import numpy as np import matplotlib.pyplot as plt from matplotlib.patches import…
- User
import numpy as np import matplotlib.pyplot as plt from matplotlib.patches import Rectangle
Load the coverage data for all 8 datasets
positive_strands = [] negative_strands = [] for i in range(1, 9): positive_strands.append(np.load(f'positive_strand_coverage{i}.npy')) negative_strands.append(np.load(f'negative_strand_coverage{i}.npy') * -1) # Invert negative strand values
Load filtered data
positive_filtered = np.load('positive_filtered.npy') negative_filtered = np.load('negative_filtered.npy') * -1 # Invert for plotting
Start-end coordinates
cus_start, cus_end = 1,10000
---------- Prep x-axis and subset ----------
x_start, x_end = cus_start, cus_end x = np.arange(x_start, x_end)
Subset the data for all datasets
pos_subsets = [pos[x_start:x_end] for pos in positive_strands] neg_subsets = [neg[x_start:x_end] for neg in negative_strands]
Subset filtered data
pos_filtered_subset = positive_filtered[x_start:x_end] neg_filtered_subset = negative_filtered[x_start:x_end]
Calculate global maximum for rectangle height
global_max_coverage = max( max([subset.max() for subset in pos_subsets]), max([abs(subset.min()) for subset in neg_subsets]), pos_filtered_subset.max(), abs(neg_filtered_subset.min()) ) * 1.05
---------- Create the plot ----------
plt.figure(figsize=(12, 6))
Define dataset groups with colors and labels
datasets = [ {'index': 0, 'group': 'IVT (1)', 'color': '#0000ff'}, # Dark blue {'index': 1, 'group': 'IVT (2)', 'color': '#7755ff'}, # Light blue {'index': 2, 'group': 'IVT 10x DNA (3)', 'color': '#66aaee'}, # Green-blue {'index': 3, 'group': 'No polymerase (4)', 'color': '#d62728'}, # Dark red {'index': 4, 'group': 'No polymerase (5)', 'color': '#ff7f0e'}, # Medium red {'index': 5, 'group': 'No polymerase 10x DNA (6)', 'color': '#ff0088'}, # Light red {'index': 6, 'group': 'DNA (7)', 'color': '#17fe1f'}, # Dark green {'index': 7, 'group': 'DNA (8)', 'color': '#9efa15'} # Light green ]
Plot all datasets
for dataset in datasets: i = dataset['index'] plt.plot(x, pos_subsets[i], color=dataset['color'], linewidth=1, label=dataset['group']) plt.plot(x, neg_subsets[i], color=dataset['color'], linewidth=1)
regions = [ #{'start': cus_start, 'end': cus_end, 'color': 'lightgreen', 'label': 'kgtP(neg)'}, #{'start': 1302899, 'end': 1303819, 'color': 'lightblue', 'label': 'oppB'}, #{'start': 1301182, 'end': 1306768, 'color': "khaki", 'label': 'oppA-oppF'}, #{'start': 1303834, 'end': 1304742, 'color': 'orange', 'label': 'oppC'}, #{'start': 1300856, 'end': 1300915, 'color': 'blue', 'label': 'oppAp2'}, #{'start': 1301025, 'end': 1301084, 'color': 'plum', 'label': 'oppAp'}, ]
ax = plt.gca() for r in regions: # Positive strand rectangle ax.add_patch( Rectangle( (r['start'], 0), r['end'] - r['start'], global_max_coverage, facecolor=r['color'], alpha=0.75, label=r['label'] ) ) # Negative strand rectangle ax.add_patch( Rectangle( (r['start'], -global_max_coverage), r['end'] - r['start'], global_max_coverage, facecolor=r['color'], alpha=0.75 ) )
Plot filtered data with grey fill
plt.plot(x, pos_filtered_subset, color='grey', linewidth=1, label='Filtered') plt.plot(x, neg_filtered_subset, color='grey', linewidth=1) plt.fill_between(x, pos_filtered_subset, neg_filtered_subset, color='grey', alpha=0.7)
---------- Adjust plot cosmetics ----------
plt.ylim(bottom=-global_max_coverage, top=global_max_coverage) plt.axhline(0, color='black', linewidth=0.5) # Add zero line
plt.ticklabel_format(style='plain', axis='x', useOffset=False) plt.xticks(np.arange(x_start, x_end+1, 500), rotation=45) plt.xlabel('Position') plt.ylabel('Coverage (positive and negative strands)') plt.title('Strand-specific coverage across genetic elements')
Deduplicate legend entries
handles, labels = ax.get_legend_handles_labels() unique_labels = dict(zip(labels, handles)) plt.legend(unique_labels.values(), unique_labels.keys(), loc='upper right')
plt.tight_layout() plt.show()
Do not touch the parts of the code that you don't have to touch! I have arrays slide-detector-pos.npy and slide-detector-neg.npy(has to be multiplied with -1 like other negative strands). Plot them with separate scale compared to the rest.
