Closed Sulstice closed 1 year ago
Current models only support IUPAC name translations. If you have enough data you could retrain the model for common chemical names.
If the data is open and in public domain I could look into building a model for this.
So far the data is stored here and is a blend of IUPAC and common chemical names. Some of the names didn't have a common name root. It's still an ongoing curation (will always be) but I am curious as to see what would happen.
I also don't mind building a model if you teach me what to do! We can maybe collaborate?
The amount of data you have shared is not enough for training such a model. And it should only contain common names not a mixture of both. If you could get only clean names of more than 10, 000 we could fine-tune the current model and then see how we could proceed further.
@Kohulan Cool, I have a plan for this so hang tight. I can update you soon.
Hello,
Is it possible to do a SMILES to Common Chemical Name as well as to IUPAC as well? I have the data already available in the form of a name to SMILES directly? Is that possible.
I will definitely build a connector to this. Been playing with a bit as well. Really like what you have done this is so awesome.