PXDesign: Fast, Modular, and Accurate
De Novo Design of Protein Binders


PXDesign is a model suite for de novo protein-binder design — a diffusion generator (PXDesign-d) paired with Protenix and AF2-IG confidence models for selection. Across seven targets, PXDesign delivers 17-82% nanomolar hits on six and 2-6× gains over strong baselines.

Protenix Team, ByteDance Seed
Web Server Technical Report GitHub Repo

WeChat Group Slack Group
Highlights

Highlights at a glance

1

High wet-lab success: 17-82% hit rates (KD < 1000 nM) on diverse targets including IL-7RA, PD-L1, VEGF-A, SC2RBD, TrkA, EGFR; TNF-α remains challenging.

2

Model-driven generation & selection: PXDesign-d boosts pass rate & diversity; Protenix-based filters strongly enrich true binders and complement AF2-IG; combining predictors further improves enrichment.

3

Ready to use: Open PXDesign GitHub repository and a public web server for the community.

PXDesign Server Walkthrough

How PXDesign works

1) Generation

  • PXDesign-d (Diffusion) is a DiT-style model for backbone generation — proposes many target-conditioned binder backbones; sequences are then assigned with ProteinMPNN.

2) Prediction & filtering

  • Complex structures are predicted with Protenix. Candidates are filtered by confidence scores (e.g., ipTM) and structure consistency using Protenix and AF2-IG.

3) Selection for wet-lab

  • Passing designs are clustered by structural similarity (Foldseek) to preserve diversity; within each cluster, higher-confidence designs (Protenix ipTM) are prioritized for expression and BLI affinity assays.

Why PXDesign works

1) Filtering & ranking power

Protenix-based filtering strongly enriches and prioritizes true binders; together with AF2-IG, it captures complementary true positives, and using both is likely to yield stronger enrichment.

Filtering and ranking power

2) In-silico success rate

PXDesign-d attains higher success rates and broader fold diversity than RFDiffusion on 10 targets; diffusion is also more throughput-efficient than hallucination for large campaigns.

In silico success rate
diversity
generation time

3) Wet-lab validation

PXDesign achieves high nanomolar hit rates, leading or matching the best on multiple targets.

Download our designs (.zip)
In-vitro benchmark

Per-target experimental success rates across methods.

Examples of success binders

Experimental hit rates (% expressing & binding) for designed binders. “–” = not tested.

Examples of success binders

Representative PXDesign-designed nanomolar binders.

Beyond protein binders

While our in-silico and wet-lab validation focuses on protein binders, PXDesign-d is naturally extensible to diverse molecular targets (e.g., nucleic acids, small molecules, post-translationally modified proteins). We provide cross-modality demonstrations and a preliminary benchmark on cyclic-peptide binders.
Cyclic-peptide generation is available on our public server as an experimental feature.

Examples of success binders

Ship Notes & Key Takeaways

What’s released

1

Models and inference pipeline:

PXDesign Github repository.

2

Hosted access:

PXDesign web server for binder and cyclic-peptide design.

3

Paper assets:

Full technical report with protocols, thresholds, and methodology details.

Key Takeaways

1

Strong hits at scale:

Diffusion-based generation + orthogonal filtering yields high hit rates and diverse binders.

2

Understand structure predictors:

AF2-IG and Protenix cover different regions of the binder space, and combining them strengthens robustness.

3

Ready to try:

Open source code + a public server make it easy to reproduce and build upon the pipeline.