Table 3 Input features to the EGNN architecture
From: Geometric deep learning improves generalizability of MHC-bound peptide predictions
Feature and shape and type | Description |
|---|---|
NODE FEATURES | |
res_type [1], int | Index of node residue type. |
pos [3], float | The xyz coordinates of the residue C-alpha. |
entity [1], bool | Boolean indicating whether the node is the peptide (1) or the protein (0). Used during pooling to identify which residues outputs to sum together (i.e. the ones with entity=1, corresponding to the peptide). |
EDGE FEATURES | |
same_chain [1], bool | Boolean indicating whether the edge connects nodes belonging to the same chain (1) or separate chains (0). |
