AN
数据与复现
AnnData
AnnData is a Python package for handling annotated data matrices, storing experimental measurements (X) alongside observ…
K-Dense-AI/claude-scientific-skills查看
数据与复现
NI
nicheformer-spatial-agent
维护者 FreedomIntelligence · 最近更新 2026年4月1日
Spatial niche analysis with Nicheformer foundation model for tissue microenvironment.
原始来源
FreedomIntelligence/OpenClaw-Medical-Skills
https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills/tree/main/skills/nicheformer-spatial-agent
- 维护者
- FreedomIntelligence
- 许可
- MIT
- 最近更新
- 2026年4月1日
技能摘要
来自 SKILL.md 的关键信息
核心说明
- Nicheformer Spatial Agent leverages Nicheformer foundation model，trained on over 53 million spatially resolved cells，to model cellular architecture 、 tissue microenvironments ，支持 unprecedented accuracy. It enables spatial context-aware cell type annotation，niche discovery，、 tissue organization analysis。
- When analyzing spatial transcriptomics requiring deep cellular context understanding。
- 用于 identifying tissue niches 、 cellular neighborhoods。
- To predict cell-cell interactions based on spatial proximity。
- When transferring annotations ，面向 atlases to new spatial data。
原始文档
SKILL.md 摘录
Core Capabilities
-
Spatial Context Embeddings: Generate embeddings that capture both gene expression and spatial context.
-
Niche Discovery: Identify recurrent cellular neighborhoods across tissues.
-
Zero-Shot Cell Type Annotation: Transfer cell type labels without retraining.
-
Spatial Perturbation Prediction: Predict effects of removing cell types from niches.
-
Cross-Tissue Transfer: Apply models trained on one tissue to another.
-
Tissue Architecture Analysis: Quantify spatial organization patterns.
Model Architecture
| Component | Description | Parameters |
|---|---|---|
| Expression Encoder | Gene expression transformer | ~100M |
| Spatial Encoder | Neighborhood graph attention | ~50M |
| Fusion Layer | Cross-attention expression + spatial | ~30M |
| Pretraining Data | 53M+ spatially resolved cells | Multi-tissue |
Supported Spatial Technologies
| Platform | Coverage | Resolution |
|---|---|---|
| 10x Xenium | Full support | Subcellular |
| MERFISH | Full support | Subcellular |
| CosMx | Full support | Subcellular |
| Visium | Supported | 55 μm spot |
| Slide-seq | Supported | 10 μm bead |
| seqFISH+ | Supported | Subcellular |
| STARmap | Supported | Subcellular |
适用场景
- Use nicheformer-spatial-agent ，用于 single-cell 或 spatial omics analysis。
- Apply nicheformer-spatial-agent to 聚类，integration，或 trajectory workflows。
不适用场景
- Do not rely on this catalog entry alone ，用于 installation 或 maintenance details。
上游相关技能
- SIMO_Multiomics_Integration_Agent - For multi-omics spatial integration
- scGPT_Agent - For single-cell foundation models
- Cell_Cell_Communication - For ligand-receptor analysis
- Spatial_Epigenomics_Agent - For spatial epigenomics
相关技能
相关技能
Cell segmentation from multiplexed tissue images. Covers deep learning (Cellpose, Mesmer) and classical approaches for n…
FreedomIntelligence/OpenClaw-Medical-Skills查看
BI
Extract, process, and deduplicate reads using Unique Molecular Identifiers (UMIs) with umi_tools. Use when library prep…
FreedomIntelligence/OpenClaw-Medical-Skills查看
Integrate multiple scRNA-seq samples/batches using Harmony, scVI, Seurat anchors, and fastMNN. Remove technical variatio…
FreedomIntelligence/OpenClaw-Medical-Skills查看