EDN
Protein Model Quality Assessment
EDN is a deep learning method for protein model quality assessment. Its underlying architecture is a rotation-equivariant, hierarchical neural network
that was trained to predict the GDT-TS score for a given protein model. EDN was trained end-to-end on raw atomic coordinates and
does neither use physics-inspired energy terms nor rely on the availability of additional information (beyond the atomic structure of the individual protein model),
such as sequence alignments of multiple proteins.
In order to score protein models with EDN, please upload a single pdb file (containing multiple models) below.
Please do not refresh the website until the file upload (as indicated by the progress bar) is complete.
The results will be emailed to the address specified upon job completion.
Please email psuriana[at]stanford.edu or seismann[at]stanford.edu with respect to any questions.