How to Choose a FigureYa Module?

FigureYa offers 300+ plotting modules covering expression profiling, immune analysis, survival analysis, single-cell, and more. With so many modules, choosing the right one becomes a challenge — names alone rarely tell you whether a template fits your data and research question.

Option 1: Gallery Website Search (Simplest)

Open the FigureYa gallery website and search directly — this is the fastest way to find modules:

• 🔗 FigureYa Gallery: >https://ying-ge.github.io/FigureYa/
• 🇨🇳 China Mirror: >https://figureya.online/ (faster for users in China)

How to Use

1. Keyword search: Type a keyword, gene name, or R package name (e.g., volcano, survival, ggplot2) in the search box to filter modules in real time.
2. Filter by visualization type: Click category buttons to browse by chart type, including:
   - ○ Circular
   - ∞ Network
   - • Scatter
   - ↔ Correlation
   - ◇ PCA
   - ▷ Survival
   - … and more
3. Browse thumbnails: Each module has a thumbnail showing the output — judge at a glance whether it fits your needs.
4. Download a single module: Hover your mouse over a thumbnail — a download option for that module will appear. Click to download, no need to clone the entire repo.

💡 Gallery search is the first step — find candidate modules here, then decide whether to download or verify further.

Option 2: Zread Chat AI (Most Intuitive)

If you don't know which keywords or technical terms to use, you can simply chat with AI in natural language and let it find modules for you across the entire FigureYa repository.

• 🔗 Zread AI: >https://zread.ai/ying-ge/FigureYa/

What Is It?

>Zread indexes the entire FigureYa repository (README, module documentation, input formats, analysis scenarios) into a chat-ready knowledge base. You just ask questions as if chatting.

How to Use

1. Open >https://zread.ai/ying-ge/FigureYa/
2. Click Ask AI and ask in natural language, for example:
   - "I want to draw a volcano plot for differentially expressed genes — which module?"
   - "Is there a module that does KM survival curve + Cox regression?"
   - "My data is a single-cell expression matrix and I need cell type annotation — which module do you recommend?"
3. The AI answers based on the repository content and recommends the corresponding FigureYa module numbers

Features

💡 Zread fits the "I have some data but don't know what to plot" scenario — chat with AI to clarify your needs first, then take the recommended module number to the gallery website to download.

Option 3: SFL (Most Systematic)

For a more systematic approach integrated with AI coding environments, use >Scientific Figure Library (SFL).

Why SFL?

What Is SFL?

>Scientific Figure Library is a local-first MCP server and App with a built-in FigureYa module search Provider. It does not execute plotting code — it does four things:

1. Search: Retrieve FigureYa modules using your plotting goal (e.g., "volcano plot", "PCA", "survival curve")
2. Browse thumbnails: View candidate module thumbnails to visually judge style fit
3. Exact preview: Preview the selected module to confirm data format and output
4. Materialize: Write the template file into your project directory with a lock file recording the version

Install

Visit the >SFL Releases page and download the plugin for your host:

On first launch, bind two directories:
- Global Library: where SFL stores its search index and cache
- Local workspace: the project directory where materialized templates are written

The Selection Workflow

Describe your plotting goal
      ↓
SFL searches FigureYa modules → returns candidates + thumbnails
      ↓
Browse thumbnails → narrow down
      ↓
Exact preview the selected module → confirm data format and output
      ↓
User confirms → materialize to project directory
      ↓
Run the materialized template in Wisp Science

Example

After installing the SFL plugin in Wisp Science, simply tell the AI:

"I want a volcano plot showing differentially expressed genes with labels"

SFL searches FigureYa for matching modules (e.g., FigureYa59volcanoV2), returns thumbnails for you to browse, and after exact preview confirmation, writes the template into your project.

SFL Design Principles

• No code execution: SFL only searches, previews, and materializes — plotting is done by your R/Python environment
• Commit-pinned identity: Each module is bound to a specific commit in the FigureYa repo, fully traceable
• No substitute plots: On materialization failure, SFL stops — it never auto-generates a replacement figure
• Respects FigureYa license: FigureYa-derived content retains CC BY-NC-SA 4.0; the iMetaMed paper is cited

More about SFL

• 📦 >SFL GitHub Repository
• 📖 >SFL Protocol Documentation
• 🔧 >SFL Quickstart
• 🌐 SFL is also listed on the FigureYa Ecosystem page

Comparison

💡 Recommended workflow: Start with Zread chat AI to clarify your needs (or search the gallery by keyword) → get candidate module numbers → download from the gallery → if you need more systematic verification or AI tool integration, use SFL for exact preview and materialization.