skills.rest
arslan9024
arslan9024COMMUNITY
Explore all skills by this author →
GitHub

string-database

Query the STRING API for protein-protein interactions, functional enrichment, and homology data.

Updated Jan 8, 2026
Search Tags:#bioinformatics#pathway analysis#homology#string database#protein interactions#functional enrichment#ppi network
One-click install
npx skills add https://github.com/arslan9024/White-Caves --skill string-database-arslan9024
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: string-database
Source: https://github.com/arslan9024/White-Caves/tree/main/.agents/skills/string_database
Command: npx skills add https://github.com/arslan9024/White-Caves --skill string-database-arslan9024

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires polite-http, and includes scripts (resource) and references (resource) components.

What problem does it solve? Retrieving protein-protein interaction networks, pathway enrichment results, and homology scores from the STRING database normally requires manual API calls and response parsing. This Skill wraps the STRING API v12 in a Python CLI so an AI assistant can run structured queries and save results directly to TSV or image files. ## Core Features & Use Cases - Interaction Networks & Partners: Retrieve interaction networks, top interaction partners, confidence scores, and network images (PNG/SVG) for a set of proteins. - Functional Enrichment: Run GO, KEGG, Pfam, and InterPro enrichment, PPI significance tests, and term-based protein searches (e.g., all proteins linked to Melanoma). - Homology & Rank-Based Analysis: Compute Smith-Waterman homology scores, cross-species best hits, and submit full ranked datasets (logFC, p-values) to the asynchronous Values/Ranks enrichment API. - Use Case: A researcher studying the p53 pathway in mouse can map gene names like Trp53 and Mdm2 to STRING IDs, pull the extended interaction network with 10 added nodes, and generate a high-resolution network image in one workflow. ## Quick Start Ask the assistant to find the interaction partners of BRCA1 in human (NCBI Taxon ID 9606) using the STRING database and save the results to a file.

Frequently Asked Questions about string-database

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I query the STRING database for protein interactions from the command line?▼

Run the bundled CLI with uv: uv run scripts/string_cli.py network --identifiers Trp53 Mdm2 --species 10090 --output /tmp/out.tsv. The network command returns interaction pairs with confidence scores, and you can add --add_nodes to expand the neighborhood.

How do I map gene names like TP53 to STRING identifiers?▼

Use the map command: uv run scripts/string_cli.py map --identifiers TP53 BRCA1 --species 9606 --output /tmp/mapped.tsv. Mapping common names to STRING IDs first guarantees much faster responses for subsequent network or enrichment queries.

Why does the STRING skill require an NCBI Taxon ID for every query?▼

The STRING API scopes all interactions and annotations by organism, so commands like network, enrichment, and homology require the --species parameter with an NCBI Taxon ID such as 9606 for human or 10090 for mouse. The skill never assumes a species and will ask if one is not provided.

Can I run pathway enrichment on a full ranked gene list with STRING?▼

Yes, the Values/Ranks API accepts complete datasets of identifiers with numeric values like logFC or p-values. Obtain an API key with valuesranks-key, submit a tab-separated file via valuesranks-submit, then poll or wait with valuesranks-status to download the enrichment TSV.

What output formats does the STRING CLI support?▼

Most commands write TSV files, while the image command produces PNG or SVG network visualizations and the Values/Ranks endpoints return JSON. All output must be written to a file via the required --output flag rather than printed to stdout.

Related Skills

Explore More Education & Research Skills→
MDheweiMDhewei
64

gene-list-curator

Curate literature-backed gene lists into a structured table with references.

Community
Intermediate
dailycafidailycafi
7

bio-metabolomics-pathway-mapping

Map metabolites to KEGG, Reactome, and SMPDB pathways with enrichment and topology analysis.

Community
Intermediate
openaiopenai
5.3k

quickgo-skill

Query the QuickGO REST API for GO terms, annotations, and ontology traversal.

Official
Intermediate
mims-harvardmims-harvard
1.7k

tooluniverse-protein-interactions

Analyze protein-protein interaction networks using STRING, BioGRID, and SASBDB databases.

Official
Advanced