Fig. 3: Distribution of the physicochemical properties for the ChEMBL training set and molecules generated by GCPG module with and without the gating condition mechanism. | Communications Biology

Fig. 3: Distribution of the physicochemical properties for the ChEMBL training set and molecules generated by GCPG module with and without the gating condition mechanism.

From: A structure-based framework for selective inhibitor design and optimization

Fig. 3

It Includes synthetic accessibility score (SAS, 0–10 range); Molecule weight (MW); number of rotatable bonds (NRB); quantitative estimate of druglikeness (QED), the Wildman–Crippen partition coefficient (LogP) and topological polar surface area (TPSA). The GCPG generated molecules include a total of 100,000 molecules from random pharmacophore hypotheses and the ChEMBL molecules comprise 100,000 molecules randomly sampled from the ChEMBL training datasets. In the gating condition mechanism, SAS is set to 2, MW is set to 400, QED is set to 0.6, and LogP is set to 3, with no restrictions on NRB and TPSA.

Back to article page