Dataset for manuscript "Self-supervised Domain Adaptation of Protein Language Model Based Solely on Positive Enzyme-reaction Pairs"

This dataset is associated with the following article:Tomoya Okuno, Naoaki Ono, Md. Altaf-Ul-Amin, Shigehiko Kanaya, Self-supervised domain adaptation of protein language model based solely on positive enzyme-reaction pairs, Computational and Structural Biotechnology Journal, 27, 2025, 5441-5449, ISSN 2001-0370, https://doi.org/10.1016/j.csbj.2025.11.045. License Notice Data in `dataset/processed/kcat` partly includes materials licensed under the Creative Commons Attribution 4.0 International (CC BY 4.0). https://creativecommons.org/licenses/by/4.0/> Kroll, A., Rousset, Y., Hu, X.-P., Liebrand, N., & Lercher, M. (2022). Dataset for manuscript "Turnover number predictions for kinetically uncharacterized enzymes using machine and deep learning" [Data set]. Zenodo. https://doi.org/10.5281/zenodo.8367052 The file `dataset/raw//rxnaamapper_sequences_1024.txt` partly includes materials licensed under the Creative Commons Attribution 4.0 International (CC BY 4.0). https://creativecommons.org/licenses/by/4.0/> Yves Gaetan Nana Teukam, Loıc Kwate Dassi, Matteo Manica, Daniel Probst, Philippe Schwaller, & Teodoro Laino. (2023). Dataset of biocatalyzed reactions [Data set]. Zenodo. https://doi.org/10.5281/zenodo.7530180 Data in the dir `dataset/processed/embeding` and the files `dataset/processed/enzsrp_full_*` partly include materials licensed under Creative Commons Attribution 4.0 International (CC BY 4.0). https://creativecommons.org/licenses/by/4.0/ > The UniProt Consortium. (2023). UniProt: The Universal Protein Knowledgebase in 2023. Nucleic Acids Research, 51(D1), D523–D531. https://doi.org/10.1093/nar/gkac1052 > Lombardot, T., Morgat, A., Bansal, P., Coudert, E., Axelsen, K. B., Aimo, L., Hyka-Nouspikel, N., Gasteiger, E., Kerhornou, A., Neto, T. B., Ignatchenko, A., Redaschi, N., Bridge, A., & Xenarios, I. (2022). Rhea, the reaction knowledgebase in 2022. Nucleic Acids Research, 50(D1), D693–D700. https://doi.org/10.1093/nar/gkab1016 Data Modification Notice Due to licensing restrictions, reaction direction information was removed from the created EnzSRP dataset and the its processed files (“enzsrp_full_*”). Please refer to ‘make_public_version_enzsrp.py’ in https://github.com/motonuko/adaptplm for details of this deletion process. The execution log is in the zip file `make_public_version_enzsrp.log`. As a result, reaction directions originally from MetaCyc were unified to “left-to-right” direction and rows that became duplicates due to this normalization were deleted. For the purpose of reproducing the EnzSRP dataset, please refer to https://github.com/motonuko/enzsrp and rebuild the dataset from scratch, or refer to the 'reactions.dat' file provided in the MetaCyc distribution. In the latter case, you will need to map reactions with direction_source set to “MetaCyc” as left-to-right, right-to-left, or both.