import matplotlib.pyplot as plt
from matplotlib.patches import Patch
import numpy as np
from scipy.interpolate import make_interp_spline

# 1. CYP1A2 Substrate Data
bin_centers = [0.0, 0.05, 0.10, 0.15, 0.20, 0.25, 0.30, 0.35, 0.40, 
               0.45, 0.50, 0.55, 0.60, 0.65, 0.70, 0.75, 0.80, 0.85, 0.90, 0.95, 1.0]

frequencies = [9.22, 11.21, 6.80, 5.42, 4.94, 4.37, 4.33, 5.02, 3.84, 
               3.36, 3.80, 4.29, 3.11, 3.56, 3.68, 4.25, 4.94, 6.23, 5.38, 2.22, 0.04]

# 2. Smoothing
x_smooth = np.linspace(min(bin_centers), max(bin_centers), 300)
spl = make_interp_spline(bin_centers, frequencies, k=3)
y_smooth = spl(x_smooth)
y_smooth = [val if val > 0 else 0 for val in y_smooth] 

# 3. Colors (Functional distinction, not risk)
colors = []
for val in bin_centers:
    if val < 0.3:
        colors.append('skyblue')
    elif val > 0.7:
        colors.append('royalblue')
    else:
        colors.append('lightgray')

# 4. Create the chart
plt.figure(figsize=(7, 6))

# Bars
plt.bar(bin_centers, frequencies, width=0.04, color=colors, edgecolor='black', alpha=0.8, label='Data Frequency')

# 5. Tags and Titles
plt.xlabel('Probability of being a CYP1A2 Substrate', fontsize=12)
plt.ylabel('% Frequency', fontsize=12)
plt.title('CYP1A2 Metabolic Pathway Usage', fontsize=14)

# Axle settings
plt.xticks(np.arange(0.0, 1.05, 0.1))
plt.xlim(-0.05, 1.05)
plt.ylim(0, 14)

# 6. Vertical Legend
legend_elements = [
    Patch(facecolor='skyblue', edgecolor='black', label='Not a Substrate (Uses other enzymes)'),
    Patch(facecolor='lightgray', edgecolor='black', label='Mixed Potential'),
    Patch(facecolor='royalblue', edgecolor='black', label='CYP1A2 Substrate (Variability Risk)'),
]

plt.legend(handles=legend_elements, loc='upper right', framealpha=0.95, ncol=1, fontsize=10)

plt.grid(axis='y', linestyle='--', alpha=0.5)
plt.tight_layout()

plt.show()