Spatial Transcriptomics Mapper

Source: https://github.com/aipoch/medical-research-skills

Spatial Transcriptomics Mapper (ID: 196)

When to Use

• Use this skill when the task is to Map spatial transcriptomics data from 10x Genomics Visium/Xenium onto.
• Use this skill for data analysis tasks that require explicit assumptions, bounded scope, and a reproducible output format.
• Use this skill when you need a documented fallback path for missing inputs, execution errors, or partial evidence.

Key Features

See ## Features above for related details.

• Scope-focused workflow aligned to: Map spatial transcriptomics data from 10x Genomics Visium/Xenium onto.
• Packaged executable path(s): scripts/__init__.py plus 1 additional script(s).
• Structured execution path designed to keep outputs consistent and reviewable.

Dependencies

See ## Prerequisites above for related details.

• Python: 3.10+. Repository baseline for current packaged skills.
• h5py: unspecified. Declared in requirements.txt.
• matplotlib: unspecified. Declared in requirements.txt.
• numpy: unspecified. Declared in requirements.txt.
• pandas: unspecified. Declared in requirements.txt.
• pil: unspecified. Declared in requirements.txt.
• pyarrow: unspecified. Declared in requirements.txt.
• scanpy: unspecified. Declared in requirements.txt.
• seaborn: unspecified. Declared in requirements.txt.
• squidpy: unspecified. Declared in requirements.txt.
• tifffile: unspecified. Declared in requirements.txt.

Example Usage

See ## Usage above for related details.

cd "20260318/scientific-skills/Data Analytics/spatial-transcriptomics-mapper"
python -m py_compile scripts/main.py
python scripts/main.py --help

Example run plan:

1. Confirm the user input, output path, and any required config values.
2. Edit the in-file CONFIG block or documented parameters if the script uses fixed settings.
3. Run python scripts/main.py with the validated inputs.
4. Review the generated output and return the final artifact with any assumptions called out.

Implementation Details

See ## Workflow above for related details.

• Execution model: validate the request, choose the packaged workflow, and produce a bounded deliverable.
• Input controls: confirm the source files, scope limits, output format, and acceptance criteria before running any script.
• Primary implementation surface: scripts/__init__.py with additional helper scripts under scripts/.
• Parameters to clarify first: input path, output path, scope filters, thresholds, and any domain-specific constraints.
• Output discipline: keep results reproducible, identify assumptions explicitly, and avoid undocumented side effects.

Quick Check

Use this command to verify that the packaged script entry point can be parsed before deeper execution.

python -m py_compile scripts/main.py

Audit-Ready Commands

Use these concrete commands for validation. They are intentionally self-contained and avoid placeholder paths.

python -m py_compile scripts/main.py
python scripts/main.py --help

Workflow

1. Confirm the user objective, required inputs, and non-negotiable constraints before doing detailed work.
2. Validate that the request matches the documented scope and stop early if the task would require unsupported assumptions.
3. Use the packaged script path or the documented reasoning path with only the inputs that are actually available.
4. Return a structured result that separates assumptions, deliverables, risks, and unresolved items.
5. If execution fails or inputs are incomplete, switch to the fallback path and state exactly what blocked full completion.

Description

Spatial Transcriptomics analysis tool for processing 10x Genomics Visium or Xenium data, projecting gene expression data back onto tissue section images to draw "gene-space" distribution maps. Supports gene expression visualization, spatial clustering analysis, and morphological feature correlation.

Features

• Visium Data Processing: Supports Space Ranger output (filtered_feature_bc_matrix.h5, spatial/tissue_positions_list.csv, spatial/tissue_lowres_image.png)
• Xenium Data Processing: Supports Xenium Explorer output (.h5, transcripts.parquet, nucleus_boundaries.parquet)
• Gene Expression Mapping: Projects expression of specified genes onto tissue images
• Spatial Clustering Visualization: Displays spatial distribution of Seurat/Scanpy clustering results
• Multi-gene Joint Analysis: Supports combined visualization of multiple genes
• High-resolution Output: Supports high-resolution image export

Installation

# Required dependencies
pip install scanpy squidpy matplotlib seaborn pillow numpy pandas h5py

# Optional: For Xenium data processing
pip install pyarrow dask

# Optional: For advanced image processing
pip install opencv-python scikit-image

Quick Start - Test Data

Generate sample Visium data to test the tool:

# Generate test data
python scripts/generate_test_data.py \
  --platform visium \
  --output ./test_data/visium_sample \
  --n-spots 500 \
  --n-genes 1000

# Run analysis on test data
python scripts/main.py \
  --platform visium \
  --data-dir ./test_data/visium_sample \
  --gene GENE_0000 \
  --output ./test_output/

Usage

Basic - Visium Data

python scripts/main.py \
  --platform visium \
  --data-dir /path/to/spaceranger/outs/ \
  --gene PIK3CA \
  --output ./output/

Basic - Xenium Data

python scripts/main.py \
  --platform xenium \
  --data-dir /path/to/xenium/outs/ \
  --gene PIK3CA \
  --output ./output/

Multiple Genes

python scripts/main.py \
  --platform visium \
  --data-dir /path/to/data/ \
  --genes PIK3CA,PTEN,EGFR \
  --mode overlay \
  --output ./output/

With Clustering Results

python scripts/main.py \
  --platform visium \
  --data-dir /path/to/data/ \
  --cluster-file ./clusters.csv \
  --output ./output/

Input File Structure

Visium (Space Ranger output)

outs/
├── filtered_feature_bc_matrix.h5    # Gene expression matrix
├── raw_feature_bc_matrix.h5         # Raw counts (optional)
├── spatial/
│   ├── tissue_positions_list.csv    # Spot positions
│   ├── tissue_lowres_image.png      # Low-res H&E image
│   ├── tissue_hires_image.png       # High-res H&E image
│   └── scalefactors_json.json       # Scale factors
└── web_summary.html

Xenium

outs/
├── cell_feature_matrix.h5           # Cell x gene matrix
├── transcripts.parquet              # Transcript coordinates
├── nucleus_boundaries.parquet       # Cell boundaries
├── cell_boundaries.parquet
├── morphology_focus.ome.tif         # Morphology image
└── experiment.xenium

Output Files

• {gene}_spatial_map.png: Single gene spatial expression map
• {gene}_heatmap.png: Gene expression heatmap
• multi_gene_overlay.png: Multi-gene overlay map (if using --mode overlay)
• cluster_spatial_map.png: Cluster spatial distribution map
• combined_report.html: Comprehensive HTML report

Parameters

Examples

Example 1: Single Gene Visualization

python scripts/main.py \
  --platform visium \
  --data-dir ./visium_sample/outs/ \
  --gene EPCAM \
  --cmap Reds \
  --output ./results/

Example 2: Tumor Marker Combination

python scripts/main.py \
  --platform visium \
  --data-dir ./breast_cancer/outs/ \
  --genes PIK3CA,ERBB2,ESR1,PGR \
  --mode multi \
  --cmap plasma \
  --output ./tumor_markers/