Design protein binders with diffusion-based generative models.
npx skills add https://github.com/yjcyxky/biominer-skills --skill boltzgen-yjcyxky
Please help me install this Agent Skill. Skill: boltzgen Source: https://github.com/yjcyxky/biominer-skills/tree/main/boltzgen Command: npx skills add https://github.com/yjcyxky/biominer-skills --skill boltzgen-yjcyxky
BoltzGen automates the design of protein binders using diffusion-based generative models, enabling rapid exploration of novel binders against target proteins, peptides, nanobodies, or antibodies.
Prepare a design.yaml describing your target and design constraints, then run BoltzGen with Docker. For example:
High-intent search queries and answers about installing and using this skill.
Protein binder design using diffusion models is automated by building backbones, designing sequences via inverse folding, and validating structures. This process supports de novo design for proteins, peptides, nanobodies, and antibodies against defined targets.
Diffusion-based inverse folding for binder design generates candidate protein sequences that fold into specific backbone structures. It enables rapid exploration of novel binders by validating structures with predictors and applying affinity filtering across diverse targets.
Yes, GPU-enabled hardware is required to run end-to-end protein binder design workflows. You must also use the BoltzGen Docker image to execute the automated design pipeline against your specified targets.
De novo nanobody design with Docker requires preparing a design.yaml file describing your target and constraints. You then run the BoltzGen Docker container with GPU access, specifying the protocol, output directory, and number of designs to generate.
Peptide binder design supports specified targets including small-molecule interactions. You can evaluate binding potential across diverse designs and select top candidates for experimental validation using the automated filtering workflow.
The best way to validate designed protein binders computationally is using structure predictors to assess folding accuracy and applying affinity prediction filters. This ensures only top-quality candidates are selected for downstream experimental validation.
adaptyvbioGenerate protein backbones with RFdiffusion using contigmap and hotspot specifications.
junior1pRank protein binder designs using ipSAE_min, LIS, and pDockQ scores.
PKU-YuanGroupConverts PDF documents to clean, structured Markdown.
jaechang-hitsSubmit cell-free protein expression and binding affinity experiments via Python SDK and REST API.
