import numpy as np import pandas as pd import gzip Load coverage data with…
- User
import numpy as np import pandas as pd import gzip
Load coverage data
with gzip.open('sample_001_coverage_unique.txt.gz', 'rt') as f:
data = np.loadtxt(f)Read the genes CSV file
genes_df = pd.read_csv('genes.csv', sep=';')
Create a list to store all regions (genes and intergenic)
all_regions = []
Intergenic region counter
intergenic_counter = 1
Add first intergenic region (if exists)
first_gene_start = genes_df.iloc[0]['starting bp'] if first_gene_start > 1: first_intergenic_avg = np.mean(data[0:first_gene_start-1]) all_regions.append([f'INTERGENIC{intergenic_counter:05d}', 1, first_gene_start-1, first_intergenic_avg]) intergenic_counter += 1
Process all genes and intergenic regions between them
for i in range(len(genes_df)): # Current gene curr_gene = genes_df.iloc[i] start = curr_gene['starting bp'] - 1 # Convert to 0-based end = curr_gene['ending bp']
# Calculate and add gene average gene_avg = np.mean(data[start:end]) all_regions.append([curr_gene['Gene name'], curr_gene['starting bp'], curr_gene['ending bp'], gene_avg]) # Add intergenic region after current gene (if not last gene) if i < len(genes_df) - 1: next_gene = genes_df.iloc[i+1] intergenic_start = curr_gene['ending bp'] + 1 intergenic_end = next_gene['starting bp'] - 1 if intergenic_end >= intergenic_start: # Check if there's a gap intergenic_avg = np.mean(data[curr_gene['ending bp']:next_gene['starting bp']-1]) all_regions.append([f'INTERGENIC{intergenic_counter:05d}', intergenic_start, intergenic_end, intergenic_avg]) intergenic_counter += 1Add final intergenic region (if exists)
last_gene_end = genes_df.iloc[-1]['ending bp'] if last_gene_end < len(data): final_intergenic_avg = np.mean(data[last_gene_end:]) all_regions.append([f'INTERGENIC{intergenic_counter:05d}', last_gene_end + 1, len(data), final_intergenic_avg])
Create DataFrame and save to CSV
results_df = pd.DataFrame(all_regions, columns=['Gene name', 'starting bp', 'ending bp', 'average']) results_df.to_csv('genes_averages.csv', sep=';', index=False)
Add the ability to pass another file instead of sample_001_coverage_unique.txt.gz. Keep default(if not specified) as sample_001_coverage_unique.txt.gz. Do not change anything else.
- Assistant
Below is the original script with one (and only one) functional addition:
an optional command‑line argument that lets you point to a different coverage file while keepingsample_001_coverage_unique.txt.gzas the default.#!/usr/bin/env python3 import argparse # <— NEW import numpy as np import pandas as pd import gzip # ------------- NEW: parse optional coverage‑file argument ------------- parser = argparse.ArgumentParser( description="Compute average coverage for genes and intergenic regions" ) parser.add_argument( "-c", "--coverage", default="sample_001_coverage_unique.txt.gz", help="Path to the coverage file (.txt.gz). " "Defaults to sample_001_coverage_unique.txt.gz" ) args = parser.parse_args() coverage_path = args.coverage # --------------------------------------------------------------------- # Load coverage data with gzip.open(coverage_path, 'rt') as f: # ← only change: use coverage_path data = np.loadtxt(f) # Read the genes CSV file genes_df = pd.read_csv('genes.csv', sep=';') # Create a list to store all regions (genes and intergenic) all_regions = [] # Intergenic region counter intergenic_counter = 1 # Add first intergenic region (if exists) first_gene_start = genes_df.iloc[0]['starting bp'] if first_gene_start > 1: first_intergenic_avg = np.mean(data[0:first_gene_start-1]) all_regions.append([ f'INTERGENIC{intergenic_counter:05d}', 1, first_gene_start-1, first_intergenic_avg ]) intergenic_counter += 1 # Process all genes and intergenic regions between them for i in range(len(genes_df)): # Current gene curr_gene = genes_df.iloc[i] start = curr_gene['starting bp'] - 1 # Convert to 0-based end = curr_gene['ending bp'] # Calculate and add gene average gene_avg = np.mean(data[start:end]) all_regions.append([ curr_gene['Gene name'], curr_gene['starting bp'], curr_gene['ending bp'], gene_avg ]) # Add intergenic region after current gene (if not last gene) if i < len(genes_df) - 1: next_gene = genes_df.iloc[i+1] intergenic_start = curr_gene['ending bp'] + 1 intergenic_end = next_gene['starting bp'] - 1 if intergenic_end >= intergenic_start: # Check if there's a gap intergenic_avg = np.mean( data[curr_gene['ending bp']:next_gene['starting bp']-1] ) all_regions.append([ f'INTERGENIC{intergenic_counter:05d}', intergenic_start, intergenic_end, intergenic_avg ]) intergenic_counter += 1 # Add final intergenic region (if exists) last_gene_end = genes_df.iloc[-1]['ending bp'] if last_gene_end < len(data): final_intergenic_avg = np.mean(data[last_gene_end:]) all_regions.append([ f'INTERGENIC{intergenic_counter:05d}', last_gene_end + 1, len(data), final_intergenic_avg ]) # Create DataFrame and save to CSV results_df = pd.DataFrame( all_regions, columns=['Gene name', 'starting bp', 'ending bp', 'average'] ) results_df.to_csv('genes_averages.csv', sep=';', index=False)Usage examples:
-
Default file (same behavior as before):
python script.py -
Custom coverage file:
python script.py -c my_other_sample.txt.gz
-
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.