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
Load slide detector data
prefix_file="sliding_scores-full-offset-cutoff7.02" slide_detector_pos = np.load(prefix_file+'-pos.npy') slide_detector_neg = np.load(prefix_file+'-neg.npy') * -1 # Invert negative strand values
Start-end coordinates
cus_start, cus_end = 3791355 - 5000, 3792637 + 5000# 1300856-150,1306768+150
---------- 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': 3791355, 'end': 3792551, 'color': 'lightgreen', 'label': 'kbl'}, {'start': 3792553, 'end': 3792637, 'color': 'lightblue', 'label': 'Promoter kblp'}, #{'start': 3913850, 'end': 3913876, 'color': 'khaki', 'label': 'TIR'}, #{'start': 3913803, 'end': 3913858, 'color': 'plum', 'label': 'BCD'}, {'start': 3792553, 'end': 3792577, 'color': 'red', 'label': 'Transcription start'}, #{'start': 1301182, 'end': 1302813, 'color': 'lightgreen', 'label': 'oppA'}, #{'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
Lines for the peaks and labels
ax2.plot(x, slide_detector_pos_subset, color='purple', linewidth=1, label='Matrix s70 Detector (+)') ax2.plot(x, slide_detector_neg_subset, color='magenta', linewidth=1, label='Matrix s70 Detector (-)')
Fill between the lines and the x-axis (y=0)
ax2.fill_between(x, slide_detector_pos_subset, 0, color='purple', alpha=0.3) ax2.fill_between(x, slide_detector_neg_subset, 0, color='magenta', alpha=0.3)
ax2.set_ylim(bottom=-slide_detector_max, top=slide_detector_max) ax2.set_ylabel('-10 box PWM score', color='purple') ax2.tick_params(axis='y', labelcolor='purple') ax2.axhline(0, color='purple', linestyle='--', linewidth=0.5, alpha=0.5) # Optional: add a zero line for the secondary axis
---------- 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
Ensure that labels from plot() are used for the legend, not fill_between() by placing plot() calls first with labels.
unique_entries = {} for handle, label in zip(all_handles, all_labels): if label not in unique_entries: unique_entries[label] = handle
ax1.legend( unique_entries.values(), unique_entries.keys(), loc='center left', bbox_to_anchor=(1.1, 0.5), borderaxespad=0, frameon=True ).set_zorder(1000) # Ensure legend is on top
plt.tight_layout(rect=[0, 0, 0.85, 1]) # Adjust rect to make space for the legend if it's outside plt.show()
I have a file named "sega007.fasta" with genome sequence in fasta format. Show the bases on the x axis, I want to see letters
- Assistant
Below is a minimal, drop-in addition that
- reads the FASTA file,
- extracts the reference sequence for the window you are already plotting (
x_start : x_end), - puts the individual bases on a second x–axis.
Because showing thousands of letters would be unreadable, the snippet automatically refuses to draw the sequence if the window is larger than 200 nt (you can change that limit).
# ─────────── Add right after you define x_start / x_end ──────────── # # 1. Read the genome sequence # (pip install biopython if you don’t have it yet) from Bio import SeqIO fasta_path = "sega007.fasta" seq_record = next(SeqIO.parse(fasta_path, "fasta")) genome_seq = str(seq_record.seq).upper() # 2. Slice the part that corresponds to the plot seq_slice = genome_seq[x_start : x_end] # 0-based coordinates! window_len = len(seq_slice) # 3. Decide whether we can sensibly draw every single base MAX_BASES_ON_AXIS = 200 # ← raise this if you dare 😅 show_letters = window_len <= MAX_BASES_ON_AXIS# ─────────── Keep the rest of your plotting code exactly as it is ─────────── # ... # plt.title('Strand-specific coverage across genetic elements') # handles1, labels1 = ax1.get_legend_handles_labels() # ... # ax1.legend(...) # --------------------------------------------------------------------------- # ─────────── Add the sequence letters on a second x-axis ─────────── if show_letters: # A twin x-axis that shares the same data limits ax_seq = ax1.twiny() # Match limits of the main axis ax_seq.set_xlim(ax1.get_xlim()) # Put one tick per base ax_seq.set_xticks(np.arange(x_start, x_end)) ax_seq.set_xticklabels(list(seq_slice), fontfamily='monospace', fontsize=7, rotation=90) # Cosmetic spacing ax_seq.tick_params(axis='x', which='major', pad=5) ax_seq.set_xlabel('Reference base') else: print(f"Window is {window_len} bp – too wide to label every base. " f"Zoom in (<={MAX_BASES_ON_AXIS} nt) if you want letters.")📌 Things to keep in mind
• Coordinate system: Python strings are 0-based, while your genomic positions are usually 1-based.
