connorcoley / retrosim Goto Github PK

Hi,
GOOD Work!
I m trying to extract reaction templates of other chemical reactions via your code.
The chemical reactions were atom mapped, but not santisfy atomic conservation. Can it work correctly?

Hi, i was trying to use retrosim and I did not find info on what to install and also any example scripts for testing. Is there a way you can help me with that. I am working on a windows machine using conda. Thanks

If I have a SMILES string like:
COC(=O)[C@H](CCCCN)NC(=O)Nc1cc(OC)cc(C(C)(C)C)c1O,

How can I add atom indexs to convert the SMILES to string like :
[NH2:1][CH2:2][CH2:3][CH2:4][CH2:5][C@@H:6]([C:7]([O:8][CH3:9])=[O:10])[NH:11][C:12](=[O:13])[NH:14][c:15]1[cH:16][c:17]([O:18][CH3:19])[cH:20][c:21]([C:22]([CH3:23])([CH3:24])[CH3:25])[c:26]1[OH:27]

Also, if I have the latter one, how can I get the former one?
I have another dataset, and would like to run your model, I am not sure how to convert the data format.

For example, when using process_an_example, '[Cl:1][C:2]1=C:9[CH:8]=[CH:7]C:4=[CH:3]1>>[Cl:1][C:2]1=C:9[CH:8]=[CH:7]C:4=[CH:3]1' gives: [CH3;D1;+0:1]-[c:2]>>[CH2;D2;+0:1]-[c:2] which seems to be incorrect.

What "super_general=True" argument does exactly in the file retrosim/utils/generate_retro_templates.py in the function process_an_example.