buildAGL-Score Input

file_upload Select file Change  
file_upload Select file Change  
This is optional. A message will be sent to your emal when your job is done.


1 Duc D Nguyen and Guo-Wei Wei, AGL-Score: Algebraic Graph Learning Score for Protein-Ligand Binding Scoring, Ranking, Docking, and Screening, Journal of Chemical Information and Modeling, 59, 3291-3304, (2019) Read 2 Duc D. Nguyen and Guo-Wei Wei, Algebraic graph learning of protein-ligand binding affinity (2018) Read

local_libraryTraining Datasets

Below are the datasets used to train AGL-Score for docking and screening power assessments

  • Docking Power Dataset: Poses folder contains the structures for training data, INDEX folder consists of labels of the corresponding structures in Poses folder
  • Screening Power Dataset: Poses folder contains the computer-generated structures for training data and test data, INDEX folder consists of predicted energies of the training data in the Poses folder

perm_contact_calendarContact Information

Contact us : weig at
Webmaster : ddnguyen at

layersAGL-Score's Flow Chart


extensionUser guide

AGL-Score is graph theory based scoring function combined with an advance machine learning algorithm for protein-ligand binding scoring, ranking, docking, and screening

Your INPUT includes
  • Protein in PDB format
  • Ligand in SDF or MOL2 format

Your OUTPUT includes
  • Predicted binding energy in kcal/mol