Design de novo protein binders with diffusion-model generators and confidence filtering.
npx skills add https://github.com/yjcyxky/biominer-skills --skill pxdesign
Please help me install this Agent Skill. Skill: pxdesign Source: https://github.com/yjcyxky/biominer-skills/tree/main/pxdesign Command: npx skills add https://github.com/yjcyxky/biominer-skills --skill pxdesign
De novo protein binder design is computationally intensive and requires integrated modeling, filtering, and validation to identify viable binders.
Use a GPU-enabled host with the PXDesign Docker image to run a full design pipeline. Example:
docker run --rm --gpus all
-v $(pwd):/data
ghcr.io/open-prophetdb/pxdesign:arm64-blackwell
pxdesign pipeline --preset extended
-i /data/design.yaml
-o /data/output
--N_sample 100
High-intent search queries and answers about installing and using this skill.
De novo protein binder design is achieved by using diffusion-model generators with Protenix and AF2-IG confidence filtering to identify viable binders. This process includes hotspot-guided design, adjustable binder length, and candidate ranking across multiple targets.
Hotspot-guided design for therapeutic binder development works by directing the diffusion-model generator to target specific interaction sites on a protein. It is combined with structure validation and scoring to prioritize candidates for protein engineering campaigns.
Yes, protein structure validation and the full binder design pipeline require a GPU-enabled Docker host. You must run the PXDesign Docker image to execute the diffusion-model generators and AF2-IG confidence filtering.
Yes, you can adjust binder length and rank candidates across multiple targets. The pipeline supports multi-target design campaigns by applying Protenix and AF2-IG confidence filtering to score and prioritize the generated protein structures.
The best way to validate and score protein binder candidates is by applying AF2-IG confidence filtering and Protenix structure validation. This integrated approach prioritizes viable therapeutic binders generated by the diffusion models.
Protenix and AF2-IG confidence filtering are used in protein engineering to filter diffusion-model outputs and ensure structural viability. This integrated modeling approach identifies high-confidence candidates suitable for therapeutic binder development.
jayll1303Build GPU-enabled Docker containers with NGC base images and uv.
adaptyvbioGenerate protein backbones with RFdiffusion using contigmap and hotspot specifications.
LiorZAutomate de novo protein binder design with AF2 and PyRosetta validation.
PKU-YuanGroupPredict protein, nucleic-acid, and small-molecule complex structures with Boltz-2.
