How do I visualize interaction networks?

The skill provides a string_network_image function that generates PNG files with evidence, confidence, or action-based coloring.

How does the skill handle different confidence levels?

Users can set a required_score between 0 and 1000, where 400 is medium confidence and 900 is the highest stringency.

Does it support species other than humans?

Yes, it supports over 5,000 organisms, including mouse, rat, yeast, and many others, using NCBI taxon IDs.

What databases are used for functional enrichment?

Enrichment analysis includes Gene Ontology (GO), KEGG pathways, Pfam domains, InterPro, SMART, and UniProt keywords.

What is the STRING Database skill?

It is a specialized Claude Code capability that interfaces with the STRING REST API to perform advanced protein network analysis and functional characterization.

STRING Database & PPI Analysis

Name: STRING Database & PPI Analysis
Author: jimmc414

byjimmc414

•

324

Data Science & ML

Queries the STRING database for protein-protein interaction networks, functional enrichment, and biological pathway analysis.

About

The STRING Database skill integrates comprehensive systems biology capabilities into Claude, allowing for the analysis of over 20 billion protein interactions across 5,000+ species. It enables researchers to map identifiers, retrieve interaction networks with varying confidence thresholds, and perform functional enrichment across Gene Ontology (GO) and KEGG pathways. By providing Python-based automation for the STRING REST API, this skill streamlines complex bioinformatics workflows, including network visualization, homology scoring, and statistical testing for protein module connectivity.

Key Features

324 GitHub stars
Generate evidence-based network visualizations in PNG format
Map gene and protein identifiers to canonical STRING IDs across thousands of species
Calculate PPI enrichment p-values to identify functional modules within protein sets
Query protein-protein interaction networks for 59M+ proteins with confidence scoring
Perform functional enrichment analysis for GO, KEGG, Pfam, and InterPro domains

Use Cases

Conducting cross-species comparisons of protein families and homology
Identifying hub proteins and expanding seed networks with novel interaction partners
Interpreting proteomics or differential expression data through pathway enrichment

About

Key Features

324 GitHub stars
Generate evidence-based network visualizations in PNG format
Map gene and protein identifiers to canonical STRING IDs across thousands of species
Calculate PPI enrichment p-values to identify functional modules within protein sets
Query protein-protein interaction networks for 59M+ proteins with confidence scoring
Perform functional enrichment analysis for GO, KEGG, Pfam, and InterPro domains

Use Cases

Conducting cross-species comparisons of protein families and homology
Identifying hub proteins and expanding seed networks with novel interaction partners
Interpreting proteomics or differential expression data through pathway enrichment