Scientific Visualization

intermediatedataMin 64K context

Creates publication-quality scientific figures and plots using matplotlib, seaborn, and plotly. Supports common scientific plot types including heatmaps, volcano plots, survival curves, network graphs, phylogenetic trees, and multi-panel figures with proper statistical annotations, color-blind safe palettes, and journal formatting.

visualization matplotlib seaborn plotly figures publication heatmap scientific-plots

Use Cases

Creating publication-ready figures for journal submissions
Generating volcano plots for differential expression results
Building multi-panel figures with consistent styling
Producing interactive dashboards for exploratory analysis
Making color-blind accessible scientific visualizations
Formatting plots to specific journal requirements (Nature, Science, Cell)

Example Prompt

Create a publication-quality multi-panel figure for a genomics paper.

The figure should contain:
- Panel A: Volcano plot of differential expression (log2FC vs -log10 p-value)
- Panel B: Heatmap of top 50 differentially expressed genes
- Panel C: UMAP embedding colored by cell type
- Panel D: Bar plot of cell type proportions across conditions

Requirements:
- Use a color-blind safe palette (e.g., Wong or Tol)
- 300 DPI, suitable for Nature-style journals
- Consistent font sizes (axis labels 8pt, titles 10pt)
- Panel labels (A, B, C, D) in bold
- Statistical annotations where appropriate
- Save as both PDF (vector) and PNG (raster)

Generate the complete matplotlib/seaborn Python code with sample data.

Recommended Models

claude-opus-4-6 gpt-5 gemini-2-5-pro

Compatible Tools

claude-codecursorkiroany

Modalities

Input: text, code, file

→

Output: text, code

Related Skills

data-analysis bioinformatics-pipeline

Author

OpenModels Community

@openmodelsrun