Protein Interaction Network Analysis

from tooluniverse import ToolUniverse
from python_implementation import analyze_protein_network

# Initialize ToolUniverse
tu = ToolUniverse()

# Analyze protein network
result = analyze_protein_network(
    tu=tu,
    proteins=["TP53", "MDM2", "ATM", "CHEK2"],
    species=9606,  # Human
    confidence_score=0.7  # High confidence
)

# Access results
print(f"Mapped: {len(result.mapped_proteins)} proteins")
print(f"Network: {result.total_interactions} interactions")
print(f"Enrichment: {len(result.enriched_terms)} GO terms")
print(f"PPI p-value: {result.ppi_enrichment.get('p_value', 1.0):.2e}")

🔍 Phase 1: Mapping 4 protein identifiers...
✅ Mapped 4/4 proteins (100.0%)

🕸️  Phase 2: Retrieving interaction network...
✅ STRING: Retrieved 6 interactions

🧬 Phase 3: Performing enrichment analysis...
✅ Found 245 enriched GO terms (FDR < 0.05)
✅ PPI enrichment significant (p=3.45e-05)

✅ Analysis complete!

result = analyze_protein_network(
    tu=tu,
    proteins=["TP53"],  # Single protein
    species=9606,
    confidence_score=0.7
)

# Top 5 partners will be in the network
for edge in result.network_edges[:5]:
    print(f"{edge['preferredName_A']} ↔ {edge['preferredName_B']} "
          f"(score: {edge['score']})")

# DNA damage response proteins
proteins = ["TP53", "ATM", "CHEK2", "BRCA1", "BRCA2"]

result = analyze_protein_network(tu=tu, proteins=proteins)

# Check PPI enrichment
if result.ppi_enrichment.get("p_value", 1.0) < 0.05:
    print("✅ Proteins form functional module!")
    print(f"   Expected edges: {result.ppi_enrichment['expected_number_of_edges']:.1f}")
    print(f"   Observed edges: {result.ppi_enrichment['number_of_edges']}")
else:
    print("⚠️  Proteins may be unrelated")

result = analyze_protein_network(
    tu=tu,
    proteins=["MAPK1", "MAPK3", "RAF1", "MAP2K1"],  # MAPK pathway
    confidence_score=0.7
)

# Show top enriched processes
print("\nTop Enriched Pathways:")
for term in result.enriched_terms[:10]:
    print(f"  {term['term']}: p={term['p_value']:.2e}, FDR={term['fdr']:.2e}")

# Apoptosis regulators
proteins = ["TP53", "BCL2", "BAX", "CASP3", "CASP9"]

result = analyze_protein_network(
    tu=tu,
    proteins=proteins,
    confidence_score=0.7
)

# Export network for Cytoscape
import pandas as pd
df = pd.DataFrame(result.network_edges)
df.to_csv("apoptosis_network.tsv", sep="\t", index=False)

# Requires BIOGRID_API_KEY in environment
result = analyze_protein_network(
    tu=tu,
    proteins=["TP53", "MDM2"],
    include_biogrid=True  # Enable BioGRID fallback
)

print(f"Primary source: {result.primary_source}")  # "STRING" or "BioGRID"

result = analyze_protein_network(
    tu=tu,
    proteins=["TP53"],
    include_structure=True  # Query SASBDB
)

if result.structural_data:
    print(f"\nFound {len(result.structural_data)} SAXS/SANS entries:")
    for entry in result.structural_data:
        print(f"  {entry.get('sasbdb_id')}: {entry.get('title')}")

@dataclass
class ProteinNetworkResult:
    # Phase 1: Identifier mapping
    mapped_proteins: List[Dict[str, Any]]
    mapping_success_rate: float

