openfold3
CommunityGPU-accelerated OpenFold3 for structure prediction.
System Documentation
What problem does it solve?
OpenFold3 provides a GPU-accelerated, open-source path to predict biomolecular structures, including proteins, DNA, RNA, and ligands, enabling researchers to generate high-confidence models from sequence data quickly.
Core Features & Use Cases
- Docker-based deployment: Run on NVIDIA DGX Spark (Grace Blackwell) with pre-compiled Triton kernels for fast startup.
- Multi-format inputs: Supports proteins, DNA, RNA, ligand complexes, and biomolecular assemblies.
- Batch and complex predictions: Generate multiple models and complex assemblies in a single workflow.
- Use Case: A structural biology team can run a batch of protein complexes to compare binding interfaces using the provided Docker image.
Quick Start
Use the OpenFold3 Docker image to run help and basic prediction commands. For example:
docker run --rm --gpus all --ipc=host --shm-size=64g
ghcr.io/open-prophetdb/openfold3:arm64-blackwell
run_openfold --help
docker run --rm --gpus all --ipc=host --shm-size=64g
ghcr.io/open-prophetdb/openfold3:arm64-blackwell
run_openfold predict --help
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: openfold3 Download link: https://github.com/yjcyxky/biominer-skills/archive/main.zip#openfold3 Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.