ABSTRACT
Xiaoshuan Tongluo formula is effective in treating mental retardation and speech astringency caused by cerebral thrombosis, but its mechanism remains unclear. In this investigation, by collecting the chemical constituents from Xiaoshuan Tongluo formula and the targets related to stroke, we obtained 1 251 constituents from the formula and 10 drug targets related with stroke. We established 18 prediction models of compound-target interaction for 10 stroke-related targets, using molecular docking method and machine learning methods includes Naive Bayesian and recursive partitioning based on the input of molecular fingerprints and molecular descriptors. Using these models, we predicted the active chemical constituents from Xiaoshuan Tongluo formula and their drug targets, 153 potential active constituents were discovered, 22 among them could interact with at least two drug targets related with stroke. On this basis, the chemical constituent-target network was constructed using network construction software, and then the important metabolic pathways of the targets were identified by using Gene-Ontology (GO) enrichment analysis, such as blood coagulation, positive regulation of angiogenesis, positive regulation of ion transport and so on. On this basis, a target-pathway network was constructed. In conclusion, using machine learning, molecular docking, virtual screening, data mining and network construction, this study explored and partially revealed the active chemical constituents and chemical constituent-target-pathway network action mechanism of Xiaoshuan Tongluo formula against stroke, which will provide important information for its further study.
ABSTRACT
Compound Yizhihao, consists of Radix isatidis, Folium isatidis, Artemisia rupestris, has a significant therapeutic effect on the treatment of influenza and fever. However, the mechanism of its action is still unclear. In this investigation, we collected the key target molecule of influenza disease and the chemical constituents of Compound Yizhihao, and developed Naïve Bayesian classification models based on the input molecular fingerprints and molecule descriptors. The built models were further applied to construct classifiers for predicting the effective constituents. We used the professional network-building software to build the constituent-target network and target-pathway network, which revealed the network pharmacology of the effective constituents in Compound Yizhihao. It will contribute to the further research of mechanism of Compound Yizhihao.