bytedance/Protenix

Health v2 · maintenance only

Adoption not part of the score

2038 stars · 306 forks observed · 2026-08-28

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

Protenix is an open-source PyTorch reproduction of AlphaFold 3 for high-accuracy biomolecular structure prediction, covering proteins, nucleic acids, and ligands. It is developed by ByteDance as a trainable, extensible research tool for the computational biology community.

Use cases

• predict 3D structure of a protein complex from sequence
• predict antibody-antigen binding structures
• train a biomolecular structure prediction model in PyTorch
• predict protein-ligand and protein-RNA interactions
• run an open-source alternative to AlphaFold 3
• evaluate structure prediction models with PXMeter benchmarks

When to choose

• you need an open-source, trainable AlphaFold 3-style model
• you want to fine-tune or extend structure prediction research
• you need antibody-antigen or protein-ligand complex prediction
• you work in computational biology with GPU resources

When to avoid

• you need a lightweight tool without GPU hardware
• you only need classical molecular docking rather than deep-learning prediction
• you need a polished end-user GUI application rather than a research codebase

Facets

library · maturity active

machine-learning deep-learning llm-training bioinformatics artificial-intelligence machine-learning python protein-structure-prediction alphafold3 pytorch computational-biology ai4science molecular-docking linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="bytedance/Protenix")