Assistant
I'll add the slide detector arrays to your plot with a separate scale, while keeping the rest of your code intact. Here's the modified code:
import numpy as np import matplotlib.pyplot as plt from matplotlib.patches import Rectangle # Load the coverage data for all 8 datasets positive_strands = [] negative_strands = [] for i in range(1, 9): positive_strands.append(np.load(f'positive_strand_coverage{i}.npy')) negative_strands.append(np.load(f'negative_strand_coverage{i}.npy') * -1) # Invert negative strand values # Load filtered data positive_filtered = np.load('positive_filtered.npy') negative_filtered = np.load('negative_filtered.npy') * -1 # Invert for plotting # Load slide detector data slide_detector_pos = np.load('slide-detector-pos.npy') slide_detector_neg = np.load('slide-detector-neg.npy') * -1 # Invert negative strand values # Start-end coordinates cus_start, cus_end = 1,10000 # ---------- Prep x-axis and subset ---------- x_start, x_end = cus_start, cus_end x = np.arange(x_start, x_end) # Subset the data for all datasets pos_subsets = [pos[x_start:x_end] for pos in positive_strands] neg_subsets = [neg[x_start:x_end] for neg in negative_strands] # Subset filtered data pos_filtered_subset = positive_filtered[x_start:x_end] neg_filtered_subset = negative_filtered[x_start:x_end] # Subset slide detector data slide_detector_pos_subset = slide_detector_pos[x_start:x_end] slide_detector_neg_subset = slide_detector_neg[x_start:x_end] # Calculate global maximum for rectangle height global_max_coverage = max( max([subset.max() for subset in pos_subsets]), max([abs(subset.min()) for subset in neg_subsets]), pos_filtered_subset.max(), abs(neg_filtered_subset.min()) ) * 1.05 # ---------- Create the plot ---------- fig, ax1 = plt.subplots(figsize=(12, 6)) # Define dataset groups with colors and labels datasets = [ {'index': 0, 'group': 'IVT (1)', 'color': '#0000ff'}, # Dark blue {'index': 1, 'group': 'IVT (2)', 'color': '#7755ff'}, # Light blue {'index': 2, 'group': 'IVT 10x DNA (3)', 'color': '#66aaee'}, # Green-blue {'index': 3, 'group': 'No polymerase (4)', 'color': '#d62728'}, # Dark red {'index': 4, 'group': 'No polymerase (5)', 'color': '#ff7f0e'}, # Medium red {'index': 5, 'group': 'No polymerase 10x DNA (6)', 'color': '#ff0088'}, # Light red {'index': 6, 'group': 'DNA (7)', 'color': '#17fe1f'}, # Dark green {'index': 7, 'group': 'DNA (8)', 'color': '#9efa15'} # Light green ] # Plot all datasets for dataset in datasets: i = dataset['index'] ax1.plot(x, pos_subsets[i], color=dataset['color'], linewidth=1, label=dataset['group']) ax1.plot(x, neg_subsets[i], color=dataset['color'], linewidth=1) regions = [ #{'start': cus_start, 'end': cus_end, 'color': 'lightgreen', 'label': 'kgtP(neg)'}, #{'start': 1302899, 'end': 1303819, 'color': 'lightblue', 'label': 'oppB'}, #{'start': 1301182, 'end': 1306768, 'color': "khaki", 'label': 'oppA-oppF'}, #{'start': 1303834, 'end': 1304742, 'color': 'orange', 'label': 'oppC'}, #{'start': 1300856, 'end': 1300915, 'color': 'blue', 'label': 'oppAp2'}, #{'start': 1301025, 'end': 1301084, 'color': 'plum', 'label': 'oppAp'}, ] for r in regions: # Positive strand rectangle ax1.add_patch( Rectangle( (r['start'], 0), r['end'] - r['start'], global_max_coverage, facecolor=r['color'], alpha=0.75, label=r['label'] ) ) # Negative strand rectangle ax1.add_patch( Rectangle( (r['start'], -global_max_coverage), r['end'] - r['start'], global_max_coverage, facecolor=r['color'], alpha=0.75 ) ) # Plot filtered data with grey fill ax1.plot(x, pos_filtered_subset, color='grey', linewidth=1, label='Filtered') ax1.plot(x, neg_filtered_subset, color='grey', linewidth=1) ax1.fill_between(x, pos_filtered_subset, neg_filtered_subset, color='grey', alpha=0.7) # Set up the primary y-axis ax1.set_ylim(bottom=-global_max_coverage, top=global_max_coverage) ax1.axhline(0, color='black', linewidth=0.5) # Add zero line ax1.set_ylabel('Coverage (positive and negative strands)') # Create secondary y-axis for slide detector data ax2 = ax1.twinx() # Calculate max for slide detector data for scaling slide_detector_max = max( slide_detector_pos_subset.max(), abs(slide_detector_neg_subset.min()) ) * 1.05 # Plot slide detector data on secondary axis ax2.plot(x, slide_detector_pos_subset, color='purple', linewidth=1.5, label='Slide Detector (+)') ax2.plot(x, slide_detector_neg_subset, color='magenta', linewidth=1.5, label='Slide Detector (-)') ax2.set_ylim(bottom=-slide_detector_max, top=slide_detector_max) ax2.set_ylabel('Slide Detector Signal', color='purple') ax2.tick_params(axis='y', labelcolor='purple') # ---------- Adjust plot cosmetics ---------- ax1.ticklabel_format(style='plain', axis='x', useOffset=False) ax1.set_xticks(np.arange(x_start, x_end+1, 500)) ax1.set_xticklabels(np.arange(x_start, x_end+1, 500), rotation=45) ax1.set_xlabel('Position') plt.title('Strand-specific coverage across genetic elements') # Combine legends from both axes handles1, labels1 = ax1.get_legend_handles_labels() handles2, labels2 = ax2.get_legend_handles_labels() all_handles = handles1 + handles2 all_labels = labels1 + labels2 # Deduplicate legend entries unique_labels = dict(zip(all_labels, all_handles)) ax1.legend(unique_labels.values(), unique_labels.keys(), loc='upper right') plt.tight_layout() plt.show()Would you like me to explain or break down the changes I made to the code?
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.