PXDesign (ByteDance, 2025)

github.com/bytedance/pxdesign
Idle236updated 6 months ago
Python
Apache-2.0

Fast, modular, and accurate de novo design of protein binders based on the Protenix foundation model, achieving 17-82% nanomolar hit rates across diverse targets with 2-6× improvement over prior methods like AlphaProteo and RFdiffusion (229+ stars, Apache 2.0)

Sourced from

  • GitHubgithub.com/bytedance/pxdesign
  • Awesome AI for Sciencegithub.com/bytedance/pxdesign

Related resources

Protein structure prediction

Active14.7K3 months ago
Python
Apache-2.0

AlphaFold 3 inference pipeline for unified biomolecular structure prediction of proteins, nucleic acids, small molecules, ions, and post-translational modifications (Google DeepMind, Nature 2024)

Active8.3K3 weeks ago
Python
Apache-2.0

Deep learning library for Chemistry based on Tensorflow

Active6.8K1 month ago
Python
MIT

Protein structure prediction from ESM models

Archived4.2K2 years ago
Python
MIT

First fully open-source model achieving AlphaFold3-level accuracy with 1000x faster binding affinity prediction (MIT)

Active4.1K1 month ago
Python
MIT

Cheminformatics toolkit

Active3.5K1 month ago
HTML
BSD-3-Clause