Bio Workflows Crispr Screen Pipeline Agent Skill

                    Library Design ([[library-design]])
                              |
                              v
                FASTQ Files -> mageck count -> count matrix
                              |
                              v
                Six-Stage QC ([[screen-qc]])
                              |
        +---------------------+---------------------+
        |                                            |
        v                                            v
  Cancer cell line?                          Non-cancer?
  Apply CN correction                        No CN correction needed
  ([[copy-number-correction]])
        |                                            |
        +---------------------+---------------------+
                              v
                  Multi-batch? Apply batch covariate
                  ([[batch-correction]])
                              |
                              v
                 Pick hit-calling method by design ([[hit-calling]])
                              |
        +-----------+---------+---------+-----------+-----------+
        |           |         |         |           |           |
        v           v         v         v           v           v
    2-cond       Time      Drug      Essential   Multi-       Specialized
    MAGeCK RRA   MAGeCK    drugZ     BAGEL2      screen       (PE/BE/SC/
                 MLE                              JACKS or     in vivo/
                                                  Chronos      combinat)
        |           |         |         |           |           |
        +-----------+---------+---------+-----------+-----------+
                              v
                   Tier-based consensus
                              v
                Orthogonal validation

mageck count \
    --list-seq library.csv \
    --sample-label Plasmid,Day0,Veh_r1,Veh_r2,Drug_r1,Drug_r2 \
    --fastq Plasmid.fq.gz Day0.fq.gz Veh_r1.fq.gz Veh_r2.fq.gz Drug_r1.fq.gz Drug_r2.fq.gz \
    --norm-method median \
    --output-prefix experiment \
    --trim-5 CACCG

import pandas as pd
import numpy as np
from sklearn.metrics import precision_recall_curve, auc

counts = pd.read_csv('experiment.count.txt', sep='\t', index_col=0)
genes = counts['Gene']
count_matrix = counts.drop('Gene', axis=1)

def gini(x):
    x = np.sort(x[x > 0].astype(float))
    if x.size == 0:
        return np.nan
    n = x.size
    cumx = np.cumsum(x)
    return (n + 1 - 2 * np.sum(cumx) / cumx[-1]) / n

per_sample = pd.DataFrame({
    'pct_zero': (count_matrix == 0).sum() / len(count_matrix) * 100,
    'gini': count_matrix.apply(gini),
    'reads_per_sgrna': count_matrix.sum() / len(count_matrix),
})

log_counts = np.log10(count_matrix + 1)
pearson = log_counts.corr()
print(per_sample)
print('Replicate Pearson:', pearson.values[pearson.values < 1].mean())

library(CRISPRcleanR)
data(KY_Library_v1.0)
norm <- ccr.NormfoldChanges(read.table('experiment.count.txt', header=TRUE, sep='\t'),
                              min_reads = 30, EXPname = 'screen',
                              libraryAnnotation = KY_Library_v1.0)
gw_lfc <- ccr.logFCs2chromPos(norm$norm_fold_changes, KY_Library_v1.0)
cleaned <- ccr.GWclean(gw_lfc, display = TRUE, label = 'screen')
corrected_counts <- ccr.correctCounts(my_screen = norm, correction = cleaned,
                                        outprefix = 'screen_cleanr',
                                        libraryAnnotation = KY_Library_v1.0)
# Feed corrected counts into MAGeCK / BAGEL2 / drugZ downstream

mageck test \
    --count-table experiment.count.txt \
    --treatment-id Day14_r1,Day14_r2,Day14_r3 \
    --control-id Day0 \
    --norm-method median \
    --output-prefix essentiality_rra

BAGEL.py fc -i experiment.count.txt -o foldchange.txt -c Day0 --min-reads 30
BAGEL.py bf -i foldchange.txt -o bayes_factor.txt -e CEGv2.txt -n NEGv1.txt \
    -c Day14_r1,Day14_r2,Day14_r3 -k 1000

mageck mle --count-table experiment.count.txt --design-matrix design.txt \
    --output-prefix timecourse_mle --norm-method median

python drugz.py \
    -i experiment.count.txt \
    -o drugz_output.txt \
    -c Veh_r1,Veh_r2,Veh_r3 \
    -x Drug_r1,Drug_r2,Drug_r3 \
    -p 5

python run_JACKS.py experiment.count.txt replicatemap.txt guidemap.txt \
    --rep_hdr Replicate --sample_hdr Sample --ctrl_sample_hdr Control \
    --sgrna_hdr sgRNA --gene_hdr Gene --outprefix jacks_out --apply_w_hp

import chronos
model = chronos.Chronos(sequence_map=sequence_map, guide_gene_map=guide_gene_map,
                          reads=counts_df, copy_number=cn_df)
model.train(n_steps=2000)
gene_effects = model.gene_effect()

mageck = pd.read_csv('essentiality_rra.gene_summary.txt', sep='\t')[['id', 'neg|fdr']].rename(
    columns={'id': 'gene', 'neg|fdr': 'mageck_neg_fdr'})
bagel = pd.read_csv('bayes_factor.txt', sep='\t')[['GENE', 'BF']].rename(
    columns={'GENE': 'gene', 'BF': 'bagel_bf'})
drugz_df = pd.read_csv('drugz_output.txt', sep='\t')[['GENE', 'fdr_synth']].rename(
    columns={'GENE': 'gene', 'fdr_synth': 'drugz_synth_fdr'})

merged = mageck.merge(bagel, on='gene', how='outer').merge(drugz_df, on='gene', how='outer')
merged['mageck_hit'] = merged['mageck_neg_fdr'] < 0.05
merged['bagel_hit'] = merged['bagel_bf'] > 6
merged['drugz_hit'] = merged['drugz_synth_fdr'] < 0.05
merged['tier'] = merged[['mageck_hit', 'bagel_hit', 'drugz_hit']].astype(int).sum(axis=1)
tier1 = merged[merged['tier'] >= 3]
tier2 = merged[merged['tier'] == 2]

import matplotlib.pyplot as plt
fig, ax = plt.subplots(figsize=(10, 8))
gene_summary = pd.read_csv('essentiality_rra.gene_summary.txt', sep='\t')
sig = gene_summary['neg|fdr'] < 0.05
ax.scatter(gene_summary.loc[~sig, 'neg|lfc'],
            -np.log10(gene_summary.loc[~sig, 'neg|fdr'].clip(lower=1e-10)),
            c='lightgray', alpha=0.5, s=10)
ax.scatter(gene_summary.loc[sig, 'neg|lfc'],
            -np.log10(gene_summary.loc[sig, 'neg|fdr'].clip(lower=1e-10)),
            c='red', alpha=0.7, s=18)
ax.axhline(-np.log10(0.05), ls='--', c='black', lw=0.5)
ax.set_xlabel('Log2 Fold Change')
ax.set_ylabel('-Log10(FDR)')
plt.savefig('volcano.png', dpi=150)