English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Structure-based virtual screening (SBVS) is a promising in silico techniquethat integrates computational methods into drug design. An extensively usedmethod in SBVS is molecular docking. However, the docking process can hardly becomputationally efficient and accurate simultaneously because classic mechanicsscoring function is used to approximate, but hardly reach, the quantummechanics precision in this method. In order to reduce the computational costof the protein-ligand scoring process and use data driven approach to boost thescoring function accuracy, we introduce a docking-based SBVS method and,furthermore, a deep learning non-docking-based method that is able to avoid thecomputational cost of the docking process. Then, we try to integrate these twomethods into an easy-to-use framework, ParaVS, that provides both choices forresearchers. Graph neural network (GNN) is employed in ParaVS, and we explainedhow our in-house GNN works and how to model ligands and molecular targets. Toverify our approaches, cross validation experiments are done on two datasets,an open dataset Directory of Useful Decoys: Enhanced (DUD.E) and an in-houseproprietary dataset without computational generated artificial decoys(NoDecoy). On DUD.E we achieved a state-of-the-art AUC of 0.981 and astate-of-the-art enrichment factor at 2% of 36.2; on NoDecoy we achieved an AUCof 0.974. We further finish inference of an open database, Enamine REALDatabase (RDB), that comprises over 1.36 billion molecules in 4050 core-hoursusing our ParaVS non-docking method (ParaVS-ND). The inference speed ofParaVS-ND is about 3.6e5 molecule / core-hour, while this number of aconventional docking-based method is around 20, which is about 16000 timesfaster. The experiments indicate that ParaVS is accurate, computationallyefficient and can be generalized to different molecular.

ParaVS: A Simple, Fast, Efficient and Flexible Graph Neural Network Framework for Structure-Based Virtual Screening