lucidrains/alphafold3-pytorch

Health v2 · maintenance only

Adoption not part of the score

1691 stars · 229 forks observed · 2026-08-28

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

A PyTorch implementation of Google DeepMind's Alphafold 3 model for protein and molecular structure prediction. It is a research-oriented reimplementation of the paper's architecture, including training pipeline components like PDB dataset preparation and sampling.

Use cases

• predict protein structures from sequences in pytorch
• reproduce alphafold 3 training from scratch
• research alphafold 3 architecture components
• train a structure prediction model on PDB data
• experiment with diffusion-based molecular structure prediction

When to choose

• you want a pure PyTorch, hackable implementation of Alphafold 3 for research
• you need to study or extend the AF3 architecture in code
• you want to train or fine-tune structure prediction models on your own data

When to avoid

• you need a production-ready, officially supported inference tool with pretrained weights
• you need optimized performance - consider alternatives like MegaFold with Triton kernels
• you need turnkey protein folding predictions without ML expertise

Facets

library · maturity active

machine-learning deep-learning llm-training deep-learning bioinformatics artificial-intelligence python alphafold3 protein-structure-prediction pytorch diffusion transformers research-implementation gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="lucidrains/alphafold3-pytorch")