Research progress and applications of strain analysis based on metagenomic data / 生物工程学报

Strain is the fundamental unit in microbial taxonomy. The functional diversity among strains has great influence on host phenotypes. With the development of microbiome research, knowing the composition and functional capacities of complex microbial communities at the strain level has become increasingly valuable in scientific research and clinical applications. This review introduces the principles of bioinformatics algorithms for strain analysis based on metagenomic data, the applications in microbiome research and directions of future development.

Influencing factors of the occurrence of propagated sensation effects at Zusanli (ST 36) based on artificial intelligence technology / 中国针灸

OBJECTIVE@#To explore the influencing factors of the occurrence of propagated sensation effects at Zusanli (ST 36) based on artificial intelligence technology.@*METHODS@#A total of 272 undergraduates and postgraduates of Guangzhou University of TCM were recruited. The basic information, including TCM constitution, body weight index (BMI), pulse, tongue and coating, face complexion, as well as the occurrence of propagated sensation effects at Zusanli (ST 36) with different acupuncture needles and techniques, were recorded. The repeated incremental pruning to produce error reduction (RIPPER) algorithm was applied to predict the results and summarize the rules of relevant factors.@*RESULTS@#① The propagated sensation effects were often observed in the subject with -deficiency constitution (55 cases in total, of them 1 case was misclassified). ② The propagated sensation effects were observed in the subject with balanced - constitution (39 cases in total, of them 0 case was misclassified). ③ The propagated sensation effects were observed in the subject with phlegm-damp constitution combined with thin tongue and white coating (31 cases in total, of them 8 cases were misclassified). ④ The propagated sensation effects were observed in the subject with phlegm-damp constitution combined with light tongue coating (7 cases in total, of them 2 cases were misclassified). ⑤ The propagated sensation effects were observed in all the subject with special constitution (6 cases in total, of them 0 cases were misclassified). ⑥ The propagated sensation effects were not observed in the subject with other constitution or the combination of constitution and symptoms (134 cases in total, of them 4 cases were misclassified). The accuracy rate of classification was 94.49%. The difference of acupuncture needles and techniques was not significant in propagated sensation effects (>0.05).@*CONCLUSION@#The TCM constitution may be the most essential factor in the occurrence of propagated sensation effects.

Analysis of the Influencing Factors of Post-stroke Depression: Based on Machine Learning / 中医杂志

Objective To determine the influencing factors of post-stroke depression by machine learning.Methods Stroke patients' medical records (688 cases eligible) were extracted from record system,including age,gender,pulse manifestation,complexion,tongue quality,fur,Chinese medicine intervention,body mass index (BMI),blood pressure,blood glucose,blood triglyceride,blood total cholesterol,smoking history,drinking history,depression family history,stroke lesion site in imaging,as well as the final depression judgment.Single rule algorithm (1R) was adopted to learn.The risk factors influencing post-stroke patients' depression in extracted information were determined.Then the cases collected were divided into the training dataset (500 cases) and the test dataset (188cases).Optimal discriminant results were obtained by random forest model.Results Single rule algorithm showed that the most important influencing factor of post-stroke depression was stroke lesion site.By computer speculation,stroke lesions in the frontal and temporal lobes were most prone to post-stroke depression.Basal ganglia,brain stem,cerebellum,medulla oblongata and occipital lobe lesions were less likely to cause depression.The accurate classification rate could amount to 88.95％ (612/688 cases).Random forest model determination was made in the former 500cases in the training dataset.The total correct rate of determining depression was 98.2％.The total correct rate of determination in 188 cases of the test dataset was 99.47％.Six hundred and eighty-eight patients' data were learnt by random forest model.The total correct rate was 98.84％.The importance measure results showed that top 3 important indexes of post-stroke depression were lesion site,Chinese medicine intervention and depression family history.Conclusion Patients with lesions in the frontal & temporal lobes and depression family history were most prone to post-stroke depression.