Environmental Hazard: Aquatic Toxicity (Sheepshead Minnow)

DrugBank database
MolPort database
Python script number 107 to build the frequency distribution graph of the Sheepshead_minnow_toxicity parameter on DrugBank molecules.
import matplotlib.pyplot as plt
import matplotlib.colors as mcolors
from matplotlib.patches import Patch
import numpy as np
from scipy.interpolate import PchipInterpolator

# 1. PASTE YOUR DATA HERE (Sheepshead_minnow_toxicity)
datos_crudos = """Bin Center	% Frequency
0.0	0.0
0.05	3.69426751592357
0.1	12.0169851380042
0.15	9.55414012738854
0.2	5.05307855626327
0.25	5.18046709129512
0.3	4.67091295116773
0.35	4.37367303609342
0.4	4.45859872611465
0.45	3.94904458598726
0.5	3.86411889596603
0.55	4.20382165605096
0.6	4.03397027600849
0.65	4.28874734607219
0.7	5.6900212314225
0.75	4.84076433121019
0.8	6.28450106157113
0.85	5.81740976645435
0.9	5.05307855626327
0.95	2.80254777070064
1	0.169851380042463"""

# 2. AUTOMATIC PROCESSING
lineas = datos_crudos.strip().split('\n')[1:] 
bins_array = []
freq_array = []

for linea in lineas:
    b, f = linea.strip().split() 
    bins_array.append(float(b))
    freq_array.append(float(f))

bins = np.array(bins_array)
freq = np.array(freq_array)

mean_val = np.average(bins, weights=freq)

interpolator = PchipInterpolator(bins, freq)
x_fit = np.linspace(min(bins), max(bins), 500)
y_fit = interpolator(x_fit)
y_fit = np.clip(y_fit, 0, None)

def get_colors(b_array):
    return ['#008000' if b < 0.4 else '#FFD700' if b <= 0.7 else '#B22222' for b in b_array]

colors_hex = get_colors(bins)
face_colors = [mcolors.to_rgba(c, alpha=0.60) for c in colors_hex]
edge_colors = [mcolors.to_rgba(c, alpha=0.90) for c in colors_hex]

# 3. CREATION OF THE GRAPH
plt.figure(figsize=(7, 6))

plt.bar(bins, freq, width=0.04, color=face_colors, edgecolor=edge_colors, linewidth=1.5, zorder=2)

plt.xlabel('Sheepshead Minnow Toxicity Probability (LC50 < 100 ppm)', fontsize=12)
plt.ylabel('% Frequency', fontsize=12)
plt.title('Environmental Hazard: Aquatic Toxicity (Sheepshead Minnow)', fontsize=14)

legend_elements = [
    Patch(facecolor=mcolors.to_rgba('#008000', 0.6), edgecolor='#008000', label='Low Toxicity / Inert (< 0.4)'),
    Patch(facecolor=mcolors.to_rgba('#FFD700', 0.6), edgecolor='#FFD700', label='Moderate Hazard (0.4 - 0.7)'),
    Patch(facecolor=mcolors.to_rgba('#B22222', 0.6), edgecolor='#B22222', label='High Lethality Risk (> 0.7)'),
]
plt.legend(handles=legend_elements, loc='upper right', framealpha=0.95, fontsize=10)

plt.grid(axis='y', linestyle=':', alpha=0.7, zorder=0)
plt.xlim(0, 1.05)
plt.ylim(0, max(freq) * 1.2) 
plt.tight_layout()

plt.show()