Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Bindome logo

PreprintWebsiteHuggingFaceMCPBeacons-API

Bindome banner Towards a protein binder candidate for every human protein

Resource

Bindome is a proteome-scale atlas of high-confidence in silico protein binder candidates. It contains >300,000 binder candidates covering >8,200 human proteins (>40% of the proteome). Every candidate carries a defined sequence, a predicted binder-target structure model, and in silico confidence metrics. We anticipate that the Bindome will be valuable for the scientific community by providing affinity and perturbation reagents with broad applications in dissecting biological mechanisms as well as in drug and target discovery. Please find here the code base to generate Bindome.

Instructions

The pipeline has three stages, run in order: TargetPreprocessing prepares target structures and domains, SweepScripts sets up and submits the binder design sweep, and BindCraft generates the actual binders. All three run in a single conda environment, set up once as described below.

Installation

Step 1: Clone the repository

git clone https://github.com/wejulius/Bindome.git

Step 2: Install the conda environment

bash Bindome/BindCraft/install_bindcraft.sh --cuda '12.4' --pkg_manager 'conda'

This creates a single BindCraft conda environment (ColabDesign, PyRosetta, JAX, biopython, requests, python-igraph, etc.) used to run our accelerated BindCraft framework, TargetPreprocessing, and SweepScripts. env/leonardo-production-environment.yaml is a pinned package list (conda list) of this environment as deployed in production on the Leonardo cluster — use it to diff against your own environment if you run into version-related issues.

Running

Target preprocessing

Fetches target structures/PAE from AlphaFold DB, segments them into domains, and builds the sweep index used by the design sweep. See TargetPreprocessing/README.md for the step-by-step scripts.

Design sweep

Sets up the sweep file structure and submits/tracks the slurm array jobs that run our accelerated BindCraft over the sweep index. See SweepScripts/README.md for details.

Citations

Wenckstern, J., Diaz-Rovira, A. M., et al. (2026). The Human Bindome: A Proteome-scale Atlas of Designed Binder Candidates. bioRxiv. doi: 10.64898/2026.07.30.741542

Acknowledgements

This repository directly builds on:

Moreover, Bindome would not be possible without these softwares:

About

Towards a protein binder candidate for every protein

Resources

Stars

40 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages