In Silico Perturbation Oracle

Quick Start

# Single gene knockout prediction
python scripts/main.py \
    --model geneformer \
    --genes TP53,BRCA1,EGFR \
    --cell-type "lung_adenocarcinoma" \
    --output ./results/
Batch target screening
python scripts/main.py \
    --model scgpt \
    --genes-file ./target_genes.txt \
    --cell-type "hepatocyte" \
    --top-k 20 \
    --pathways KEGG,GO_BP \
    --output ./results/

Python API

from in_silico_perturbation_oracle import PerturbationOracle
Initialize Oracle
oracle = PerturbationOracle(
    model_name="geneformer",
    cell_type="cardiomyocyte"
)
Execute virtual knockout
results = oracle.predict_knockout(
    genes=["MYC", "KRAS", "BCL2"],
    perturbation_type="complete_ko",  # Complete knockout
    n_permutations=100
)
Get differentially expressed genes
degs = results.get_differential_expression(
    pval_threshold=0.05,
    logfc_threshold=1.0
)
Pathway enrichment analysis
pathways = results.enrich_pathways(
    database=["KEGG", "GO_BP"],
    top_n=10
)
Target scoring
target_scores = results.score_targets()
print(target_scores.head(10))

# Python dependencies
pip install -r requirements.txt

1. Experimental Design Recommendations

# Recommended: Combinatorial knockout screening
results = oracle.predict_combinatorial_ko(
    gene_pairs=[
        ("BCL2", "MCL1"),
        ("PIK3CA", "PTEN")
    ],
    synergy_threshold=0.3
)
Recommended: Dose-response simulation
results = oracle.predict_dose_response(
    gene="MTOR",
    doses=[0.25, 0.5, 0.75, 0.9],  # Partial knockout ratios
)

2. Wet Lab Integration

# Export wet lab validation recommendations
oracle.export_validation_guide(
    top_targets=10,
    include_controls=True,
    format="lab_protocol"
)

3. Quality Control