Xuewei Wang

A computational approach to botanical drug design by modeling quantitative composition-activity relationship.

Herbal medicine has been successfully applied in clinical therapeutics throughout the world. Following the concept of quantitative composition–activity relationship, the presented study proposes a computational strategy to predict bioactivity of herbal medicine and design new botanical drug. As a case, the quantitative relationship between chemical composition and decreasing cholesterol effect of Qi‐Xue‐Bing‐Zhi‐Fang, a widely used herbal medicine in China, was investigated. Quantitative composition–activity relationship models generated by multiple linear regression, artificial neural networks, and support vector regression exhibited different capabilities of predictive accuracy. Moreover, the proportion of two active components of Qi‐Xue‐Bing‐Zhi‐Fang was optimized based on the quantitative composition–activity relationship model to obtain new formulation. Validation experiments showed that the optimized herbal medicine has greater activity. The results indicate that the presented method is an efficient approach to botanical drug design.

Brief communication: A causal relationship discovery-based approach to identifying active components of herbal medicine

Herbal medicine is widely applied for clinical use in East Asia and other countries. However, unclear correlation between its complex chemical composition and bioactivity prevents its application in the West. In the present study, a stepwise causal adjacent relationship discovery algorithm has been developed to study correlation between composition and bioactivity of herbal medicine and identify active components from the complex mixture. This approach was successfully applied in discovering active constituents from mixed extracts of Radix Salviae miltiorrhizae and Cortex Moutan. Moreover, advantage of the present approach compared with bioassay-guided isolation was demonstrated by its application on a typical herbal drug. The current work offers a new way to virtually screen active components of herbal medicine, and it might be helpful to accelerate the process of new drug discovery from natural products.

A Causal Discovery Approach to Identifying Active Components of Herbal Medicine

In the present study, a stepwise causal adjacent relationship discovery (STEPCARD) method has been developed to identify active components of herbal medicine. The combination of two active components had been successfully recognized from a typical Chinese formulation. Animal experiments validated the computational result. It indicates current work might be helpful to accelerate the process of new drug discovery from herbal medicine

Empirical Study on Modeling Quantitative Composition- Activity Relationships in Chinese Herbal Medicine

Chinese herbal medicine (CHM) consists of up hundreds of chemical components, which have complex relationships with their bioactivities. Quantitatively modeling composition-activity relationships playing a crucial role in drug design from CHM. In this paper, principle component regression, partial least square regression and least square support vector machine were used to perform this task and exhibit high predictive precisions