AN
Data & Repro
AnnData
AnnData is a Python package for handling annotated data matrices, storing experimental measurements (X) alongside observation metadata (obs)…
K-Dense-AI/claude-scientific-skillsView
Data & Repro
NI
nicheformer-spatial-agent
Maintainer FreedomIntelligence · Last updated April 1, 2026
Spatial niche analysis with Nicheformer foundation model for tissue microenvironment.
Original source
FreedomIntelligence/OpenClaw-Medical-Skills
https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills/tree/main/skills/nicheformer-spatial-agent
- Maintainer
- FreedomIntelligence
- License
- MIT
- Last updated
- April 1, 2026
Skill Snapshot
Key Details From SKILL.md
Key Notes
- The Nicheformer Spatial Agent leverages the Nicheformer foundation model, trained on over 53 million spatially resolved cells, to model cellular architecture and tissue microenvironments with unprecedented accuracy. It enables spatial context-aware cell type annotation, niche discovery, and tissue organization analysis.
- When analyzing spatial transcriptomics requiring deep cellular context understanding.
- For identifying tissue niches and cellular neighborhoods.
- To predict cell-cell interactions based on spatial proximity.
- When transferring annotations from atlases to new spatial data.
Source Doc
Excerpt From SKILL.md
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 |
Use cases
- Use nicheformer-spatial-agent for single-cell or spatial omics analysis.
- Apply nicheformer-spatial-agent to clustering, integration, or trajectory workflows.
Not for
- Do not rely on this catalog entry alone for installation or maintenance details.
Upstream Related Skills
- 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
Related skills
Related skills
BI
Data & Repro
bio-imaging-mass-cytometry-cell-segmentation
Cell segmentation from multiplexed tissue images. Covers deep learning (Cellpose, Mesmer) and classical approaches for nuclear and whole-cel…
FreedomIntelligence/OpenClaw-Medical-SkillsView
BI
Data & Repro
bio-read-qc-umi-processing
Extract, process, and deduplicate reads using Unique Molecular Identifiers (UMIs) with umi_tools. Use when library prep includes UMIs and ac…
FreedomIntelligence/OpenClaw-Medical-SkillsView
BI
Data & Repro
bio-single-cell-batch-integration
Integrate multiple scRNA-seq samples/batches using Harmony, scVI, Seurat anchors, and fastMNN. Remove technical variation while preserving b…
FreedomIntelligence/OpenClaw-Medical-SkillsView