Reaction Mechanisms for Training Reactron Dataset (3.5M)

A dataset containing reaction mechanisms designed for training the Reactron model, a tool for predicting reaction outcomes.

Acknowledgement: Reaction mechanisms of 226,669 reactions in USPTO-480K reaction dataset1 originally extracted from US patents (USPTO) reaction dataset2 generated by MechFinder3 to train Reactron. This dataset includes approximately 2.85 million mechanistic steps. Reference: 1.Jin, W., Coley, C., Barzilay, R., & Jaakkola, T. (2017). Predicting organic reaction outcomes with weisfeiler-lehman network. Advances in neural information processing systems, 30. Lowe, Daniel (2017). Chemical reactions from US patents (1976-Sep2016). figshare. Dataset. https://doi.org/10.6084/m9.figshare.5104873.v1 Chen, S., Babazade, R., Kim, T., Han, S., & Jung, Y. (2024). A large-scale reaction dataset of mechanistic pathways of organic reactions. Scientific Data, 11(1), 863.