a-r-j/graphein

Health v2 · maintenance only

Adoption not part of the score

1190 stars · 142 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity active

machine-learning deep-learning data-science data-visualization cli bioinformatics machine-learning deep-learning data-science python cli cross-platform 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

For agents

markdown · JSON · MCP: product_card(name="a-r-j/graphein")