Download
Protenix is an open-source, trainable PyTorch reimplementation of AlphaFold 3, developed by ByteDance with the goal of democratizing high-accuracy protein structure prediction for computational biology and drug-discovery research. Protenix provides a complete pipeline for turning protein sequences (with optional MSA / sequence alignment) or structural inputs (e.g. PDB/CIF) into full 3D atomic-level structure predictions. It supports both “full” models and lightweight variants such as “Protenix-Mini,” offering a trade-off between speed/compute cost and predictive accuracy — making structure prediction accessible even in resource-constrained environments. The project also includes support for constraints (e.g., specifying residue- or atom-level contact constraints, or pocket constraints) to guide predictions toward biologically or experimentally relevant conformations, which enhances its utility for tasks like modeling complexes, ligands, or antibody–antigen interactions.
Features
- Support for full 3D atomic-level protein structure prediction starting from amino acid sequences
- Optional constraint guidance (residue-level, atom-level, or pocket constraints) to influence predicted conformations
- Lightweight variants (e.g. “Mini” model) optimized for faster inference and reduced compute/memory cost
- End-to-end pipeline including MSA search, input conversion (PDB/CIF → JSON), inference, and output generation
- Open-source PyTorch implementation enabling retraining, finetuning, and community-driven extension
- Compatibility with downstream tasks such as protein–ligand docking or protein binder design (via related frameworks)
Project Samples
