QM_137k

This dataset, titled "QM_137k.parquet," originates from the supporting information of the publication "Regio-selectivity prediction with a machine-learned reaction representation and on-the-fly quantum mechanical descriptors" by Yanfei Guan et al., MIT. It includes preprocessed quantum mechanical descriptors for 137,000 molecules. The dataset has been modified to include the Conduction Dual Descriptor (CDD), calculated using Hirshfeld charges and Fukui indices. The original dataset is available at Figshare.