The user wants me to create a single-page web app that runs a Gray-Scott reaction-diffusion simulation. This is a fascinating simulation that produces organic Turing patterns. Let me break down what I need to do:

1. Create a single HTML file (index.html) with:
   - CSS in a <style> tag
   - JS in a <script> tag
   - No external resources
   - A canvas for the simulation
   - Mouse interaction to seed new growth

The Gray-Scott model simulates two virtual chemicals (U and V) that diffuse and react. The equations are:
- du/dt = Du * ∇²u - uv² + f(1-u)
- dv/dt = Dv * ∇²v + uv² - (f+k)v

Where:
- u, v are concentrations of the two chemicals
- Du, Dv are diffusion rates
- f is the feed rate
- k is the kill rate

I'll need to:
1. Set up a canvas
2. Implement the simulation using WebGL or Canvas 2D with manual convolution
3. Use double buffering for the simulation
4. Add mouse interaction to add "chemical" at cursor position
5. Make it visually appealing with good color mapping

For performance, I should use fragment shaders in WebGL, but that's complex. Let me start with a Canvas 2D approach using manual convolution, which is simpler but slower. Actually, for real-time performance, WebGL would be better. Let me try a hybrid approach or just use Canvas 2D with optimizations.

Actually, let me implement this with WebGL for performance, as the Gray-Scott simulation really benefits from GPU acceleration. I'll create fragment shaders for the reaction-diffusion step.

Let me write the complete index.html file

The user asked me to create a Gray-Scott reaction-diffusion simulation. I've written a complete single-page web app to `/workspace/index.html`. Let me verify the file was created correctly and check if there are any issues.

Looking at my implementation:
1. I used WebGL for GPU-accelerated simulation (essential for real-time performance)
2. The Gray-Scott equations are implemented in a fragment shader
3. Mouse interaction allows seeding new growth (left click adds activator V, right click adds inhibitor U)
4. Multiple presets for different pattern types (Coral, Mitosis, Solitons, etc.)
5. UI controls for feed rate, kill rate, diffusion rates, and timestep
6. Beautiful color mapping for visualization
7. Self-contained with no external resources

The simulation uses:
- Ping-pong framebuffers for the reaction-diffusion calculation
- 9-point Laplacian stencil for better accuracy
- 8 sub-steps per frame for stability
- Cyan/blue/pink color scheme for organic-looking patterns

Let me verify the file exists and maybe test it by checking the content is valid

The user hasn't asked for anything else. The file has been created successfully. Let me provide a brief summary of what was built and how to use it.