MSK Ecosystems Validator

Validation tools for MSK single-cell ecosystems data, with support for CELLxGENE schema compliance and ontology term validation.

Features

• AnnData validation: Validate h5ad files against pydantic models
• Schema validation: Validate obs (cell metadata) and var (gene metadata) against CELLxGENE schema
• Ontology validation: Validate ontology terms using the EBI OLS4 API

Installation

# Clone the repository
git clone <repository-url>
cd msk-ecosystems-validator

# Install with uv (recommended)
uv sync --extra dev

# Or with pip
pip install -e .

Usage

CLI

# Validate an AnnData file
uv run validate-anndata data/sample.h5ad

# Validate with obs and var schema checks
uv run validate-anndata data/sample.h5ad --validate-obs --validate-var

# Verbose output
uv run validate-anndata data/sample.h5ad --validate-obs --validate-var -v

Development

# Install development dependencies
uv sync --extra dev

# Run tests
uv run pytest

# Run tests with coverage
uv run pytest --cov=src