Skip to main content
. Author manuscript; available in PMC: 2017 Sep 3.
Published in final edited form as: J Comput Aided Mol Des. 2016 Sep 3;30(9):761–771. doi: 10.1007/s10822-016-9960-x

Fig. 1.

Fig. 1

The overall approach for our D3R submission. D3R ligands were ranked using a 2D QSAR approach trained using ChEMBL data (left side) or through a structure-based docking and scoring approach that used the DUD-E data set to train custom scoring functions for re-ranking poses docked using smina and the AutoDock Vina scoring function (right side).