Ligo-Biosciences/AlphaFold3

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1091 stars · 94 forks observed · 2026-08-28

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

An open-source Python implementation of AlphaFold3, DeepMind's biomolecular structure prediction model, including the full model architecture and training code. It currently supports single-chain protein prediction, with ligand, multimer, and nucleic acid capabilities planned.

Use cases

• predict protein 3D structure from sequence
• train AlphaFold3 model on own protein data
• research open-source biomolecular folding
• extend structure prediction to ligands and nucleic acids
• reproduce AlphaFold3 training dynamics

When to choose

• you need a freely licensed, modifiable AlphaFold3 implementation for research
• you want to train or fine-tune structure prediction models on your own GPU cluster
• you want to contribute to or build on open protein-folding tooling

When to avoid

• you need production-ready, accurate predictions of full complexes with ligands today
• you lack multi-GPU (A100-class) hardware for training or inference
• you want a polished tool with stable releases and support

Facets

library · maturity experimental

machine-learning deep-learning llm-training bioinformatics machine-learning deep-learning python alphafold3 protein-structure-prediction structural-biology pytorch open-science biotech gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Ligo-Biosciences/AlphaFold3")