EGNA_Readme

Readme

EGNA is a web server for accurate protein-ligand binding affinity prediction. An empirical neural network is designed to explore the interaction patterns between proteins and ligands. It was trained on the refined and general set of PDBbind 2016 and evaluated on the CASF-2016 and non-overlapping CSAR-HiQ. The results show that it outperforms the state-of-the-art scoring functions.

Result Page

Results will be shown in the result page when the job is finished. The example result page is shown in the figure below. The output is the pKd value (unit is Mol) of the input complex.

Q&A

1. How should I use EGNA?

First, you need to upload a PDB format file or paste the text which contains 3D coordinates of the protein; second, you need to upload an SDF or MOL2 format file or paste the text which contains 3D coordinates of the ligand; third, select the format of the ligand file; at last, you can input the email address which is used to receive the results.

2. How long will it take to generate the results?

Running time is mainly related to the time for running HHblits and other jobs in the queue. If there is no job in the queue, it may take about 10-20 min to get the result.