The user wants a single-page web app that simulates the Gray-Scott reaction-diffusion system, displaying organic Turing patterns on a canvas in real time. Mouse interaction should seed new growth. Everything in one index.html file, no external resources.

Key components:
1. Canvas element for rendering
2. Gray-Scott simulation on a 2D grid (two chemicals: U and V)
3. Real-time rendering with pixel manipulation
4. Mouse interaction to add chemical V (the "feed" chemical)
5. Good UI with controls for parameters (feed rate, kill rate, etc.)

The Gray-Scott model uses two chemicals U and V with:
- ∂U/∂t = Du∇²U - UV² + f(1-U)
- ∂V/∂t = Dv∇²V + UV² - (f+k)V

Where:
- Du, Dv are diffusion rates (typically Du=1.0, Dv=0.5)
- f is the feed rate
- k is the kill rate
- UV² is the reaction term

I'll use a Laplacian convolution kernel for diffusion, and render with a color map that maps U and V concentrations to visually appealing colors.

Let me write a comprehensive implementation with:
- Double-buffered grids (U and V)
- Efficient simulation loop
- Mouse seeding (add V chemical where mouse is)
- Color mapping based on U-V values for organic look
- Parameter controls (feed, kill, presets)
- Responsive canvas

The file has been created successfully. Let me verify it's present and correct.

The file is created. Let me verify it's well-formed by checking the HTML structure.