Automate all-atom protein design with diffusion models via YAML configuration.
npx skills add https://github.com/adaptyvbio/protein-design-skills --skill boltzgen
Please help me install this Agent Skill. Skill: boltzgen Source: https://github.com/adaptyvbio/protein-design-skills/tree/main/skills/boltzgen Command: npx skills add https://github.com/adaptyvbio/protein-design-skills --skill boltzgen
BoltzGen enables all-atom protein design using diffusion models, empowering simultaneous backbone and side-chain optimization for precise binding predictions.
Run a basic BoltzGen design with a YAML binder config: modal run modal_boltzgen.py --input-yaml binder.yaml --protocol protein-anything --num-designs 50
High-intent search queries and answers about installing and using this skill.
All-atom protein binder design uses diffusion models to jointly optimize the protein backbone and side chains. BoltzGen automates this process, allowing you to configure and run end-to-end design campaigns via a YAML file.
Yes, you can use a YAML configuration to design peptides and small-molecule targets. This approach enables reproducible end-to-end campaigns for precise binding predictions across different molecular targets.
You can run an end-to-end protein design workflow by executing the design script with a YAML input and specific protocol. This automates the inverse folding, structure prediction, and ranking steps to output CIF structures and metrics.
The Modal ecosystem is required to run the Python-based tooling for all-atom protein design campaigns. It facilitates executing the design, inverse folding, structure prediction, and ranking processes seamlessly.
Simultaneous optimization of protein backbone and side-chain packing is achieved through all-atom design with diffusion. This method provides accurate structural predictions for precise binding interactions.
A BoltzGen protein design campaign produces CIF structures and design metrics. These outputs result from the automated workflow encompassing design, inverse folding, structure prediction, and ranking.
junior1pGenerate side-chain-aware protein binder designs from YAML-configured campaigns using BoltzGen diffusion.
LiorZGenerate ranked protein binder designs from YAML specifications using diffusion and inverse folding.
adaptyvbioDesign protein sequences from structural backbones using ProteinMPNN inverse folding.
zongtingweiDesign all-atom protein structures with side-chain packing around target binding sites.
