data-viz-plots

Data Visualization (Universal)

Overview

This skill enables you to create professional scientific visualizations including scatter plots, line charts, heatmaps, violin plots, and more. Unlike cloud-hosted solutions, this skill uses the matplotlib and seaborn Python libraries and executes locally in your environment, making it compatible with ALL LLM providers including GPT, Gemini, Claude, DeepSeek, and Qwen.

When to Use This Skill

• Create publication-quality figures for papers and presentations
• Generate exploratory data analysis (EDA) plots
• Visualize gene expression, QC metrics, or clustering results
• Create multi-panel figures combining different plot types
• Export high-resolution images for reports
• Customize plot aesthetics (colors, fonts, styles)

How to Use

Step 1: Import Required Libraries

import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
import numpy as np
from matplotlib import gridspec
import matplotlib.patches as mpatches

# Set style for publication-quality plots
sns.set_style("whitegrid")
plt.rcParams['figure.dpi'] = 150
plt.rcParams['savefig.dpi'] = 300
plt.rcParams['font.size'] = 10

Step 2: Basic Scatter Plot

# Create figure and axis
fig, ax = plt.subplots(figsize=(6, 5))

# Scatter plot
ax.scatter(x_data, y_data, s=20, alpha=0.6, c='steelblue', edgecolors='k', linewidths=0.5)

# Labels and title
ax.set_xlabel('Gene Expression (log2)', fontsize=12)
ax.set_ylabel('Cell Count', fontsize=12)
ax.set_title('Expression vs. Cell Count', fontsize=14, fontweight='bold')

# Grid and styling
ax.grid(alpha=0.3)
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)

# Save figure
plt.tight_layout()
plt.savefig('scatter_plot.png', dpi=300, bbox_inches='tight')
plt.show()
print("✅ Scatter plot saved to: scatter_plot.png")

Step 3: Line Plot with Multiple Series

fig, ax = plt.subplots(figsize=(8, 5))

# Plot multiple lines
ax.plot(time_points, group1_values, marker='o', label='Group 1', color='#E74C3C', linewidth=2)
ax.plot(time_points, group2_values, marker='s', label='Group 2', color='#3498DB', linewidth=2)
ax.plot(time_points, group3_values, marker='^', label='Group 3', color='#2ECC71', linewidth=2)

# Styling
ax.set_xlabel('Time Point', fontsize=12)
ax.set_ylabel('Expression Level', fontsize=12)
ax.set_title('Gene Expression Over Time', fontsize=14, fontweight='bold')
ax.legend(frameon=True, loc='best', fontsize=10)
ax.grid(alpha=0.3, linestyle='--')

plt.tight_layout()
plt.savefig('line_plot.png', dpi=300, bbox_inches='tight')
plt.show()

Step 4: Box Plot and Violin Plot

# Prepare data (long-form DataFrame)
# df should have columns: 'cluster', 'expression', 'gene', etc.

fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(12, 5))

# Box plot
sns.boxplot(data=df, x='cluster', y='expression', palette='Set2', ax=ax1)
ax1.set_title('Box Plot: Expression by Cluster', fontsize=12, fontweight='bold')
ax1.set_xlabel('Cluster', fontsize=11)
ax1.set_ylabel('Expression Level', fontsize=11)
ax1.tick_params(axis='x', rotation=45)

# Violin plot
sns.violinplot(data=df, x='cluster', y='expression', palette='muted', ax=ax2, inner='quartile')
ax2.set_title('Violin Plot: Expression Distribution', fontsize=12, fontweight='bold')
ax2.set_xlabel('Cluster', fontsize=11)
ax2.set_ylabel('Expression Level', fontsize=11)
ax2.tick_params(axis='x', rotation=45)

plt.tight_layout()
plt.savefig('box_violin_plot.png', dpi=300, bbox_inches='tight')
plt.show()

Step 5: Heatmap

# Prepare data matrix (rows=genes, columns=samples or clusters)
# gene_expression_matrix: pandas DataFrame or numpy array

fig, ax = plt.subplots(figsize=(8, 6))

# Create heatmap
sns.heatmap(
    gene_expression_matrix,
    cmap='viridis',
    cbar_kws={'label': 'Expression'},
    xticklabels=True,
    yticklabels=True,
    linewidths=0.5,
    linecolor='gray',
    ax=ax
)

ax.set_title('Gene Expression Heatmap', fontsize=14, fontweight='bold')
ax.set_xlabel('Samples', fontsize=12)
ax.set_ylabel('Genes', fontsize=12)

plt.tight_layout()
plt.savefig('heatmap.png', dpi=300, bbox_inches='tight')
plt.show()

Step 6: Bar Plot with Error Bars

fig, ax = plt.subplots(figsize=(7, 5))

