hmdb-database

Parses local Human Metabolome Database XML files to retrieve metabolite information.

298|27|Updated Feb 18, 2026
One-click install
npx skills add https://github.com/jaechang-hits/SciAgent-Skills --skill hmdb-database-jaechang-hits
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: hmdb-database
Source: https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/proteomics-protein-engineering/hmdb-database
Command: npx skills add https://github.com/jaechang-hits/SciAgent-Skills --skill hmdb-database-jaechang-hits

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires lxml, pandas, and includes references (resource) components.

What problem does it solve?

This Skill enables programmatic access to comprehensive metabolite information from the Human Metabolome Database (HMDB) by parsing a locally downloaded XML file, overcoming the lack of a public REST API.

Core Features & Use Cases

  • Metabolite Lookup: Retrieve detailed information on over 220,000 metabolites by HMDB ID or name.
  • Property Extraction: Access chemical properties, biological context (pathways, locations), disease associations, spectral data, and cross-database identifiers.
  • Use Case: Identify potential biomarkers for a disease by querying HMDB for metabolites associated with specific conditions and their abnormal concentration ranges in biological fluids.

Quick Start

Use the hmdb-database skill to find the chemical formula for glucose using its HMDB ID 'HMDB0000122'.

Frequently Asked Questions about hmdb-database

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

FAQPage Schema
How do I query the Human Metabolome Database locally without a public REST API?

You can query the Human Metabolome Database by downloading the HMDB XML file locally and parsing it with Python libraries like lxml and pandas to retrieve detailed metabolite information programmatically.

Can I extract disease associations and biological pathways for specific metabolites from HMDB?

Yes, parsing the HMDB XML allows you to extract biological context including disease associations, biological pathways, concentrations, and cross-database identifiers for over 220,000 metabolites.

How do I retrieve chemical properties for a metabolite using its HMDB ID?

You can retrieve chemical properties by providing the specific HMDB ID, such as 'HMDB0000122' for glucose, to parse the local XML file and extract the associated chemical data.

Do I need to download the entire HMDB XML file to perform metabolomics data analysis?

Yes, a local XML download of the HMDB is required. The Skill processes this local file to perform metabolomics data analysis, overcoming the lack of a public REST API for direct database access.

What is the best way to find potential biomarkers for a disease using HMDB metabolite data?

The best way to find potential biomarkers is to query the local HMDB XML for metabolites associated with specific conditions and extract their abnormal concentration ranges in biological fluids.

Does parsing the HMDB XML with lxml work for extracting spectral data and cross-database mappings?

Yes, using lxml to parse the HMDB XML works for extracting spectral data, biological locations, and cross-database mappings, providing comprehensive metabolite details for bioinformatics research.