# a-r-j/graphein

Protein Graph Library

Repository: https://github.com/a-r-j/graphein
Canonical: https://ross.abutalabs.com/products/graphein
Homepage: https://graphein.ai/
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: protein, protein-structure, deep-learning, pytorch, graph-neural-networks, dgl, computational-biology, bioinformatics, structural-biology, protein-data-bank, protein-design, geometric-deep-learning, pytorch-geometric, python, interactomics, interactome, rna, ppi-networks, gene-regulatory-networks, drug-discovery
Last push: 2026-08-17T21:55:51+00:00

## Health v2 (maintenance only)
Score: 76/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 35, longevity 100
- inputs: {"age_days": 2562, "days_push": 16, "days_rel": 221, "gap_med": 493, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1190, forks 142 (observed 2026-08-28T04:03:55.966096+00:00)

## What it is
Graphein is a Python library for constructing graph and mesh representations of proteins, RNA, molecules, and biological interaction networks (PPI and gene regulatory networks). It outputs graphs compatible with NetworkX, PyTorch Geometric, and DGL for use in geometric deep learning workflows.

## Use cases
- convert PDB protein structures into residue or atom graphs for machine learning
- build graph neural network datasets from AlphaFold structures
- construct protein-protein interaction networks for analysis
- represent RNA secondary structure as graphs
- create gene regulatory network graphs
- prepare protein structure data for PyTorch Geometric or DGL models
- visualize protein graphs and meshes in 3D
- batch-convert PDB files to graph pickles from the command line

## When to choose
- you need graph representations of biomolecular structures for deep learning
- you want interoperability with PyTorch Geometric, DGL, or NetworkX
- you work in computational biology, protein design, or drug discovery
- you need configurable, feature-rich protein graph construction pipelines

## When to avoid
- you need a general-purpose graph library unrelated to biology
- you require a fully stable, production-hardened API (the project is early-stage)
- you only need simple sequence-based protein analysis without structural graphs

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, data-science, data-visualization, cli
- domain: bioinformatics, machine-learning, deep-learning, data-science
- platform: python, cli, cross-platform
- tags: protein-structure, graph-neural-networks, geometric-deep-learning, pytorch-geometric, dgl, networkx, ppi-networks, rna-graphs, gene-regulatory-networks, alphafold, drug-discovery, computational-biology, algorithms

## Member repositories
- a-r-j/graphein (main) score 76

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:55.966096+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:23:00.882144+00:00, confidence not recorded.
  - readme: https://github.com/a-r-j/graphein (fetched 2026-08-28T04:03:55.966096+00:00, sha fee2d2d79a23)
  - homepage: https://graphein.ai/ (fetched 2026-08-29T12:30:28.491164+00:00, sha c93a8a387026)
  - site_page: https://graphein.ai/getting_started/installation.html (fetched 2026-08-29T12:30:28.500855+00:00, sha ad87a8679a07)
  - site_page: http://graphein.ai//getting_started/installation.html (fetched 2026-08-29T12:30:28.512582+00:00, sha 9025e3f45f57)
  - registry_pypi: https://pypi.org/pypi/graphein/json (fetched 2026-08-29T12:30:28.514829+00:00, sha e445cb20d189)
  - site_page: http://www.graphein.ai (fetched 2026-08-29T12:30:28.503137+00:00, sha 11aba09ae290)
  - site_page: http://graphein.ai/getting_started/usage.html (fetched 2026-08-29T12:30:28.505588+00:00, sha 03a896c6bb89)
  - site_page: http://graphein.ai/modules/graphein.protein.html (fetched 2026-08-29T12:30:28.507856+00:00, sha 9e2e68a4208f)
- Data as of 2026-08-30T08:39:29.467469+00:00.