Dataset

cG-SchNet


Download Original Data Files 17.2 MB
Download Dataset Parquet Files 13.5 MB
Download Dataset XYZ Files 5.0 MB
Find on Hugging Face 🤗

Species content of dataset


Dataset viewer powered by Hugging Face

Name :
cG-SchNet
Extended ID :
cG-SchNet__Gebauer-Gastegger-Hessmann-Muller-Schutt__DS_xzaglubh0trq_0
ColabFit ID :
DS_xzaglubh0trq_0
Files :
colabfitspec.json
Description :
Configurations from a cG-SchNet trained on a subset of the QM9dataset. Model was trained with the intention of providing molecules withspecified functional groups or motifs, relying on sampling of molecularfingerprint data. Relaxation data for the generated molecules is computedusing ORCA software. Configuration sets include raw data fromcG-SchNet-generated configurations, with models trained on several differenttypes of target data and DFT relaxation data as a separate configurationset. Includes approximately 80,000 configurations.
Authors :
Niklas W.A. Gebauer, Michael Gastegger, Stefaan S.P. Hessmann, Klaus-Robert Müller, Kristof T. Schütt
DOI :
10.60732/de8af6a2 https://commons.datacite.org/doi.org/10.60732/de8af6a2 https://doi.datacite.org/dois/10.60732%2Fde8af6a2 https://doi.org/10.60732/de8af6a2 Cite as: Gebauer, N. W., Gastegger, M., Hessmann, S. S., Müller, K., and Schütt, K. T. "cG-SchNet." ColabFit, 2023. https://doi.org/10.60732/de8af6a2.
For other citation formats, see the DataCite Fabrica page for this dataset.
Num. Configurations :
23,632
Num. Atoms :
418,729
Downloads :
29
Calculated Property Types :
cauchy_stress energy
Elements :
C (38.45%) F (0.05%) H (49.14%) N (3.21%) O (9.15%)
Methods :
IP-cgSchNet
Software :
ORCA
Publication Link :
https://doi.org/10.1038/s41467-022-28526-y
Data Source Link :
https://github.com/atomistic-machine-learning/cG-SchNet/
Configuration Sets by Name :
Configuration Sets by ID :
Report an issue with this dataset

No uploaded content is transferred in ownership from the original creators to ColabFit. All content is distributed under the license specified by its contributor who has stated that he or she has the authority to share it under the specified license.