Hmdb Database logo

Hmdb Database

Community
jimmc414
hmdb-database

Access Human Metabolome Database (220K+ metabolites). Search by name/ID/structure, retrieve chemical properties, biomarker data, NMR/MS spectra, pathways, for metabolomics and identification.

Overview

Publisherjimmc414
RepositoryKosmos
Skill namehmdb-database
Stars
585
Forks
105
Bundled files
1
Links
Skill sourceRepository
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by jimmc414 on GitHub. Read the source before you install it.

Installation

Install the Hmdb Database AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jimmc414/Kosmos.git /tmp/Kosmos
mkdir -p .claude/skills
cp -r /tmp/Kosmos/kosmos-claude-scientific-skills/scientific-skills/hmdb-database .claude/skills/hmdb-database
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Hmdb Database in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Hmdb Database on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Hmdb Database is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

HMDB Database

Overview

The Human Metabolome Database (HMDB) is a comprehensive, freely available resource containing detailed information about small molecule metabolites found in the human body.

When to Use This Skill

This skill should be used when performing metabolomics research, clinical chemistry, biomarker discovery, or metabolite identification tasks.

Database Contents

HMDB version 5.0 (current as of 2025) contains:

  • 220,945 metabolite entries covering both water-soluble and lipid-soluble compounds
  • 8,610 protein sequences for enzymes and transporters involved in metabolism
  • 130+ data fields per metabolite including:
    • Chemical properties (structure, formula, molecular weight, InChI, SMILES)
    • Clinical data (biomarker associations, diseases, normal/abnormal concentrations)
    • Biological information (pathways, reactions, locations)
    • Spectroscopic data (NMR, MS, MS-MS spectra)
    • External database links (KEGG, PubChem, MetaCyc, ChEBI, PDB, UniProt, GenBank)

Core Capabilities

1. Web-Based Metabolite Searches

Access HMDB through the web interface at https://www.hmdb.ca/ for:

Text Searches:

  • Search by metabolite name, synonym, or identifier (HMDB ID)
  • Example HMDB IDs: HMDB0000001, HMDB0001234
  • Search by disease associations or pathway involvement
  • Query by biological specimen type (urine, serum, CSF, saliva, feces, sweat)

Structure-Based Searches:

  • Use ChemQuery for structure and substructure searches
  • Search by molecular weight or molecular weight range
  • Use SMILES or InChI strings to find compounds

Spectral Searches:

  • LC-MS spectral matching
  • GC-MS spectral matching
  • NMR spectral searches for metabolite identification

Advanced Searches:

  • Combine multiple criteria (name, properties, concentration ranges)
  • Filter by biological locations or specimen types
  • Search by protein/enzyme associations

2. Accessing Metabolite Information

When retrieving metabolite data, HMDB provides:

Chemical Information:

  • Systematic name, traditional names, and synonyms
  • Chemical formula and molecular weight
  • Structure representations (2D/3D, SMILES, InChI, MOL file)
  • Chemical taxonomy and classification

Biological Context:

  • Metabolic pathways and reactions
  • Associated enzymes and transporters
  • Subcellular locations
  • Biological roles and functions

Clinical Relevance:

  • Normal concentration ranges in biological fluids
  • Biomarker associations with diseases
  • Clinical significance
  • Toxicity information when applicable

Analytical Data:

  • Experimental and predicted NMR spectra
  • MS and MS-MS spectra
  • Retention times and chromatographic data
  • Reference peaks for identification

3. Downloadable Datasets

HMDB offers bulk data downloads at https://www.hmdb.ca/downloads in multiple formats:

Available Formats:

  • XML: Complete metabolite, protein, and spectra data
  • SDF: Metabolite structure files for cheminformatics
  • FASTA: Protein and gene sequences
  • TXT: Raw spectra peak lists
  • CSV/TSV: Tabular data exports

Dataset Categories:

  • All metabolites or filtered by specimen type
  • Protein/enzyme sequences
  • Experimental and predicted spectra (NMR, GC-MS, MS-MS)
  • Pathway information

Best Practices:

  • Download XML format for comprehensive data including all fields
  • Use SDF format for structure-based analysis and cheminformatics workflows
  • Parse CSV/TSV formats for integration with data analysis pipelines
  • Check version dates to ensure up-to-date data (current: v5.0, 2023-07-01)

Usage Requirements:

  • Free for academic and non-commercial research
  • Commercial use requires explicit permission (contact samackay@ualberta.ca)
  • Cite HMDB publication when using data

