kegg-database

Query KEGG pathways, genes, compounds, and drugs via REST API endpoints.

33.0k|3.2k|Updated Oct 19, 2025
One-click install
npx skills add https://github.com/K-Dense-AI/claude-scientific-skills --skill kegg-database
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: kegg-database
Source: https://github.com/K-Dense-AI/claude-scientific-skills/tree/main/scientific-databases/kegg-database
Command: npx skills add https://github.com/K-Dense-AI/claude-scientific-skills --skill kegg-database

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Manually extracting and integrating biological pathway, gene, and compound data from KEGG is tedious and prone to inconsistencies. This Skill automates access to the KEGG REST API, simplifying complex systems biology and enrichment analyses, allowing researchers to quickly uncover biological insights.

Core Features & Use Cases

  • Pathway & Gene Querying: Retrieve detailed information on metabolic pathways, genetic information, genes, and compounds across various organisms.
  • ID Conversion & Linking: Seamlessly convert identifiers between KEGG and external databases (e.g., UniProt, NCBI) and link related entries within KEGG.
  • Drug Interaction Analysis: Directly check for drug-drug interactions, aiding in pharmacological research and drug combination analysis.
  • Use Case: Given a list of differentially expressed genes, automatically map them to KEGG pathways to identify enriched biological processes, saving hours of manual lookup and cross-referencing.

Quick Start

List all human-specific pathways

from scripts.kegg_api import kegg_list hsa_pathways = kegg_list('pathway', 'hsa') print("First 3 human pathways:") print(' '.join(hsa_pathways.split(' ')[:3]))

Find genes by keyword (e.g., 'p53')

from scripts.kegg_api import kegg_find gene_results = kegg_find('genes', 'p53') print(" Genes matching 'p53':") print(' '.join(gene_results.split(' ')[:3]))

Frequently Asked Questions about kegg-database

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

FAQPage Schema
How do I access KEGG pathway and gene data programmatically?

Access KEGG pathway and gene data using the REST API via Python or HTTP requests to https://rest.kegg.jp. The Skill wraps core operations—kegg_list, kegg_find, kegg_get, kegg_conv, kegg_link, and kegg_ddi—returning raw text for parsing. Query pathways, genes, compounds, enzymes, diseases, and drugs across organisms with entry limits (max 10 per multi-entry request).

Can I convert gene IDs between KEGG and external databases like UniProt or NCBI?

Yes, the kegg_conv operation seamlessly converts identifiers between KEGG and external databases including UniProt and NCBI. Use it to link your gene lists to KEGG entries, enabling cross-database enrichment and systems biology analysis without manual lookup.

How do I map differentially expressed genes to KEGG pathways?

Query genes using kegg_find to identify KEGG entries, then use kegg_link to map them to metabolic pathways. Retrieve pathway details with kegg_get, automating enrichment analysis and reducing hours of manual cross-referencing to minutes.

Can I check drug-drug interactions using KEGG data?

Yes, the kegg_ddi operation directly checks for drug-drug interactions. Retrieve interaction data for pharmacological research and drug combination analysis without building custom interaction databases.

What output formats does KEGG REST API support?

KEGG REST API supports multiple output formats including aaseq, ntseq, mol, kcf, image, kgml, and json. Select the format matching your downstream analysis needs—sequence data, chemical structures, pathway diagrams, or structured data.

Are there usage restrictions for KEGG data access?

KEGG data access is restricted to academic use. Verify your use case qualifies before integrating into production systems or commercial workflows; the Skill enforces these academic-use restrictions.