Topology-Based and Conformation-Based Decoys Database: An Unbiased Online Database for Training and Benchmarking Machine-Learning Scoring Functions

摘要

Machine-learning-basedscoring functions (MLSFs) have gained attentionfor their potential to improve accuracy in binding affinity predictionand structure-based virtual screening (SBVS) compared to classicalSFs. Developing accurate MLSFs for SBVS requires a large and unbiaseddataset that includes structurally diverse actives and decoys. Unfortunately,most datasets suffer from hidden biases and data insufficiency. Here,we developed topology-based and conformation-based decoys database(ToCoDDB). The biological targets and active ligands in ToCoDDB werecollected from scientific literature and established datasets. Thedecoys were generated and debiased by using conditional recurrentneural networks and molecular docking. ToCoDDB is presently the largestunbiased database with 2.4 million decoys encompassing 155 targets.The detailed information and performance benchmark for each targetare provided, which are beneficial for training and evaluating MLSFs.Moreover, the online decoys generation function of ToCoDDB furtherexpands its application range to any target. ToCoDDB is freely availableat http://cadd.zju.edu.cn/tocodecoy/.