You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am interested in your work. While I read the code, I found that during preprocessing, in the class get_graph_features_from_smi in data_utils.py.
The codes
# padding
for a_graph in a_graphs:
while len(a_graph) < 11: # OH MY GOODNESS... Fe can be bonded to 10...
a_graph.append(1e9)
for b_graph in b_graphs:
while len(b_graph) < 11: # OH MY GOODNESS... Fe can be bonded to 10...
b_graph.append(1e9)
I cannot understand why the atom and bond graphs needed to be padded to length 11. Could you tell me something about it?
Thanks a lot.
The text was updated successfully, but these errors were encountered:
@yippp As in the comment, during our own testing with cornor cases, we found some metal complexes can literally have up to 10 bonds (e.g. for Fe centers bonded to 10 ligands). Therefore we decided to pad to 11 just to be more robust.
I am interested in your work. While I read the code, I found that during preprocessing, in the class
get_graph_features_from_smi
indata_utils.py
.The codes
I cannot understand why the atom and bond graphs needed to be padded to length 11. Could you tell me something about it?
Thanks a lot.
The text was updated successfully, but these errors were encountered: