# martinpacesa/BindCraft

User friendly and accurate binder design pipeline

Repository: https://github.com/martinpacesa/BindCraft
Canonical: https://ross.abutalabs.com/products/bindcraft
Language: Python
License: MIT
License Family: permissive
Topics: alphafold2, binder, design, protein, pyrosetta
Last push: 2026-08-12T07:44:26+00:00

## Health v2 (maintenance only)
Score: 78/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 97, release rhythm 68, longevity 51
- inputs: {"age_days": 714, "days_push": 21, "days_rel": 138, "gap_med": 69.5, "n_releases_24m": 7}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1196, forks 277 (observed 2026-08-28T04:03:56.990708+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, simulation, data-generation
- domain: bioinformatics, artificial-intelligence, deep-learning
- platform: python
- tags: protein-design, alphafold2, binder-design, pyrosetta, computational-biology, drug-discovery, gpu, linux, docker

## Member repositories
- martinpacesa/BindCraft (main) score 78

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:56.990708+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:22:03.125631+00:00, confidence not recorded.
  - readme: https://github.com/martinpacesa/BindCraft (fetched 2026-08-28T04:03:56.990708+00:00, sha d5c16dd1ed8b)
- Data as of 2026-08-30T08:39:29.467469+00:00.