Orchestrate an end-to-end protein binder design pipeline for 15-PGDH.
npx skills add https://github.com/alex-hh/in-silico-pgdh --skill pgdh-design
Please help me install this Agent Skill. Skill: pgdh-design Source: https://github.com/alex-hh/in-silico-pgdh/tree/main/.claude/skills/pgdh-design Command: npx skills add https://github.com/alex-hh/in-silico-pgdh --skill pgdh-design
This Skill automates the complex, multi-step process of designing and evaluating protein binders for the 15-PGDH target, ensuring all results are standardized and tracked.
Run the complete PGDH binder design, validation, and scoring pipeline.
High-intent search queries and answers about installing and using this skill.
You can automate the 15-PGDH protein binder design pipeline by orchestrating design generation, validation, and scoring into a single command. This coordinates BoltzGen, RFdiffusion3, Boltz-2, and ipSAE sequentially to produce standardized final results.
Managing S3 directory structures for computational biology campaigns is handled by standardizing all design outputs into a central source of truth directory. This ensures consistent data management and synchronized tracking across generation and evaluation phases.
Yes, Boltz-2 and RFdiffusion3 are used together within the orchestrated pipeline. RFdiffusion3 handles the initial design generation, while Boltz-2 performs the GPU-based validation and evaluation of the generated protein binders.
GPU-based evaluation jobs in a binder design workflow are coordinated by the pipeline's orchestration logic. It manages the sequential execution of validation tools like Boltz-2 and synchronizes the scoring results into a master campaign tracker.
No, the 15-PGDH binder design pipeline requires no manual intervention between generation and scoring. It orchestrates the end-to-end flow from sequence generation through to final scoring and ranking automatically with a single command.
junior1pCompute ESM2 embeddings and pseudo-log-likelihood scores for protein sequences.
junior1pGenerate side-chain-aware protein binder designs from YAML-configured campaigns using BoltzGen diffusion.
junior1pRank protein binder designs using ipSAE_min, LIS, and pDockQ scores.
adaptyvbioPredict protein structures from FASTA sequences using Chai-1.
