How does the skill handle different gene or protein name formats?

It includes a robust identifier mapping operation that converts common gene names and external database IDs into canonical STRING identifiers to ensure data accuracy.

What types of functional enrichment analysis are available?

You can perform enrichment analysis for Gene Ontology (GO) Biological Process, Molecular Function, Cellular Component, KEGG pathways, Pfam domains, and UniProt keywords.

Can I visualize protein networks with this skill?

Yes, the skill can generate network visualizations as PNG files, offering different 'flavors' such as evidence-based coloring, confidence thickness, or action-based arrows.

What organisms does this skill support?

It supports over 5,000 organisms, including human (9606), mouse (10090), and fruit fly (7227), by utilizing NCBI taxon IDs for precise mapping.

STRING Protein Database Integration

Name: STRING Protein Database Integration
Author: pur3v4d3r

bypur3v4d3r

•

Data Science & ML

Retrieves and analyzes protein-protein interaction networks and functional enrichment data directly from the STRING database.

About

This skill integrates the STRING database into your Claude Code workflow, enabling advanced systems biology research and pathway analysis. It provides programmatic access to over 59 million proteins and 20 billion interactions across 5,000+ species. Users can seamlessly map gene identifiers, retrieve interaction networks with evidence-based scoring, perform GO/KEGG functional enrichment, and generate high-quality network visualizations. It is designed specifically for researchers and bioinformaticians looking to automate protein data collection and analyze functional modules within complex biological systems.

Key Features

Protein-protein interaction (PPI) network retrieval with weighted evidence scoring
Comprehensive functional enrichment analysis across GO, KEGG, and Pfam
Statistical PPI enrichment testing to validate functional protein modules
Automated identifier mapping for 5,000+ species using NCBI taxon IDs
High-quality PNG network visualization with customizable evidence coloring
1 GitHub stars

Use Cases

Interpreting differential expression results from proteomics or transcriptomics experiments
Conducting cross-species homology and evolutionary protein family comparisons
Discovering novel interaction partners and hub proteins in cellular signaling pathways

About

Key Features

Protein-protein interaction (PPI) network retrieval with weighted evidence scoring
Comprehensive functional enrichment analysis across GO, KEGG, and Pfam
Statistical PPI enrichment testing to validate functional protein modules
Automated identifier mapping for 5,000+ species using NCBI taxon IDs
High-quality PNG network visualization with customizable evidence coloring
1 GitHub stars

Use Cases

Interpreting differential expression results from proteomics or transcriptomics experiments
Conducting cross-species homology and evolutionary protein family comparisons
Discovering novel interaction partners and hub proteins in cellular signaling pathways