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. Also contains .json showing the parameters used in cleaning and .log showing 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. We also included the predictions made by the trained Molecular Transformer on the test set so you can verify our results.Paper: https://chemrxiv.org/engage/chemrxiv/article-details/64ca5d3e4a3f7d0c0d78ca42Code: 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.