Open AccessGenerating property-matched decoy molecules using deep learning
Author(s) -
Fergus Imrie,
A.R. Bradley,
Charlotte M. Deane
Publication year - 2021
Publication title -
bioinformatics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 3.599
H-Index - 390
eISSN - 1367-4811
pISSN - 1367-4803
DOI - 10.1093/bioinformatics/btab080
Subject(s) - decoy , computer science , virtual screening , artificial intelligence , benchmarking , machine learning , concatenation (mathematics) , generalization , exploit , rendering (computer graphics) , data mining , bioinformatics , computer security , mathematics , chemistry , drug discovery , mathematical analysis , biochemistry , receptor , marketing , combinatorics , business , biology
An essential step in the development of virtual screening methods is the use of established sets of actives and decoys for benchmarking and training. However, the decoy molecules in commonly used sets are biased meaning that methods often exploit these biases to separate actives and decoys, and do not necessarily learn to perform molecular recognition. This fundamental issue prevents generalization and hinders virtual screening method development.