4. Programmatic API Access

API Availability: HMDB does not provide a public REST API. Programmatic access requires contacting the development team:

Alternative Programmatic Access:

  • R/Bioconductor: Use the hmdbQuery package for R-based queries
    • Install: BiocManager::install("hmdbQuery")
    • Provides HTTP-based querying functions
  • Downloaded datasets: Parse XML or CSV files locally for programmatic analysis
  • Web scraping: Not recommended; contact team for proper API access instead

5. Common Research Workflows

Metabolite Identification in Untargeted Metabolomics:

  1. Obtain experimental MS or NMR spectra from samples
  2. Use HMDB spectral search tools to match against reference spectra
  3. Verify candidates by checking molecular weight, retention time, and MS-MS fragmentation
  4. Review biological plausibility (expected in specimen type, known pathways)

Biomarker Discovery:

  1. Search HMDB for metabolites associated with disease of interest
  2. Review concentration ranges in normal vs. disease states
  3. Identify metabolites with strong differential abundance
  4. Examine pathway context and biological mechanisms
  5. Cross-reference with literature via PubMed links

Pathway Analysis:

  1. Identify metabolites of interest from experimental data
  2. Look up HMDB entries for each metabolite
  3. Extract pathway associations and enzymatic reactions
  4. Use linked SMPDB (Small Molecule Pathway Database) for pathway diagrams
  5. Identify pathway enrichment for biological interpretation

Database Integration:

  1. Download HMDB data in XML or CSV format
  2. Parse and extract relevant fields for local database
  3. Link with external IDs (KEGG, PubChem, ChEBI) for cross-database queries
  4. Build local tools or pipelines incorporating HMDB reference data

Related HMDB Resources

The HMDB ecosystem includes related databases:

  • DrugBank: ~2,832 drug compounds with pharmaceutical information
  • T3DB (Toxin and Toxin Target Database): ~3,670 toxic compounds
  • SMPDB (Small Molecule Pathway Database): Pathway diagrams and maps
  • FooDB: ~70,000 food component compounds

These databases share similar structure and identifiers, enabling integrated queries across human metabolome, drug, toxin, and food databases.

Best Practices

Data Quality:

  • Verify metabolite identifications with multiple evidence types (spectra, structure, properties)
  • Check experimental vs. predicted data quality indicators
  • Review citations and evidence for biomarker associations

Version Tracking:

  • Note HMDB version used in research (current: v5.0)
  • Databases are updated periodically with new entries and corrections
  • Re-query for updates when publishing to ensure current information

Citation:

  • Always cite HMDB in publications using the database
  • Reference specific HMDB IDs when discussing metabolites
  • Acknowledge data sources for downloaded datasets

Performance:

  • For large-scale analysis, download complete datasets rather than repeated web queries
  • Use appropriate file formats (XML for comprehensive data, CSV for tabular analysis)
  • Consider local caching of frequently accessed metabolite information

Reference Documentation

See references/hmdb_data_fields.md for detailed information about available data fields and their meanings.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Hmdb Database AI skill do?

Access Human Metabolome Database (220K+ metabolites). Search by name/ID/structure, retrieve chemical properties, biomarker data, NMR/MS spectra, pathways, for metabolomics and identification.

Why use Hmdb Database on TypingMind?

Because you install it once and use it with any model. Hmdb Database is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Hmdb Database in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jimmc414/Kosmos/tree/master/kosmos-claude-scientific-skills/scientific-skills/hmdb-database. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Hmdb Database?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Hmdb Database?

As many as you like. As long as a model supports skills, you can use Hmdb Database with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Hmdb Database AI skill free?

It is published on GitHub by jimmc414. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
code-yeongyu logo

Data Scientist

code-yeongyu
CommunityPopular

Processes and analyzes data with resident-kernel engines (DuckDB, Polars) and one-shot tools. Use for CSV/parquet/JSON analysis, group-by/join/aggregation, time series, distributions, cleaning, or…

5.7K
69.1K
10 files
View
tt-a1i logo

Archify

tt-a1i
CommunityPopular

Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and…

4.4K
65.8K
195 files
View
coreyhaines31 logo

Ab Testing

coreyhaines31
CommunityPopular

When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test…

7.7K
50.7K
3 files
View
coreyhaines31 logo

Ai Seo

coreyhaines31
CommunityPopular

When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers. Also use when the user mentions 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine…

7.7K
50.7K
9 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