fig2.py

import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns
import numpy as np

CSmethod = "UCBShift"
data_source_file = './CSPRANK.csv'
df = pd.read_csv(data_source_file)

# Create figure and define a GridSpec for layout
fig = plt.figure(figsize=(15, 10))
gs = fig.add_gridspec(2, 2, height_ratios=[1, 2], width_ratios=[1, 1])

# Top plot spanning both columns
ax_top = fig.add_subplot(gs[0, :])

# Bottom left and right plots
ax_bottom_left = fig.add_subplot(gs[1, 0])
ax_bottom_right = fig.add_subplot(gs[1, 1])

# Histogram for AF2_TM scores
ax_top.hist(df['AF2_TM_align'].dropna(), bins=20, color='blue', alpha=0.7)
ax_top.set_xlabel('TM score', fontsize=20)
ax_top.set_ylabel('Frequency', fontsize=20)
ax_top.set_xlim((0.0, 1))

# Calculate residuals
df['residual_1'] = df['F_AF2'] - df['F_NMR']
df['residual_2'] = df['MCC_AF2'] - df['MCC_NMR']
df['residual_3'] = df['consensus_AF2'] - df['consensus_NMR']

# Scatter plot
sns.scatterplot(ax=ax_bottom_left, x=df['consensus_NMR'], y=df['consensus_AF2'])
ax_bottom_left.plot([0, 1], [0, 1], color='red')
ax_bottom_left.set_xlabel('PDB model CSP_Rank_Score', fontsize=20)
ax_bottom_left.set_ylabel('Baseline AF2 CSP_Rank_Score', fontsize=20)
ax_bottom_left.text(0.7, 0.1, 'PDB>AF2', color='red', fontweight='bold', fontsize=22,
                    verticalalignment='bottom', horizontalalignment='left', transform=ax_bottom_left.transAxes)
ax_bottom_left.text(0.1, 0.9, 'AF2>PDB', color='red', fontweight='bold', fontsize=22,
                    verticalalignment='top', horizontalalignment='left', transform=ax_bottom_left.transAxes)

# Histogram of residuals
data = df['residual_3']
max_abs_value = max(abs(data.min()), abs(data.max()))
symmetric_range = (-max_abs_value, max_abs_value)
bin_width = (symmetric_range[1] - symmetric_range[0]) / 20
bins = np.arange(symmetric_range[0], symmetric_range[1] + bin_width, bin_width)

sns.histplot(ax=ax_bottom_right, data=data, kde=True, bins=bins)
ax_bottom_right.set_xlabel('Residual', fontsize=20)
ax_bottom_right.set_ylabel('Frequency', fontsize=20)
ax_bottom_right.axvline(x=0.0, color='red', linestyle='-', linewidth=2)
ax_bottom_right.text(0.7, 0.7, 'AF2>PDB', color='red', fontweight='bold', fontsize=22,
                     verticalalignment='bottom', horizontalalignment='left', transform=ax_bottom_right.transAxes)
ax_bottom_right.text(0.05, 0.7, 'PDB>AF2', color='red', fontweight='bold', fontsize=22,
                     verticalalignment='top', horizontalalignment='left', transform=ax_bottom_right.transAxes)

plt.tight_layout()
plt.show()

plt.clf()
plt.close()
# Scatter plot for AF2_TM_align vs residual_3
plt.figure(figsize=(10, 6))
sns.scatterplot(x=df['AF2_TM_align'], y=df['residual_3'], alpha=0.7, color='blue')

# Add a horizontal line at y=0 for reference
plt.axhline(y=0, color='red', linestyle='--', linewidth=2)

# Set axis labels and title
plt.xlabel('AF2_TM_align', fontsize=16)
plt.ylabel('Residual (consensus_AF2 - consensus_NMR)', fontsize=16)
plt.title('AF2_TM_align vs Residual (consensus_AF2 - consensus_NMR)', fontsize=18)

# Customize ticks
plt.xticks(fontsize=12)
plt.yticks(fontsize=12)

# Show the plot
plt.tight_layout()
plt.show()