Other Chemistry Commons^™

Hidden Bias In The Dud-E Dataset Leads To Misleading Performance Of Deep Learning In Structure-Based Virtual Screening, Lieyang Chen, Anthony Cruz, Steven Ramsey, Callum J. Dickson, Jose S. Duca, Viktor Hornak, David R. Koes, Tom Kurtzman

Publications and Research

Recently much effort has been invested in using convolutional neural network (CNN) models trained on 3D structural images of protein-ligand complexes to distinguish binding from non-binding ligands for virtual screening. However, the dearth of reliable protein-ligand x-ray structures and binding affinity data has required the use of constructed datasets for the training and evaluation of CNN molecular recognition models. Here, we outline various sources of bias in one such widely-used dataset, the Directory of Useful Decoys: Enhanced (DUDE). We have constructed and performed tests to investigate whether CNN models developed using DUD-E are properly learning the underlying physics of molecular …