Dataset

OMol25_train_4M

Download Original Data Files 20.0 GB

Download Dataset Parquet Files 12.3 GB

Find on Hugging Face 🤗

Species content of dataset

Dataset viewer powered by Hugging Face

Name :

OMol25_train_4M

Extended ID :

OMol25_train_4M__Levine-Shuaibi-Spotte-Smith-Taylor-Hasyim-Michel-Batatia-Csanyi-Dzamba-Eastman-Frey-Fu-Gharakhanyan-Krishnapriyan-Rackers-Raja-Rizvi-Rosen-Ulissi-Vargas-Zitnick-Blau-Wood__DS_k8m3sm6ves4u_0

ColabFit ID :

DS_k8m3sm6ves4u_0

Files :

colabfitspec.json

Description :

The Train 4M set from OMol25 (~4 million structure training subset). From the dataset creator: OMol25 represents the largest high quality molecular DFT dataset spanning biomolecules, metal complexes, electrolytes, and community datasets. OMol25 was generated at the ω B97M-V/def2-TZVPD level of theory.

Authors :

Daniel S. Levine, Muhammed Shuaibi, Evan Walter Clark Spotte-Smith, Michael G. Taylor, Muhammad R. Hasyim, Kyle Michel, Ilyes Batatia, Gábor Csányi, Misko Dzamba, Peter Eastman, Nathan C. Frey, Xiang Fu, Vahe Gharakhanyan, Aditi S. Krishnapriyan, Joshua A. Rackers, Sanjeev Raja, Ammar Rizvi, Andrew S. Rosen, Zachary Ulissi, Santiago Vargas, C. Lawrence Zitnick, Samuel M. Blau, Brandon M. Wood

DOI :

10.60732/b6f9382a https://commons.datacite.org/doi.org/10.60732/b6f9382a https://doi.datacite.org/dois/10.60732%2Fb6f9382a https://doi.org/10.60732/b6f9382a Cite as: Levine, D. S., Shuaibi, M., Spotte-Smith, E. W. C., Taylor, M. G., Hasyim, M. R., Michel, K., Batatia, I., Csányi, G., Dzamba, M., Eastman, P., Frey, N. C., Fu, X., Gharakhanyan, V., Krishnapriyan, A. S., Rackers, J. A., Raja, S., Rizvi, A., Rosen, A. S., Ulissi, Z., Vargas, S., Zitnick, C. L., Blau, S. M., and Wood, B. M. "OMol25 train 4M." ColabFit, 2025. https://doi.org/10.60732/b6f9382a.
For other citation formats, see the DataCite Fabrica page for this dataset.

Num. Configurations :

3,986,754

Num. Atoms :

218,680,957

Downloads :

370

Calculated Property Types :

atomic_forces energy

Elements :

Ag (0.01%) Al (0.01%) Ar (0.0%) As (0.04%) Au (0.01%) B (0.1%) Ba (0.01%) Be (0.01%) Bi (0.01%) Br (0.29%) C (31.54%) Ca (0.01%) Cd (0.01%) Ce (0.0%) Cl (0.66%) Co (0.01%) Cr (0.01%) Cs (0.01%) Cu (0.01%) Dy (0.0%) Er (0.0%) Eu (0.0%) F (1.09%) Fe (0.01%) Ga (0.01%) Gd (0.0%) Ge (0.02%) H (49.54%) He (0.0%) Hf (0.01%) Hg (0.01%) Ho (0.0%) I (0.11%) In (0.01%) Ir (0.02%) K (0.01%) Kr (0.0%) La (0.0%) Li (0.02%) Lu (0.0%) Mg (0.01%) Mn (0.01%) Mo (0.01%) N (5.81%) Na (0.01%) Nb (0.0%) Nd (0.0%) Ne (0.0%) Ni (0.01%) O (8.53%) Os (0.01%) P (0.5%) Pb (0.01%) Pd (0.02%) Pm (0.0%) Pr (0.0%) Pt (0.02%) Rb (0.01%) Re (0.01%) Rh (0.01%) Ru (0.02%) S (0.98%) Sb (0.03%) Sc (0.01%) Se (0.07%) Si (0.13%) Sm (0.0%) Sn (0.01%) Sr (0.01%) Ta (0.01%) Tb (0.0%) Tc (0.01%) Te (0.03%) Ti (0.02%) Tl (0.01%) Tm (0.0%) V (0.02%) W (0.01%) Xe (0.0%) Y (0.01%) Yb (0.0%) Zn (0.01%) Zr (0.01%)

