GEOM-Drugs: Energy-Annotated Conformer Ensembles for Drug-Like Molecules (SDF)
- Provider
- Axelrod and Gomez-Bombarelli (MIT); mirror by raulsofia
- License
- CC0-1.0 (source)
- Size
- 20 files
- Format
- CSV (in sampled files)
- Stored at
- Hugging Face (https://huggingface.co/datasets/raulsofia/geom_drugs)
- Access
- Free and public. No account with the data provider is needed.
- Category
- Chemistry & Materials
- Source
- https://doi.org/10.1038/s41597-022-01288-4
About GEOM-Drugs: Energy-Annotated Conformer Ensembles for Drug-Like Molecules (SDF)
The drug-like subset of GEOM (Geometric Ensemble Of Molecules) from the Gomez-Bombarelli group at MIT: conformer ensembles of about 300,000 drug-like molecules with associated experimental data, generated with CREST metadynamics at the semi-empirical GFN2-xTB level, with conformer energies and Boltzmann statistical weights. This mirror packages the conformers and SMILES as SDF and text files in two versions: allconfs/ with every available conformer and 5confs/ with at most five per molecule. Each holds an unsplit *_confs.sdf, *_counts.csv (conformers per SMILES) and *_smiles.smi, plus an 80/20 train/test split made on unique SMILES so that no molecule appears in both; about 73 GB in total (measured 2026-11-15). Read with RDKit SDMolSupplier. GEOM-Drugs is the standard benchmark for 3D molecular generation and conformer generation models (EDM, GeoDiff, Torsional Diffusion, MiDi). The original GEOM release on Harvard Dataverse (doi:10.7910/DVN/JNGTDF) is CC0-1.0; cite Axelrod and Gomez-Bombarelli, Scientific Data 9, 185 (2022).
How to load this dataset in Python
import pandas as pd
df = pd.read_csv("hf://datasets/raulsofia/geom_drugs/5confs/5confs_counts.csv")
df.head()Data structure
File types in sampled files: CSV
Files
Example file: 5confs/5confs_counts.csv
Analyze this dataset without downloading it
On Scigantic, GEOM-Drugs: Energy-Annotated Conformer Ensembles for Drug-Like Molecules (SDF) opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.
This page is also available as Markdown and as JSON.
Related Chemistry & Materials datasets
- QM9 C7H10O2 Constitutional Isomers: 6,095 Molecules at G4MP2 (Ramakrishnan et al. 2014, figshare), ColabFit Conversion
- Alexandria Materials Database Snapshot: 5.07 Million DFT Crystal Entries (pymatgen Parquet)
- Open Catalyst 2025 (OC25) Validation Split: Solid-Liquid Interface DFT, ColabFit Conversion
- SN2 Reactions of Methyl Halides with Halide Anions (DSD-BLYP-D3), ColabFit Conversion
- WS22 alanine dipeptide: Wigner-Sampled Conformations with PBE0 Energies and Forces, ColabFit Conversion
- MLIP-liquid-corrections: BSSE and Three-Body Dispersion Labels for OMol25 Molecules
- Materials Project Electronic Densities of States (VASP)
- Silica (SiO2) SCAN DFT Training Set for a Machine-Learned Interatomic Potential (Erhard et al. 2022), ColabFit Conversion