MolAtlas dataset

Molecular property dataset calculated for MolAtlas This dataset contains molecular properties in GDB calculated for constructing the MolAtlas, a visualization framework for molecular property distributions. Detailed descriptions of the computational methods and dataset construction can be found in the following paper and repository: MolAtlas: a visualization framework for molecular property distributions to guide functional molecule development.ChemRxiv, 27 August 2025.DOI: https://doi.org/10.26434/chemrxiv-2025-lm0fz GitHub repository:https://github.com/molecule-generator-collection/MolAtlas Data contents and usage The dataset is provided as Python pickle files and can be used as follows: import pandas as pdmolatlas_df = pd.read_pickle("GDB_wFL_df_curated.pkl")molatlas_df.head() The column names in the dataset foundamentally correspond to the property labels defined in the paper.