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