Skip to main content
Fig. 1 | BMC Bioinformatics

Fig. 1

From: Comparative assessment of strategies to identify similar ligand-binding pockets in proteins

Fig. 1

Procedure to compile the TOUGH-M1 dataset. Ligand-bound proteins selected from the Protein Data Bank are subjected to a series of filters to retain drug-like molecules and remove redundancy. Subsequently, binding pockets are computationally detected in representative complexes and the target-bound ligands are clustered to produce groups of chemically similar molecules. Finally, globally dissimilar protein pairs are identified either within each ligand cluster to create the Positive subset of TOUGH-M1, or between ligand clusters to compose the Negative subset of TOUGH-M1

Back to article page