martinpacesa/BindCraft

Health v2 · maintenance only

Adoption not part of the score

1216 stars · 278 forks observed · 2026-09-21

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

BindCraft is a Python-based computational pipeline for de novo protein binder design that combines AlphaFold2 backpropagation, ProteinMPNN, and PyRosetta filtering. Users specify a target protein PDB and the pipeline automatically generates and filters candidate binder designs until enough pass quality metrics to order synthetically.

Use cases

• design de novo protein binders to a target protein
• generate therapeutic or research antibody-like binder candidates
• run AlphaFold2-based binder design trajectories on a GPU
• screen computationally designed binders before ordering synthesis
• design binders targeting specific hotspot residues on a protein

When to choose

• you need automated end-to-end binder design with minimal manual intervention
• you have access to an NVIDIA GPU with at least 32 GB memory
• you want a free, open-source alternative to commercial protein design suites
• you want reproducible binder designs backed by a published preprint

When to avoid

• you lack a CUDA-compatible NVIDIA GPU or Google Colab access
• you need commercial use without a PyRosetta license
• you need quick one-off designs rather than hundreds to thousands of trajectories
• you work outside structural biology and protein engineering

Facets

library · maturity active

machine-learning deep-learning simulation data-generation bioinformatics artificial-intelligence deep-learning python protein-design alphafold2 binder-design pyrosetta computational-biology drug-discovery gpu linux docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="martinpacesa/BindCraft")