菜单
Rank perturbation targets by drugability, pathway relevance, and safety given constraints.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | target_prioritization |
| description | Rank perturbation targets by drugability, pathway relevance, and safety given constraints. |
| category | bio/perturb_seq |
| version | 1 |
| requires_tools | ["fetch_url","search_knowledge_base","python_repl"] |
| requires_network | true |
| user_invocable | true |
| species | any |
| modality | perturb_seq |
| stage | prioritization |
| stability | experimental |
| safety_level | medium |
User has a list of candidate genes or perturbations and wants them ranked by suitability for follow-up (drugability, pathway, safety).
Local: Use search_knowledge_base for lab-specific target lists or constraints.
Annotate: For each candidate, use fetch_url (UniProt/Open Targets/DrugBank if available) to get:
Score: In python_repl, build a simple score (e.g. 0–1 for druggable, pathway relevance, safety) and rank.
Present: Ranked table with short justification per target and caveats (e.g. "limited drug data").
Manage the BioAPEX current-feature workflow from scoping through review and completion
Turn an analysis request into a Slurm-ready execution plan with commands, resource assumptions, and job structure.
Scale a buffer recipe to a target volume and compute component masses/volumes.
Save a fetched summary or document to the knowledge base for later retrieval (e.g. after PubMed/UniProt lookup).
Interpret scRNA clusters using marker genes and suggest cell type or state.
Critically evaluate a perturbation hypothesis — challenge assumptions, propose negative controls, and flag confounders.
