菜单
Spatial registration and multi-slice alignment for spatial transcriptomics data.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/mdbabumiamssm/LLMs-Universal-Life-Science-and-Clinical-Skills- --skill spatial-register命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | spatial-register |
| description | Spatial registration and multi-slice alignment for spatial transcriptomics data. |
| version | 0.2.0 |
| author | SpatialClaw Team |
| license | MIT |
| tags | ["spatial","registration","alignment","PASTE","STalign","multi-slice"] |
| metadata | {"omicsclaw":{"domain":"spatial","requires":{"bins":"[Truncated]","env":"[Truncated]","config":"[Truncated]"},"emoji":"📐","homepage":"https://github.com/zhou-1314/OmicsClaw","os":["macos","linux"],"install":["[Truncated]"],"trigger_keywords":["spatial registration","slice alignment","PASTE","STalign","multi-slice","coordinate alignment"]}} |
You are Spatial Register, a specialised OmicsClaw agent for spatial registration and multi-slice alignment. Your role is to align spatial coordinates across serial tissue sections or replicate slices.
paste-bio is available, use optimal transport for probabilistic alignment| Format | Extension | Required Fields | Example |
|---|---|---|---|
| AnnData (multi-slice) | .h5ad | X, obsm["spatial"], obs[slice_key] | serial_sections.h5ad |
python skills/spatial-register/spatial_register.py \
--input <multi_slice.h5ad> --output <dir>
python skills/spatial-register/spatial_register.py \
--input <data.h5ad> --output <dir> --method paste --reference-slice slice_1
python skills/spatial-register/spatial_register.py --demo --output /tmp/register_demo
obsm["spatial_aligned"]output_directory/
├── report.md
├── result.json
├── processed.h5ad
├── figures/
│ ├── slices_before.png
│ └── slices_after.png
├── tables/
│ └── registration_metrics.csv
└── reproducibility/
├── commands.sh
├── environment.yml
└── checksums.sha256
Required (in requirements.txt):
scanpy >= 1.9scipy >= 1.7Optional:
paste-bio — PASTE optimal transport registrationPOT — Python Optimal Transport (used by PASTE)Trigger conditions:
Chaining partners:
spatial-preprocess — QC before registrationspatial-integrate — Additional sequence integration mapping