Graphene Design Universe 256K: Atomistic Porous and Patterned Graphene Geometries
- Provider
- Laboratory for Atomistic and Molecular Mechanics (LAMM), MIT
- License
- Apache-2.0 (source)
- Size
- 4,073 files
- Format
- Parquet (in sampled files)
- Stored at
- Hugging Face (https://huggingface.co/datasets/lamm-mit/graphene-design-universe-256k)
- Access
- Free and public. No account with the data provider is needed.
- Category
- Chemistry & Materials
- Source
- https://huggingface.co/datasets/lamm-mit/graphene-design-universe-256k
About this dataset
256,000 unrelaxed atomistic graphene designs from the Laboratory for Atomistic and Molecular Mechanics (LAMM) at MIT, each a periodic cell of carbon sites selected from pristine graphene by a geometric generator. It keeps all 64,000 designs of the earlier 64K release and adds 192,000 in 24 groups: the original 16 (round, square, hexagonal and oriented pores, angled slits, strut and polygon networks, pore gradients, flaws and seams, veins, nested and fibrous hierarchies, composite grids) and eight hybrid groups such as morphing pores, branching networks and multiscale pore fields. Designs range from 100 to 18,933,353 atoms (8.44 billion sites in total) with cell widths of 3.69 to 497.28 nm. The publishers state that no force-field evaluation, relaxation, molecular dynamics or mechanical property calculation was done, so there are no mechanical labels. Listing the repository (measured 2026-11-13) shows data/ with Parquet metadata shards (1.43 GB), images/ with tar shards of 384 by 384 PNG previews (1.5 GB), coordinates/ with tar shards of gzip-compressed extended XYZ files (51.7 GB), mechanics/ with a design inventory and result schemas, plus source_masks/, embedding/, provenance/, code/ and tools/. Read metadata with pandas or pyarrow and structures with ASE or OVITO; IDs run GDU-000000 to GDU-255999. Released under Apache-2.0; cite the dataset URL and revision.
How to load this dataset in Python
from datasets import load_dataset
ds = load_dataset("lamm-mit/graphene-design-universe-256k")
print(ds)Data structure
File types in sampled files: Parquet
Files
Example file: data/designs-0000.parquet
Analyze this dataset without downloading it
On Scigantic, Graphene Design Universe 256K: Atomistic Porous and Patterned Graphene Geometries 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
- Binding affinity (SPR) instrument output with ASM: 15 exports from Cytiva Biacore Insight, Cytiva Biacore T200 Control, Cytiva Biacore T200 Evaluation
- Systematic Magnesium (Mg) Structure Set for Machine Learning Potentials and Defects: DFT (Poul et al. 2023, Edmond), ColabFit Conversion
- QM7b and AlphaML: LR-CCSD and Hybrid DFT Static Dipole Polarizabilities for 7,211 Molecules, ColabFit Conversion
- Open Molecules 2025 (OMol25) Validation Set, ColabFit Conversion
- Revised MD17 (rMD17) Molecular Dynamics Benchmark, ColabFit Conversion
- Phonix: Database for Anharmonic Phonon Interactions
- Open Catalyst 2020 (OC20) S2EF Out-of-Domain (Both) Validation Set, ColabFit Conversion
- OQMD v1.8: 1.4 Million DFT Crystal Structures and Formation Energies (HDF5)