In Silico Perturbation Oracle

# Basic dependencies
pip install torch transformers scanpy scvi-tools

# Bioinformatics tools
pip install gseapy enrichrpy

# Model-specific dependencies
pip install geneformer scgpt

# 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/

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))

# Recommended naming format
epithelial_cells:
  - lung_epithelial
  - intestinal_epithelial
  - mammary_epithelial

immune_cells:
  - t_cell_cd4
  - t_cell_cd8
  - b_cell
  - macrophage
  - dendritic_cell

specialized_cells:
  - cardiomyocyte
  - hepatocyte
  - neuron_excitatory
  - fibroblast
  - endothelial_cell

{
  "KEGG": {
    "pathways": [
      {
        "name": "p53_signaling_pathway",
        "p_value": 0.001,
        "enrichment_ratio": 3.5,
        "genes": ["CDKN1A", "GADD45A", "MDM2"]
      }
    ]
  }
}

in-silico-perturbation-oracle/
├── configs/
│   ├── geneformer_config.yaml    # Geneformer model configuration
│   ├── scgpt_config.yaml         # scGPT model configuration
│   └── cell_type_mapping.yaml    # Cell type mapping
├── data/
│   ├── reference_expression/     # Reference expression profiles
│   └── gene_annotations/         # Gene annotation files
├── models/
│   ├── geneformer_adapter.py     # Geneformer interface
│   ├── scgpt_adapter.py          # scGPT interface
│   └── base_model.py             # Base model abstract class
├── scripts/
│   └── main.py                   # Main entry script
├── utils/
│   ├── differential_expression.py  # Differential expression analysis
│   ├── pathway_enrichment.py       # Pathway enrichment
│   ├── target_scoring.py           # Target scoring
│   └── visualization.py            # Visualization tools
└── examples/
    ├── single_knockout_example.py
    ├── batch_screening_example.py
    └── cancer_targets_example.py

Overall_Score = w₁ × Efficacy + w₂ × Safety + w₃ × Druggability + w₄ × Novelty

Where:
- Efficacy: Based on number of DEGs and pathway change magnitude
- Safety: Based on essential gene database and toxicity prediction
- Druggability: Based on druggability and structural accessibility
- Novelty: Based on literature and patent novelty
- Weights: w₁=0.35, w₂=0.25, w₃=0.25, w₄=0.15 (configurable)

# 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
)

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

@software{in_silico_perturbation_oracle_2024,
  title={In Silico Perturbation Oracle: Virtual Gene Knockout Prediction},
  author={OpenClaw Bioinformatics Team},
  year={2024},
  url={https://github.com/openclaw/bio-skills}
}

# Python dependencies
pip install -r requirements.txt