EpiGraph

B cell epitope prediction by capturing spatial clustering property
of the epitopes using graph attention network


[Output Format]

1. .csv file is downloadable in the result page
2. Columns: PDB, Residue, Score, Epitope, RSA
3. PDB: Name of the PDB
4. Residue: Amino acid residue in PDB file
    *Format -> chain:amino_acid:residue_number (ex. A:PRO:51)
5. Score: Probability of model prediction
    *Scores are mostly near 0.1000, order could be more valuable.
6. Epitope: Binary classification result based on the threshold
    *threshold may not be optimal to individuals cases.
7. RSA: Relative Surface Accessibility; measure of surface exposure

Developed by Bioinformatics and Computational Biology Lab at KAIST (Korea Advanced Institute of Science and Technology)
Copyright 2023 Sungjin Choi and Dongsup Kim