-
|
Hi, Thank you so much for sharing such great code! I have a question regarding Link-invent. In the paper, it is mentioned that the generative model can not handle P atom(Phosphorus) and when actually calculating it, generation was skipped when a fragment containing P was used as input SMILES. If I want to perform sampling on fragments containing P, would I have no other option but to rebuild the model? Or are there any tips like how to give the input SMILES? Thank you in advance. |
Beta Was this translation helpful? Give feedback.
Replies: 2 comments 1 reply
-
|
Hi, welcome to the REINVENT community and many thanks for your interest in the software! If you want to do work with additional elements (tokens) you would need to retrain the prior. There is currently no way to extend an exisiting prior's vocabulary. Many thanks, |
Beta Was this translation helpful? Give feedback.
-
|
Hi Hannes, Thank you very much for your prompt response and for clarifying the situation. I understand that I would need to retrain the prior to work with additional elements such as phosphorus. Given the challenge of rebuilding the model, as discussed in the following URL, I would greatly appreciate any guidance or tips you could share on how to best approach the preprocessing and training steps for this task. Thank you again for your support and assistance! |
Beta Was this translation helpful? Give feedback.
-
|
As this is Linkinvent @jiazhenhe may have more insight into training a new prior. |
Beta Was this translation helpful? Give feedback.
Hi,
welcome to the REINVENT community and many thanks for your interest in the software!
If you want to do work with additional elements (tokens) you would need to retrain the prior. There is currently no way to extend an exisiting prior's vocabulary.
Many thanks,
Hannes.