菜单
Compare gene signatures across perturbations and suggest clustering or grouping.
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
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.
| name | perturbation_signature_compare |
| description | Compare gene signatures across perturbations and suggest clustering or grouping. |
| category | bio/perturb_seq |
| version | 1 |
| requires_tools | ["read_file","python_repl"] |
| requires_network | false |
| user_invocable | true |
| species | any |
| modality | perturb_seq |
| stage | analysis |
| stability | experimental |
| safety_level | low |
User has multiple perturbation signatures (e.g. DE lists or effect sizes per gene per perturbation) and wants to compare or group them.
Load: If paths given, use read_file; otherwise ask for a matrix or list of (perturbation, gene, score) triples.
Structure: Build a perturbation × gene matrix (e.g. log2FC or binary DE).
Compare: Use python_repl to compute:
Cluster: Suggest grouping (e.g. "perturbations A and B are similar; C is distinct") and optionally suggest visualization (heatmap, dendrogram).
Summarize: Table or list of similar pairs/groups and one-sentence biological interpretation.