Methods :

DFT-ωB97M-V

Software :

ORCA

Publication Link :

https://doi.org/10.48550/arXiv.2505.08762

Data Source Link :

https://huggingface.co/facebook/OMol25

Configuration Sets by Name :

Configuration Sets by ID :

Name: OMol25_train_4M Extended ID: OMol25_train_4M__Levine-Shuaibi-Spotte-Smith-Taylor-Hasyim-Michel-Batatia-Csanyi-Dzamba-Eastman-Frey-Fu-Gharakhanyan-Krishnapriyan-Rackers-Raja-Rizvi-Rosen-Ulissi-Vargas-Zitnick-Blau-Wood__DS_k8m3sm6ves4u_0 Description: The Train 4M set from OMol25 (~4 million structure training subset). From the dataset creator: OMol25 represents the largest high quality molecular DFT dataset spanning biomolecules, metal complexes, electrolytes, and community datasets. OMol25 was generated at the ω B97M-V/def2-TZVPD level of theory. Authors: Daniel S. Levine Muhammed Shuaibi Evan Walter Clark Spotte-Smith Michael G. Taylor Muhammad R. Hasyim Kyle Michel Ilyes Batatia Gábor Csányi Misko Dzamba Peter Eastman Nathan C. Frey Xiang Fu Vahe Gharakhanyan Aditi S. Krishnapriyan Joshua A. Rackers Sanjeev Raja Ammar Rizvi Andrew S. Rosen Zachary Ulissi Santiago Vargas C. Lawrence Zitnick Samuel M. Blau Brandon M. Wood DOI: 10.60732/b6f9382a Calculated Property Types: atomic_forces energy Elements: Ag (0.01%) Al (0.01%) Ar (0.0%) As (0.04%) Au (0.01%) B (0.1%) Ba (0.01%) Be (0.01%) Bi (0.01%) Br (0.29%) C (31.54%) Ca (0.01%) Cd (0.01%) Ce (0.0%) Cl (0.66%) Co (0.01%) Cr (0.01%) Cs (0.01%) Cu (0.01%) Dy (0.0%) Er (0.0%) Eu (0.0%) F (1.09%) Fe (0.01%) Ga (0.01%) Gd (0.0%) Ge (0.02%) H (49.54%) He (0.0%) Hf (0.01%) Hg (0.01%) Ho (0.0%) I (0.11%) In (0.01%) Ir (0.02%) K (0.01%) Kr (0.0%) La (0.0%) Li (0.02%) Lu (0.0%) Mg (0.01%) Mn (0.01%) Mo (0.01%) N (5.81%) Na (0.01%) Nb (0.0%) Nd (0.0%) Ne (0.0%) Ni (0.01%) O (8.53%) Os (0.01%) P (0.5%) Pb (0.01%) Pd (0.02%) Pm (0.0%) Pr (0.0%) Pt (0.02%) Rb (0.01%) Re (0.01%) Rh (0.01%) Ru (0.02%) S (0.98%) Sb (0.03%) Sc (0.01%) Se (0.07%) Si (0.13%) Sm (0.0%) Sn (0.01%) Sr (0.01%) Ta (0.01%) Tb (0.0%) Tc (0.01%) Te (0.03%) Ti (0.02%) Tl (0.01%) Tm (0.0%) V (0.02%) W (0.01%) Xe (0.0%) Y (0.01%) Yb (0.0%) Zn (0.01%) Zr (0.01%) Methods: DFT-ωB97M-V Software: ORCA Number of Configurations: 3,986,754 Number of Atoms: 218,680,957 Publication Link: https://doi.org/10.48550/arXiv.2505.08762 Data Source Link: https://huggingface.co/facebook/OMol25

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.