Fig. 1
From: Drug repositioning of herbal compounds via a machine-learning approach
Overview of the proposed work. The training dataset was obtained from a previous study, and the drug and disease property data was retrieved from each database. Using the property information, similarity scores were calculated and combined to represent drug-disease associations. The drug-disease associations and similarity scores were used to construct a prediction model through cross-validation and external validation. Finally, the best performing model was applied to predict the repositioning candidates from the herbal compounds