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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

One key task in virtual screening is to accurately predict the bindingaffinity ($\triangle$$G$) of protein-ligand complexes. Recently, deep learning(DL) has significantly increased the predicting accuracy of scoring functionsdue to the extraordinary ability of DL to extract useful features from rawdata. Nevertheless, more efforts still need to be paid in many aspects, for theaim of increasing prediction accuracy and decreasing computational cost. Inthis study, we proposed a simple scoring function (called OnionNet-2) based onconvolutional neural network to predict $\triangle$$G$. The protein-ligandinteractions are characterized by the number of contacts between proteinresidues and ligand atoms in multiple distance shells. Compared to publishedmodels, the efficacy of OnionNet-2 is demonstrated to be the best for twowidely used datasets CASF-2016 and CASF-2013 benchmarks. The OnionNet-2 modelwas further verified by non-experimental decoy structures from docking programand the CSAR NRC-HiQ data set (a high-quality data set provided by CSAR), whichshowed great success. Thus, our study provides a simple but efficient scoringfunction for predicting protein-ligand binding free energy.

OnionNet-2: A Convolutional Neural Network Model for Predicting Protein-Ligand Binding Affinity based on Residue-Atom Contacting Shells