search

yuqianghan / editretro

Retrosynthesis Prediction with an Iterative String Editing Model
MIT License
10 stars 3 forks source link

Dead-loop problem #13

Open xxxlive opened 1 month ago

xxxlive commented 1 month ago

The Full data set contains some dirty data which causes the stuck problem in the preprocessing stage. For example product:[F:1][C:2]([C:3](=[O:4])[NH:15][O:16][C:3]([C:2]([F:1])([F:12])[F:13])=[O:4])([F:12])[F:13] contains duplicate atom map. This can lead to a dead-loop problem.

yuqianghan commented 1 month ago

Thank you for being interested in our work. We have updated the preprocess_data.py file with the -batch parameter to preprocess the datasets.