Tumor Gene Expression Profile

import matplotlib.pyplot as plt
import numpy as np

# Gene expression data (log2 fold change)
np.random.seed(42)
genes = ['TP53', 'BRCA1', 'EGFR', 'MYC', 'KRAS', 'PIK3CA']
# Expression in tumor vs normal tissue
tumor_expr = [
    np.random.normal(-1.5, 0.8, 50),   # TP53 downregulated
    np.random.normal(-2.0, 1.0, 50),   # BRCA1 downregulated
    np.random.normal(2.5, 1.2, 50),    # EGFR upregulated
    np.random.normal(3.0, 0.9, 50),    # MYC upregulated
    np.random.normal(1.8, 1.1, 50),    # KRAS upregulated
    np.random.normal(1.5, 0.7, 50),    # PIK3CA upregulated
]

# Colors based on regulation
colors = ['#3B82F6', '#2563EB', '#EF4444', '#DC2626', '#F97316', '#FB923C']

# Create figure
fig, ax = plt.subplots(figsize=(12, 7), facecolor='white')

vp = ax.violinplot(tumor_expr, positions=range(len(genes)), widths=0.7,
                   showmeans=False, showmedians=False, showextrema=False)

for i, body in enumerate(vp['bodies']):
    body.set_facecolor(colors[i])
    body.set_edgecolor('white')
    body.set_linewidth(2)
    body.set_alpha(0.75)

# Reference line at 0 (no change)
ax.axhline(0, color='#6B7280', linewidth=1.5, linestyle='-', zorder=0)
ax.fill_between([-0.5, 5.5], -0.5, 0.5, color='#F3F4F6', alpha=0.5, zorder=0)
ax.text(5.6, 0, 'No\nchange', fontsize=8, color='#6B7280', va='center')

# Significance thresholds
ax.axhline(1, color='#F97316', linewidth=1, linestyle='--', alpha=0.5)
ax.axhline(-1, color='#3B82F6', linewidth=1, linestyle='--', alpha=0.5)

# Add median markers and significance
for i, expr in enumerate(tumor_expr):
    median = np.median(expr)
    
    # Determine significance
    is_sig = abs(median) > 1
    
    ax.scatter(i, median, c='white', s=100, zorder=10,
               edgecolor=colors[i], linewidth=2.5)
    
    # Significance star
    if is_sig:
        stars = '***' if abs(median) > 2 else '**' if abs(median) > 1.5 else '*'
        y_pos = median + 0.5 if median > 0 else median - 0.5
        ax.text(i, y_pos, stars, ha='center', fontsize=12, 
                color=colors[i], fontweight='bold')

# Gene type indicators
for i, gene in enumerate(genes):
    gene_type = 'TSG' if i < 2 else 'ONC'
    ax.text(i, -4.2, gene_type, ha='center', fontsize=8, 
            color='#3B82F6' if i < 2 else '#EF4444', fontweight='500')

# Labels
ax.text(-0.5, 3.5, 'Upregulated', fontsize=10, color='#EF4444', fontweight='500')
ax.text(-0.5, -3.5, 'Downregulated', fontsize=10, color='#3B82F6', fontweight='500')

# Styling
ax.set_xticks(range(len(genes)))
ax.set_xticklabels(genes, fontsize=12, fontweight='700', family='monospace')
ax.set_ylabel('Log2 Fold Change', fontsize=12, fontweight='500', color='#374151')
ax.set_ylim(-4.5, 5)

ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
ax.spines['left'].set_color('#E5E7EB')
ax.spines['bottom'].set_color('#E5E7EB')
ax.tick_params(colors='#6B7280', labelsize=10)
ax.yaxis.grid(True, linestyle='--', alpha=0.3, color='#9CA3AF')

plt.tight_layout()
plt.show()