tooluniverse-crispr-screen-analysis

Phase 1: Data Import & sgRNA Count Processing

Load sgRNA Count Matrix

import pandas as pd
import numpy as np

def load_sgrna_counts(counts_file):
    """
    Load sgRNA count matrix from MAGeCK format or generic TSV.

    Expected format:
    sgRNA | Gene | Sample1 | Sample2 | Sample3 | ...
    sgRNA_1 | BRCA1 | 1500 | 1200 | 1100 | ...
    sgRNA_2 | BRCA1 | 1800 | 1500 | 1400 | ...
    """
    counts = pd.read_csv(counts_file, sep='\t')

    # Validate required columns
    required_cols = ['sgRNA', 'Gene']
    if not all(col in counts.columns for col in required_cols):
        raise ValueError(f"Missing required columns: {required_cols}")

    # Extract sample columns
    sample_cols = [col for col in counts.columns if col not in ['sgRNA', 'Gene']]

    # Create count matrix
    count_matrix = counts[sample_cols].copy()
    count_matrix.index = counts['sgRNA']

    # Gene mapping
    sgrna_to_gene = dict(zip(counts['sgRNA'], counts['Gene']))

    metadata = {
        'n_sgrnas': len(counts),
        'n_genes': counts['Gene'].nunique(),
        'n_samples': len(sample_cols),
        'sample_names': sample_cols,
        'sgrna_to_gene': sgrna_to_gene
    }

    return count_matrix, metadata

## Load counts

counts, meta = load_sgrna_counts("sgrna_counts.txt")
print(f"Loaded {meta['n_sgrnas']} sgRNAs targeting {meta['n_genes']} genes across {meta['n_samples']} samples")
python
def create_design_matrix(sample_names, conditions, timepoints=None):
    """
    Create experimental design linking samples to conditions.

    Example:
    Sample | Condition | Timepoint | Replicate
    T0_rep1 | baseline | 0 | 1
    T14_rep1 | treatment | 14 | 1
    """
    design = pd.DataFrame({
        'Sample': sample_names,
        'Condition': conditions
    })

    if timepoints is not None:
        design['Timepoint'] = timepoints

    # Auto-detect replicates
    design['Replicate'] = design.groupby('Condition').cumcount() + 1

    return design

## Example usage

sample_names = ['T0_rep1', 'T0_rep2', 'T14_rep1', 'T14_rep2', 'T14_rep3']
conditions = ['baseline', 'baseline', 'treatment', 'treatment', 'treatment']
design = create_design_matrix(sample_names, conditions)