# Data
categories = ['Cluster 0', 'Cluster 1', 'Cluster 2', 'Cluster 3']
means = [120, 85, 200, 150]
errors = [15, 10, 25, 20]

# Bar plot
bars = ax.bar(categories, means, yerr=errors, capsize=5,
               color=['#E74C3C', '#3498DB', '#2ECC71', '#F39C12'],
               edgecolor='black', linewidth=1.2, alpha=0.8)

# Labels
ax.set_ylabel('Cell Count', fontsize=12)
ax.set_title('Cell Counts by Cluster', fontsize=14, fontweight='bold')
ax.set_ylim(0, max(means) * 1.3)

# Add value labels on bars
for bar, mean in zip(bars, means):
    height = bar.get_height()
    ax.text(bar.get_x() + bar.get_width()/2., height + 5,
            f'{mean}', ha='center', va='bottom', fontsize=10)

plt.tight_layout()
plt.savefig('bar_plot.png', dpi=300, bbox_inches='tight')
plt.show()

Advanced Features

Multi-Panel Figure

# Create complex layout
fig = plt.figure(figsize=(12, 8))
gs = gridspec.GridSpec(2, 3, figure=fig, hspace=0.3, wspace=0.3)

# Panel A: Scatter
ax1 = fig.add_subplot(gs[0, :2])
ax1.scatter(x_data, y_data, c=cluster_labels, cmap='tab10', s=10, alpha=0.6)
ax1.set_title('A. UMAP Projection', fontsize=12, fontweight='bold', loc='left')
ax1.set_xlabel('UMAP1')
ax1.set_ylabel('UMAP2')

# Panel B: Violin
ax2 = fig.add_subplot(gs[0, 2])
sns.violinplot(data=df, y='expression', palette='Set2', ax=ax2)
ax2.set_title('B. Expression', fontsize=12, fontweight='bold', loc='left')

# Panel C: Heatmap
ax3 = fig.add_subplot(gs[1, :])
sns.heatmap(matrix, cmap='coolwarm', center=0, ax=ax3, cbar_kws={'label': 'Z-score'})
ax3.set_title('C. Gene Expression Heatmap', fontsize=12, fontweight='bold', loc='left')

plt.savefig('multi_panel_figure.png', dpi=300, bbox_inches='tight')
plt.show()

Custom Color Palette

# Define custom colors
custom_palette = ['#E74C3C', '#3498DB', '#2ECC71', '#F39C12', '#9B59B6']

# Use in seaborn
sns.set_palette(custom_palette)

# Or create color dict for specific mapping
color_dict = {
    'T cells': '#E74C3C',
    'B cells': '#3498DB',
    'Monocytes': '#2ECC71',
    'NK cells': '#F39C12'
}

# Use in scatter plot
for cell_type, color in color_dict.items():
    mask = df['celltype'] == cell_type
    ax.scatter(df.loc[mask, 'x'], df.loc[mask, 'y'],
               c=color, label=cell_type, s=20, alpha=0.7)
ax.legend()

Density Plot

from scipy.stats import gaussian_kde

fig, ax = plt.subplots(figsize=(8, 6))

# Calculate density
xy = np.vstack([x_data, y_data])
z = gaussian_kde(xy)(xy)

# Sort points by density for better visualization
idx = z.argsort()
x, y, z = x_data[idx], y_data[idx], z[idx]

# Scatter with density colors
scatter = ax.scatter(x, y, c=z, s=20, cmap='viridis', alpha=0.6, edgecolors='none')
plt.colorbar(scatter, ax=ax, label='Density')

ax.set_xlabel('UMAP1', fontsize=12)
ax.set_ylabel('UMAP2', fontsize=12)
ax.set_title('Density Scatter Plot', fontsize=14, fontweight='bold')

plt.tight_layout()
plt.savefig('density_plot.png', dpi=300, bbox_inches='tight')
plt.show()

Common Use Cases

QC Metrics Visualization

# Assuming adata.obs has QC columns: n_genes, n_counts, percent_mito

fig, axes = plt.subplots(1, 3, figsize=(15, 4))

# Plot 1: Histogram of genes per cell
axes[0].hist(adata.obs['n_genes'], bins=50, color='steelblue', edgecolor='black', alpha=0.7)
axes[0].axvline(adata.obs['n_genes'].median(), color='red', linestyle='--', label='Median')
axes[0].set_xlabel('Genes per Cell', fontsize=11)
axes[0].set_ylabel('Frequency', fontsize=11)
axes[0].set_title('Genes per Cell Distribution', fontsize=12, fontweight='bold')
axes[0].legend()

# Plot 2: Scatter UMI vs Genes
axes[1].scatter(adata.obs['n_counts'], adata.obs['n_genes'],
                s=5, alpha=0.5, c=