    # Phase 2: Network retrieval
    network_edges: List[Dict[str, Any]]
    total_interactions: int

    # Phase 3: Enrichment analysis
    enriched_terms: List[Dict[str, Any]]
    ppi_enrichment: Dict[str, Any]

    # Phase 4: Structural data (optional)
    structural_data: Optional[List[Dict[str, Any]]]

    # Metadata
    primary_source: str  # "STRING" or "BioGRID"
    warnings: List[str]

{
    "stringId_A": "9606.ENSP00000269305",  # Protein A STRING ID
    "stringId_B": "9606.ENSP00000258149",  # Protein B STRING ID
    "preferredName_A": "TP53",             # Protein A name
    "preferredName_B": "MDM2",             # Protein B name
    "ncbiTaxonId": 9606,                   # Species
    "score": 0.999,                        # Combined confidence (0-1)
    "nscore": 0.0,                         # Neighborhood score
    "fscore": 0.0,                         # Gene fusion score
    "pscore": 0.0,                         # Phylogenetic profile score
    "ascore": 0.947,                       # Coexpression score
    "escore": 0.951,                       # Experimental score
    "dscore": 0.9,                         # Database score
    "tscore": 0.994                        # Text mining score
}

{
    "category": "Process",                  # GO category
    "term": "GO:0006915",                   # GO term ID
    "description": "apoptotic process",     # Term description
    "number_of_genes": 4,                   # Genes in your set
    "number_of_genes_in_background": 1234, # Genes in genome
    "p_value": 1.23e-05,                    # Enrichment p-value
    "fdr": 0.0012,                          # FDR correction
    "inputGenes": "TP53,MDM2,BAX,CASP3"    # Matching genes
}

┌─────────────────────────────────────────────────────────────┐
│ Phase 1: Identifier Mapping                                 │
│ ─────────────────────────────────────────────────────────── │
│ STRING_map_identifiers()                                    │
│   • Validates protein names exist in database              │
│   • Converts to STRING IDs for consistency                 │
│   • Returns mapping success rate                           │
└─────────────────────────────────────────────────────────────┘
                            ↓
┌─────────────────────────────────────────────────────────────┐
│ Phase 2: Network Retrieval                                  │
│ ─────────────────────────────────────────────────────────── │
│ PRIMARY: STRING_get_network() (no API key needed)          │
│   • Retrieves all pairwise interactions                    │
│   • Returns confidence scores by evidence type             │
│                                                             │
│ FALLBACK: BioGRID_get_interactions() (if enabled)          │
│   • Used if STRING fails or for validation                 │
│   • Requires BIOGRID_API_KEY                               │
└─────────────────────────────────────────────────────────────┘
                            ↓
┌─────────────────────────────────────────────────────────────┐
│ Phase 3: Enrichment Analysis                                │
│ ─────────────────────────────────────────────────────────── │
│ STRING_functional_enrichment()                              │
│   • GO terms (Process, Component, Function)                │
│   • KEGG pathways                                           │
│   • Reactome pathways                                       │
│   • FDR-corrected p-values                                  │
│                                                             │
│ STRING_ppi_enrichment()                                     │
│   • Tests if proteins interact more than random            │
│   • Returns p-value for functional coherence               │
└─────────────────────────────────────────────────────────────┘
                            ↓
┌─────────────────────────────────────────────────────────────┐
│ Phase 4: Structural Data (Optional)                         │
│ ─────────────────────────────────────────────────────────── │
│ SASBDB_search_entries()                                     │
│   • SAXS/SANS solution structures                           │
│   • Protein flexibility and conformations                   │
│   • Complements crystal/cryo-EM data                       │
└─────────────────────────────────────────────────────────────┘

# Install ToolUniverse (if not already installed)
pip install tooluniverse

# Or with extras
pip install tooluniverse[all]

tooluniverse-protein-interactions/
├── SKILL.md                    # This file
├── python_implementation.py    # Main implementation
├── QUICK_START.md             # Quick reference
├── DOMAIN_ANALYSIS.md         # Design rationale
├── PHASE2_COMPLETE.md         # Tool testing results
├── PHASE4_IMPLEMENTATION_COMPLETE.md
└── KNOWN_ISSUES.md            # ToolUniverse limitations

python your_script.py 2>&1 | grep -v "Error loading tools"