ORDerly supplementary datasets

Supplementary datasets used in ORDerly (i.e. the non-benchmark datasets)Condition prediction datasets: Contains parquet files for each of the four flavours of ORDerly-condition datasets that we used in the ORDerly paper. Condition prediction datasets config: Contains the .log and .json files showing the parameters used in cleaning and the impact on dataset size after each cleaning step.Transformer datasets: Contains plain txt files with the six transformer-ready datasets that were used for training/testing with Molecular Transformer. Non uspto data: Contains the datasets created with ORDerly from non-USPTO data in ORD. These datasets were used as test sets for forward prediction and retrosynthesis prediction.Preprint: https://chemrxiv.org/engage/chemrxiv/article-details/64ca5d3e4a3f7d0c0d78ca42Neurips workshop paper: https://openreview.net/forum?id=R8FQMsECISCode: https://github.com/sustainable-processes/orderlyThe ORDerly benchmark datasets can be found here: https://figshare.com/articles/dataset/ORDerly_chemical_reactions_condition_benchmarks/23298467Please feel free to contact me, Daniel Wigh, at [e-mail] in case of any questions.