SpatialPowerGuider

AI-Driven Statistical Framework for Spatial Omics Power Analysis

Overview

SpatialPowerGuider is an intelligent web platform that leverages large language models (LLMs) to provide interactive guidance for designing spatial omics experiments.

Features

• 🔬 Multi-Platform Support: Visium, MERFISH, seqFISH+, CODEX
• 📊 Interactive Visualizations: Real-time power curves and effect size analysis
• 🤖 AI-Powered Guidance: Context-aware experimental design assistance
• 📈 Statistical Framework: Rigorous power analysis for TA, SVG, and CCC analyses
• 🎨 Beautiful UI: Space-themed design with modern web technologies

Tech Stack

• Frontend: Next.js 15, React 18, TypeScript
• Styling: Tailwind CSS with custom space theme
• Charts: ECharts (echarts-for-react)
• Icons: React Icons

Getting Started

Prerequisites

• Node.js 18+
• npm or yarn

Installation

# Install dependencies
npm install

# Run development server
npm run dev

Open http://localhost:3000 in your browser.

Build for Production

npm run build
npm start

Project Structure

SpatialPowerGuider/
├── app/
│   ├── components/
│   │   ├── SettingsPanel.tsx      # Left panel - experiment settings
│   │   ├── VisualizationPanel.tsx # Middle panel - charts and results
│   │   └── ChatPanel.tsx          # Right panel - AI assistant
│   ├── globals.css                 # Global styles and space theme
│   ├── layout.tsx                  # Root layout
│   └── page.tsx                    # Main page
├── public/                         # Static assets
├── package.json
└── README.md

Key Components

Settings Panel

Configure experimental parameters including:

• Technology platform selection
• Analysis type (TA/SVG/CCC)
• Sample size and replicates
• Statistical parameters (effect size, α, power)

Visualization Panel

Interactive charts showing:

• Power curves across sample sizes
• Effect size comparisons
• Real-time recommendations
• Detailed parameter tables

AI Chat Panel

Conversational interface providing:

• Context-aware guidance
• Platform-specific advice
• Sample size recommendations
• Study design optimization tips

Research Context

This software supports the parent R01 grant developing statistical frameworks for spatial omics experimental design. The AI layer makes these sophisticated statistical methods accessible to biomedical researchers without deep statistical training.

Principal Investigators

• Qin Ma, PhD (Ohio State University)
• Dongjun Chung, PhD (Ohio State University)

License

MIT License - see LICENSE file for details

Contact

For questions or support: Cankun Wang

Acknowledgments

Developed as part of the Biostatistics & Bioinformatics Lab at The Ohio State University