If yourx_start/x_endvariables are 1-based, subtract 1 when slicing:seq_slice = genome_seq[x_start-1 : x_end] # if positions are 1-based• If you want colour-coded letters (A: green, T: red, etc.) you can iterate over the slice and place
ax_seq.text()calls instead of usingset_xticklabels().• The extra axis will need vertical space. If letters overlap with the legend, increase the figure height or move the legend.
That’s all you need—run the script, zoom into any ≤ 200 bp window, and the bases will show up on the new axis.
- User
Full Code. NOW!
- Assistant
Here’s a single, copy-paste-and-run script that
• loads all eight coverage tracks, the filtered data and the sliding-window detector,
• reads the reference FASTA,
• plots everything exactly as before, plus a second x-axis that shows the actual bases (letters) when you zoom into a window of reasonable length (≤ 200 nt by default).#!/usr/bin/env python3 # -*- coding: utf-8 -*- # ------------------------------------------------------------ # Imports # ------------------------------------------------------------ import numpy as np import matplotlib.pyplot as plt from matplotlib.patches import Rectangle # -> Only needed for the sequence axis from Bio import SeqIO # pip install biopython # ------------------------------------------------------------ # I/O paths # ------------------------------------------------------------ fasta_path = "sega007.fasta" coverage_prefix_pos = "positive_strand_coverage" coverage_prefix_neg = "negative_strand_coverage" filtered_pos_file = "positive_filtered.npy" filtered_neg_file = "negative_filtered.npy" slide_prefix = "sliding_scores-full-offset-cutoff7.02" # <-- your PWM file prefix # ------------------------------------------------------------ # Genomic window you want to see # ------------------------------------------------------------ cus_start, cus_end = 3791355 - 5000, 3792637 + 5000 # edit as required x_start, x_end = cus_start, cus_end # keep shorthand # ------------------------------------------------------------ # Load coverage data (8 experiments) # ------------------------------------------------------------ positive_strands = [np.load(f"{coverage_prefix_pos}{i}.npy") for i in range(1, 9)] negative_strands = [np.load(f"{coverage_prefix_neg}{i}.npy") * -1 for i in range(1, 9)] # Sub-select the window x = np.arange(x_start, x_end) pos_subsets = [pos[x_start:x_end] for pos in positive_strands] neg_subsets = [neg[x_start:x_end] for neg in negative_strands] # ------------------------------------------------------------ # Filtered coverage & PWM detector # ------------------------------------------------------------ positive_filtered = np.load(filtered_pos_file) negative_filtered = np.load(filtered_neg_file) * -1 pos_filtered_subset = positive_filtered[x_start:x_end] neg_filtered_subset = negative_filtered[x_start:x_end] slide_detector_pos = np.load(slide_prefix + "-pos.npy") slide_detector_neg = np.load(slide_prefix + "-neg.npy") * -1 slide_detector_pos_subset = slide_detector_pos[x_start:x_end] slide_detector_neg_subset = slide_detector_neg[x_start:x_end] # ------------------------------------------------------------ # Reference sequence (FASTA) – for the base letters axis # ------------------------------------------------------------ seq_record = next(SeqIO.parse(fasta_path, "fasta")) genome_seq = str(seq_record.seq).upper() # WARNING: # If your genomic positions are 1-based, uncomment the next line # x_start -= 1; x_end -= 1 seq_slice = genome_seq[x_start:x_end] window_len = len(seq_slice) MAX_BASES_ON_AXIS = 200 # draw letters only if window ≤ this # ------------------------------------------------------------ # Plotting # ------------------------------------------------------------ fig, ax1 = plt.subplots(figsize=(12, 6)) # ---------- Plot every dataset ---------- datasets = [ {'index': 0, 'group': 'IVT (1)', 'color': '#0000ff'}, {'index': 