Open connorcoley opened 1 year ago
This dataset is getting close to submission now. There is now a basic dataset (39k reactions) which passes essential validation checks. There are however some chemical inputs (including solvent) which are only defined by name (no SMILES). I'm going to attempt to add in the SMILES for the most common recurring chemicals so rdkit can index them.
https://chemrxiv.org/engage/chemrxiv/article-details/63581205aca1989b92e4d77c
Status: data will be released upon publication