in the TCM category of the China National Knowledge Infrastructure (CNKI) database by crawler technology.After data cleaning,lexicon building,word segmentation and other related basic pre-treatment work,it uses natural language processing technique to extract the feature of the web text data,constructs the Support Vector Machine (SVM) classification model,and extracts the relation between TCM prescription and disease.The results showed that among 1073581 abstracts,204780 sentences,which included both TCM prescription and the disease according to dictionaries,were filtered.The SVM classification model whose feature is constructed by constituency parser is in a better accuracy,which achieved 87％.Applying the SVM model in filtered sentences,this study obtained the relation triples between TCM prescription and the disease.It was concluded that by using the method of machine learning to extract relation on abstract data from the CNKI database,the extracted relation triples of TCM prescription and disease will take a positive effect on the research of disease treatment by TCM prescription.

Objective: To study the role of rs 12145833 polymorphism of SDCCAG 8 gene in the intervention of childhood obesity, so as to provide scientific basis for formulating personalized intervention measures based on genetic background in children with obesity. Methods: From September 2018 to June 2019, a total of 393 children aged 8-10 years in Beijing were enrolled in a cluster randomized controlled trial. Eight schools were randomly allocated into intervention group and control group at a ratio of 1∶1. Saliva DNA samples were collected to detect rs 12145833 polymorphism of SDCCAG 8 gene. The intervention group received a comprehensive intervention, while the control group received usual practice. Intervention measures included diet improvement, sports, school amd family sport. The obesity related indicators were measured at baseline and after the end of intervention 1 academic year. Multiple linear regression and Logistic regression were used to analyze the interaction between genes and intervention on obesity indicators. Results: In the intervention group, children with TT genotype of rs 12145833 of the SDCCAG 8 gene had less increase in systolic( β=4.56, 95%CI=1.84-7.28, P <0.01) and diastolic blood pressure( β=2.59, 95%CI=0.45-4.73, P <0.05) than those with GT and GG genotypes. In the control group, the systolic blood pressure of children with TT genotype increased more than those with GT and GG genotype( β=-2.86, 95%CI=-5.63--0.83, P <0.05). There was an interaction between rs 12145833 polymorphism of SDCCAG 8 gene and intervention on systolic blood pressure, diastolic blood pressure and body fat percentage in children( P <0.05). Conclusion Children with TT genotype of rs 12145833 in the SDCCAG 8 gene are more sensitive to obesity intervention than those with GG and GT genotypes, especially in the improvement of systolic blood pressure, diastolic blood pressure and body fat percentage. Further trials to study the role of rs 12145833 polymorphism of SDCCAG 8 gene in the intervention of childhood obesity among different ethnic populations are needed.