1, 'group': 'IVT (2)', 'color': '#7755ff'}, {'index': 2, 'group': 'IVT 10x DNA (3)', 'color': '#66aaee'}, {'index': 3, 'group': 'No polymerase (4)', 'color': '#d62728'}, {'index': 4, 'group': 'No polymerase (5)', 'color': '#ff7f0e'}, {'index': 5, 'group': 'No polymerase 10x DNA (6)','color': '#ff0088'}, {'index': 6, 'group': 'DNA (7)', 'color': '#17fe1f'}, {'index': 7, 'group': 'DNA (8)', 'color': '#9efa15'} ] for ds in datasets: i = ds['index'] ax1.plot(x, pos_subsets[i], color=ds['color'], linewidth=1, label=ds['group']) ax1.plot(x, neg_subsets[i], color=ds['color'], linewidth=1) # ---------- Regions (rectangles) ---------- regions = [ {'start': 3791355, 'end': 3792551, 'color': 'lightgreen', 'label': 'kbl'}, {'start': 3792553, 'end': 3792637, 'color': 'lightblue', 'label': 'Promoter kblp'}, {'start': 3792553, 'end': 3792577, 'color': 'red', 'label': 'Transcription start'}, ] # Height for the rectangles = a bit more than the largest coverage signal 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 for r in regions: # positive strand rect 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 rect ax1.add_patch(Rectangle( (r['start'], -global_max_coverage), r['end'] - r['start'], global_max_coverage, facecolor=r['color'], alpha=0.75 )) # ---------- Filtered coverage ---------- 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) # Y-limits primary axis ax1.set_ylim(-global_max_coverage, global_max_coverage) ax1.axhline(0, color='black', linewidth=0.5) ax1.set_ylabel('Coverage (± strands)') # ---------- Secondary y-axis (PWM detector) ---------- ax2 = ax1.twinx() slide_detector_max = max( slide_detector_pos_subset.max(), abs(slide_detector_neg_subset.min()) ) * 1.05 ax2.plot(x, slide_detector_pos_subset, color='purple', linewidth=1, label='Matrix s70 (+)') ax2.plot(x, slide_detector_neg_subset, color='magenta', linewidth=1, label='Matrix s70 (-)') ax2.fill_between(x, slide_detector_pos_subset, 0, color='purple', alpha=0.3) ax2.fill_between(x, slide_detector_neg_subset, 0, color='magenta', alpha=0.3) ax2.set_ylim(-slide_detector_max, slide_detector_max) ax2.set_ylabel('-10 box PWM score', color='purple') ax2.tick_params(axis='y', labelcolor='purple') ax2.axhline(0, color='purple', linestyle='--', linewidth=0.5, alpha=0.5) # ---------- 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 & de-duplicate legends handles1, labels1 = ax1.get_legend_handles_labels() handles2, labels2 = ax2.get_legend_handles_labels() uniq = {} for h, l in zip(handles1 + handles2, labels1 + labels2): if l not in uniq: uniq[l] = h ax1.legend(uniq.values(), uniq.keys(), loc='center left', bbox_to_anchor=(1.02, 0.5'), frameon=True).set_zorder(1000) plt.tight_layout(rect=[0, 0, 0.87, 1]) # ------------------------------------------------------------ # EXTRA x-axis with base letters (only if window ≤ MAX_BASES_ON_AXIS) # ------------------------------------------------------------ if window_len <= MAX_BASES_ON_AXIS: ax_seq = ax1.twiny() ax_seq.set_xlim(ax1.get_xlim()) ax_seq.set_xticks(np.arange(x_start, x_end)) ax_seq.set_xticklabels(list(seq_slice), fontfamily='monospace', fontsize=7, rotation=90) ax_seq.tick_params(axis='x', which='major', pad=5) ax_seq.set_xlabel('Reference base') else: print(f"Window length = {window_len} bp → too wide for base display " f"(limit = {MAX_BASES_ON_AXIS}). Zoom in if you want letters.") plt.show()What changed compared with your previous version?
- Added Biopython import & FASTA reader (
SeqIO.parse). - Extracted the slice
seq_slicefor the current window. - Built a second x-axis (
ax_seq) that shows one tick per base, but only if the window is reasonably small (≤ 200 nt by default).
AdjustMAX_BASES_ON_AXISas you see fit. - Minor refactor so everything lives in a single, self-contained file.
Enjoy!
- Added Biopython import & FASTA reader (
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.