String DatabaseSAFE

The largest open-source medical AI skills library for OpenClaw🦞.

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: string-database
description: "Query STRING API for protein-protein interactions (59M proteins, 20B interactions). Network analysis, GO/KEGG enrichment, interaction discovery, 5000+ species, for systems biology."
---

# STRING Database

## Overview

STRING is a comprehensive database of known and predicted protein-protein interactions covering 59M proteins and 20B+ interactions across 5000+ organisms. Query interaction networks, perform functional enrichment, discover partners via REST API for systems biology and pathway analysis.

## When to Use This Skill

This skill should be used when:
- Retrieving protein-protein interaction networks for single or multiple proteins
- Performing functional enrichment analysis (GO, KEGG, Pfam) on protein lists
- Discovering interaction partners and expanding protein networks
- Testing if proteins form significantly enriched functional modules
- Generating network visualizations with evidence-based coloring
- Analyzing homology and protein family relationships
- Conducting cross-species protein interaction comparisons
- Identifying hub proteins and network connectivity patterns

## Quick Start

The skill provides:
1. Python helper functions (`scripts/string_api.py`) for all STRING REST API operations
2. Comprehensive reference documentation (`references/string_reference.md`) with detailed API specifications

When users request STRING data, determine which operation is needed and use the appropriate function from `scripts/string_api.py`.

## Core Operations

### 1. Identifier Mapping (`string_map_ids`)

Convert gene names, protein names, and external IDs to STRING identifiers.

**When to use**: Starting any STRING analysis, validating protein names, finding canonical identifiers.

**Usage**:
```python
from scripts.string_api import string_map_ids

# Map single protein
result = string_map_ids('TP53', species=9606)

# Map multiple proteins
result = string_map_ids(['TP53', 'BRCA1', 'EGFR', 'MDM2'], species=9606)

# Map with multiple matches per query
result = string_map_ids('p53', species=9606, limit=5)
```

**Parameters**:
- `species`: NCBI taxon ID (9606 = human, 10090 = mouse, 7227 = fly)
- `limit`: Number of matches per identifier (default: 1)
- `echo_query`: Include query term in output (default: 1)

**Best practice**: Always map identifiers first for faster subsequent queries.

### 2. Network Retrieval (`string_network`)

Get protein-protein interaction network data in tabular format.

**When to use**: Building interaction networks, analyzing connectivity, retrieving interaction evidence.

**Usage**:
```python
from scripts.string_api import string_network

# Get network for single protein
network = string_network('9606.ENSP00000269305', species=9606)

# Get network with multiple proteins
proteins = ['9606.ENSP00000269305', '9606.ENSP00000275493']
network = string_network(proteins, required_score=700)

# Expand network with additional interactors
network = string_network('TP53', species=9606, add_nodes=10, required_score=400)

# Physical interactions only
network = string_network('TP53', species=9606, network_type='physical')
```

**Parameters**:
- `required_score`: Confidence threshold (0-1000)
  - 150: low confidence (exploratory)
  - 400: medium confidence (default, standard analysis)
  - 700: high confidence (conservative)
  - 900: highest confidence (very stringent)
- `network_type`: `'functional'` (all evidence, default) or `'physical'` (direct binding only)
- `add_nodes`: Add N most connected proteins (0-10)

**Output columns**: Interaction pairs, confidence scores, and individual evidence scores (neighborhood, fusion, coexpression, experimental, database, text-mining).

### 3. Network Visualization (`string_network_image`)

Generate network visualization as PNG image.

**When to use**: Creating figures, visual exploration, presentations.

**Usage**:
```python
from scripts.string_api import string_network_image

# Get network image
proteins = ['TP53', 'MDM2', 'ATM', 'CHEK2', 'BRCA1']
img_data = string_network_image(proteins, species=9606, required_score=700)

# Save image
with open('network.png', 'wb') as f:
    f.write(img_data)

# Evidence-colored network
img = string_network_image(proteins, species=9606, network_flavor='evidence')

# Confidence-based visualization
img = string_network_image(proteins, species=9606, network_flavor='confidence')

# Actions network (activation/inhibition)
img = string_network_image(proteins, species=9606, network_flavor='actions')
```

**Network flavors**:
- `'evidence'`: Colored lines show evidence types (default)
- `'confidence'`: Line thickness represents confidence
- `'actions'`: Shows activating/inhibiting relationships

### 4. Interaction Partners (`string_interaction_partners`)

Find all proteins that interact with given protein(s).

**When to use**: Discovering novel interactions, finding hub proteins, expanding networks.

**Usage**:
```python
from scripts.string_api import string_interaction_partners

# Get top 10 interactors of TP53
partners = string_interaction_partners('TP53', species=9606, limit=10)

# Get high-confidence interactors
partners = string_interaction_partners('TP53', species=9606,
                                      limit=20, required_score=700)

# Find interactors for multiple proteins
partners = string_interaction_partners(['TP53', 'MDM2'],
                                      species=9606, limit=15)
```

**Parameters**:
- `limit`: Maximum number of partners to return (default: 10)
- `required_score`: Confidence threshold (0-1000)

**Use cases**:
- Hub protein identification
- Network expansion from seed proteins
- Discovering indirect connections

### 5. Functional Enrichment (`string_enrichment`)

Perform enrichment analysis across Gene Ontology, KEGG pathways, Pfam domains, and more.

**When to use**: Interpreting protein lists, pathway analysis, functional characterization, understanding biological processes.

**Usage**:
```python
from scripts.string_enrichment import 

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

declared (5 observation(s))

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.