Tooluniverse Systems BiologySAFE

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: tooluniverse-systems-biology
description: Comprehensive systems biology and pathway analysis using multiple pathway databases (Reactome, KEGG, WikiPathways, Pathway Commons, BioModels). Performs pathway enrichment, protein-pathway mapping, keyword searches, and systems-level analysis. Use when analyzing gene sets, exploring biological pathways, or investigating systems-level biology.
---

# Systems Biology & Pathway Analysis

Comprehensive pathway and systems biology analysis integrating multiple curated databases to provide multi-dimensional view of biological systems, pathway enrichment, and protein-pathway relationships.

## When to Use This Skill

**Triggers**:
- "Analyze pathways for this gene list"
- "What pathways is [protein] involved in?"
- "Find pathways related to [keyword/process]"
- "Perform pathway enrichment analysis"
- "Map proteins to biological pathways"
- "Find computational models for [process]"
- "Systems biology analysis of [genes/proteins]"

**Use Cases**:
1. **Gene Set Analysis**: Identify enriched pathways from RNA-seq, proteomics, or screen results
2. **Protein Function**: Discover pathways and processes a protein participates in
3. **Pathway Discovery**: Find pathways related to diseases, processes, or phenotypes
4. **Systems Integration**: Connect genes → pathways → processes → diseases
5. **Model Discovery**: Find computational systems biology models (SBML)
6. **Cross-Database Validation**: Compare pathway annotations across multiple sources

## Core Databases Integrated

| Database | Coverage | Strengths |
|----------|----------|-----------|
| **Reactome** | Human-curated reactions & pathways | Detailed mechanistic pathways with reactions |
| **KEGG** | Reference pathways across organisms | Metabolic maps, disease pathways, drug targets |
| **WikiPathways** | Community-curated pathways | Emerging processes, collaborative updates |
| **Pathway Commons** | Integrated meta-database | Aggregates multiple sources (Reactome, KEGG, etc.) |
| **BioModels** | Computational SBML models | Mathematical/dynamic systems biology models |
| **Enrichr** | Statistical enrichment | Pathway over-representation analysis |

## Workflow Overview

```
Input → Phase 1: Enrichment → Phase 2: Protein Mapping → Phase 3: Keyword Search → Phase 4: Top Pathways → Report
```

---

## Phase 1: Pathway Enrichment Analysis

**When**: Gene list provided (from experiments, screens, differentially expressed genes)

**Objective**: Identify biological pathways statistically over-represented in gene list

### Tools Used

**enrichr_gene_enrichment_analysis**:
- **Input**:
  - `gene_list`: Array of gene symbols (e.g., ["TP53", "BRCA1", "EGFR"])
  - `library`: Pathway database (e.g., "KEGG_2021_Human", "Reactome_2022")
- **Output**: Array of enriched pathways with p-values, adjusted p-values, genes
- **Use**: Statistical over-representation analysis

### Workflow

1. Submit gene list to Enrichr
2. Query KEGG pathway library for human
3. Get enriched pathways sorted by significance
4. Extract:
   - Pathway names and IDs
   - P-values (raw and adjusted)
   - Genes from input list in each pathway
   - Enrichment scores

### Decision Logic

- **Significance threshold**: Adjusted p-value < 0.05 (default)
- **Minimum genes**: At least 2 genes from input list in pathway
- **Report top pathways**: Show 10-20 most significant
- **Empty results**: If no enrichment → note "no significant pathways" (don't fail)

---

## Phase 2: Protein-Pathway Mapping

**When**: Protein UniProt ID provided

**Objective**: Map protein to all known pathways it participates in

### Tools Used

**Reactome_map_uniprot_to_pathways**:
- **Input**:
  - `id`: UniProt accession (e.g., "P53350")
- **Output**: Array of Reactome pathways containing this protein
- **Note**: Parameter is `id` (not `uniprot_id`)

**Reactome_get_pathway_reactions**:
- **Input**:
  - `stId`: Reactome pathway stable ID (e.g., "R-HSA-73817")
- **Output**: Array of reactions and subpathways
- **Use**: Get mechanistic details of pathways

### Workflow

1. Map UniProt ID to Reactome pathways
2. Get all pathways this protein appears in
3. For top pathway (or user-specified):
   - Retrieve detailed reactions and subpathways
   - Extract event names, types (Reaction vs Pathway)
   - Note disease associations if present

### Decision Logic

- **Multiple pathways**: Report all pathways, prioritize by hierarchical level
- **Top pathway details**: Get detailed reactions for 1-3 most relevant
- **Versioned IDs**: Reactome uses unversioned IDs - strip version if present
- **Empty results**: Check if protein ID valid; suggest alternative databases if Reactome empty

---

## Phase 3: Keyword-Based Pathway Search

**When**: User provides keyword or biological process name

**Objective**: Search multiple pathway databases to find relevant pathways

### Tools Used

#### KEGG Search
**kegg_search_pathway**:
- **Input**: `keyword` (e.g., "diabetes", "apoptosis")
- **Output**: Array of pathway IDs and descriptions
- **Coverage**: Reference pathways, metabolism, diseases

**kegg_get_pathway_info**:
- **Input**: `pathway_id` (e.g., "hsa04930")
- **Output**: Pathway details, genes, compounds
- **Use**: Get detailed information for specific pathway

#### WikiPathways Search
**WikiPathways_search**:
- **Input**:
  - `query`: Keyword or gene symbol
  - `organism`: Species filter (e.g., "Homo sapiens")
- **Output**: Array of pathway matches with IDs, names, URLs
- **Coverage**: Community-curated, includes emerging pathways

#### Pathway Commons Search
**pc_search_pathways**:
- **Input**:
  - `action`: "search_pathways"
  - `keyword`: Search term
  - `datasource`: Optional filter (e.g., "reactome", "kegg")
  - `limit`: Max results (default: 10)
- **Output**: Total hits and array of pathways with source attribution
- **Coverage**: Meta-database aggregating multiple sources

#### BioModels Search
**biomodels_search**:
- **Input**:
  - `query`: Keyword for computational models
  - `lim

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

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (1)

.env.template

Gates applied: no_behavioural_pass.