Fig. 3From: Identification of novel small molecule inhibitors for solute carrier SGLT1 using proteochemometric modelingChemical space of the selected compounds compared to the training and screening datasets. a The Diverse set (yellow) and Cluster set (green) are displayed compared to the training (orange and red) and Enamine screening set (blue). The Enamine set is represented by a random selection of 20,000 out of the total of 1,815,674 compounds (~ 1%) in the screening set to limit t-SNE calculation time. b The molecular weight and ALogP of the Diverse and Cluster set compared to the training and screening setsBack to article page